diff --git a/.env.sample b/.env.sample
index a76c5e9..f45ac6e 100644
--- a/.env.sample
+++ b/.env.sample
@@ -1,2 +1 @@
 OPENAI_API_KEY=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
-LLAMA_CLOUD_API_KEY=llx-MkHkuDxnSxXEHvsIPAtjEZl4iSB8pHS1mgYDVZQlA690LUub
\ No newline at end of file
diff --git a/Dockerfile b/Dockerfile
index 4e61a58..5f91811 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -7,8 +7,9 @@ ENV PYTHONUNBUFFERED=1 \
     PYTHONDONTWRITEBYTECODE=1 \
     PIP_NO_CACHE_DIR=1
 
-# Copy only requirements files first to leverage Docker cache
-COPY pyproject.toml ./ 
+# Copy only necessary files
+COPY pyproject.toml ./
+COPY requirements.txt ./
 
 # Install system and Python dependencies in a single layer
 RUN apt-get update && \
@@ -19,10 +20,20 @@ RUN apt-get update && \
     pip install --no-cache-dir --upgrade pip setuptools setuptools-scm && \
     rm -rf /var/lib/apt/lists/* 
 
-# Copy project files
-COPY . .
-
 # Install base project
-RUN pip install --no-cache-dir -e . 
+RUN pip install -r requirements.txt
 
-CMD ["bash"]
+# Copy project files
+COPY autorag /usr/src/app/autorag
+COPY main.py /usr/src/app/main.py
+COPY making.sh /usr/src/app/making.sh
+COPY entrypoint.sh /usr/src/app/entrypoint.sh
+
+# Set permissions for entrypoint
+RUN chmod +x /usr/src/app/entrypoint.sh
+
+# Use entrypoint.sh as the container entrypoint
+ENTRYPOINT ["/usr/src/app/entrypoint.sh"]
+
+# Set a default command (optional, can be overridden)
+CMD ["bash"]
\ No newline at end of file
diff --git a/README.md b/README.md
index ca3068a..036f3b3 100644
--- a/README.md
+++ b/README.md
@@ -1,51 +1,68 @@
-# AutoRAG Evaluation
+# 📊 AutoRAG Evaluation
 
-이 문서는 AutoRAG을 활용하여 RAG 파이프라인을 설정하고 평가하는 과정에 대한 안내입니다.
+AutoRAG Evaluation은 RAG(Relevance-Augmented Generation) 파이프라인을 평가하기 위한 도구입니다.  
+이 문서는 데이터 생성부터 RAG 평가 및 대시보드 활용까지의 전체 과정에 대한 안내를 제공합니다.
 
 ---
 
-## 📌 환경 세팅
+## **🚀 1. 환경 설정**
 
-1. `.env` 파일을 설정합니다. (`.env.sample` 참고)
-2. Docker 이미지를 빌드합니다.
+### **1️⃣ `.env` 파일 설정**
+
+`.env.sample` 파일을 참고하여 `.env` 파일을 생성하고 필요한 환경 변수를 설정합니다.
+
+### **2️⃣ Docker 이미지 빌드**
 
 ```bash
-   docker build -t autorag-base .
+docker build -t autorag-base .
 ```
 
-3. Docker Compose를 실행하여 서비스를 시작합니다.
+### **3️⃣ Docker Compose 백그라운드 실행**
 
 ```bash
-   docker compose up -d
+docker compose up -d
 ```
 
-4. Hugginface embedding, Ollama LLM을 위한 추가 모듈 설치를 시작합니다.
+### **4️⃣ 실행 모드 (Docker)**
+
+AutoRAG Evaluation은 실행 모드에 따라 다르게 동작합니다.  
+Docker 실행 시 아래 명령어를 사용하여 모드를 선택하세요.
 
 ```bash
-   pip install -r requirements_custom.txt
+docker run autorag-base <mode>
+```
+
+| 실행 모드  | 설명                             |
+| ---------- | -------------------------------- |
+| `data-gen` | 데이터 생성 (`making.sh` 실행)   |
+| `evaluate` | RAG 평가 (`main.py` 실행)        |
+| `bash`     | 컨테이너 내부 접근 (`/bin/bash`) |
+
+예시:
+
+```bash
+docker run autorag-base data-gen
+docker run autorag-base evaluate
+docker run autorag-base bash
 ```
 
 ---
 
-## 📂 데이터 생성
+## **📂 2. 데이터 생성**
 
 RAG 평가를 위해 **QA 데이터 세트**와 **코퍼스 데이터 세트**가 필요합니다.
 
-### 1️⃣ 프로젝트 폴더 생성
+### **1️⃣ 프로젝트 폴더 생성**
 
 ```bash
 cd projects
-mkdir -p "project_name"
-cd "project_name"
-mkdir -p raw_data config
+mkdir -p example_project/{raw_data,config}
 ```
 
-- **`raw_data/`**: 분석할 원본 데이터를 저장 (`.pdf` 등)
-- **`config/`**: 파싱(`parse.yaml`), 청킹(`chunk.yaml`) 설정 파일을 저장
+- **`raw_data/`**: 원본 데이터 저장 (`.pdf`, `.txt` 등)
+- **`config/`**: 설정 파일 저장 (`parse.yaml`, `chunk.yaml` 등)
 
-### 2️⃣ 파싱 설정 (`parse.yaml`)
-
-파싱 모듈을 설정합니다.
+### **2️⃣ 파싱 설정 (`parse.yaml`)**
 
 ```yaml
 modules:
@@ -53,11 +70,7 @@ modules:
     parse_method: pdfminer
 ```
 
-여러 개의 파싱 모듈을 동시에 사용할 수도 있습니다.
-
-### 3️⃣ 청킹 설정 (`chunk.yaml`)
-
-청킹 모듈을 설정합니다.
+### **3️⃣ 청킹 설정 (`chunk.yaml`)**
 
 ```yaml
 modules:
@@ -68,25 +81,21 @@ modules:
     add_file_name: en
 ```
 
-여러 개의 청킹 모듈을 사용할 경우, QA 데이터와 매핑해야 합니다.
-
-### 4️⃣ QA 데이터 생성
-
-`raw_data/`에 저장된 파일을 바탕으로 **파싱 → 청킹 → QA 데이터 생성**을 진행합니다.  
-QA 데이터는 `GPT-4o-mini` 모델을 사용하여 **20건**을 생성합니다.
+### **4️⃣ QA 데이터 생성**
 
 ```bash
-cd autorag-workspace
-sh making.sh
+bash making.sh
 ```
 
+> **참고:** `GPT-4o-mini` 모델을 사용하여 자동으로 QA 데이터를 생성합니다. (기본 20건)
+
 ---
 
-## 🔍 RAG Pipeline 평가
+## **🔍 3. RAG Pipeline 평가**
 
-### 1️⃣ Ollama 모델 다운로드
+### **1️⃣ Ollama 모델 다운로드**
 
-WSL(Windows Subsystem for Linux)에서 실행합니다.
+WSL(Windows Subsystem for Linux)에서 실행해야 합니다.
 
 ```bash
 docker exec -it autorag-ollama bash
@@ -94,61 +103,32 @@ ollama pull phi4
 ollama list
 ```
 
-### 2️⃣ AutoRAG 평가 실행
+### **2️⃣ 평가 실행**
 
 ```bash
-cd Autorag-workspace
 python main.py
 ```
 
-### 3️⃣ 평가 결과 확인
+### **3️⃣ 평가 결과 확인**
 
 평가 결과는 프로젝트 폴더 내 `benchmark_*` 경로에 저장됩니다.
 
-#### ✅ 전체 파이프라인 평가 결과
+#### **✅ 전체 평가 결과**
 
 ```bash
-cd projects/프로젝트이름/benchmark_{*}/*/
-summary.csv
+cd projects/example_project/benchmark_*/summary.csv
 ```
 
-#### ✅ 세부 평가 결과
+#### **✅ 세부 평가 결과**
 
-- **검색기 노드 라인 평가 결과**
-  ```bash
-  cd ./retrieve_node_line
-  summary.csv
-  ```
-- **검색 노드 평가 결과**
-  ```bash
-  cd ./retrieve_node_line/retrival
-  summary.csv
-  ```
-- **리랭커 노드 평가 결과**
-  ```bash
-  cd ./retrieve_node_line/passage_reranker
-  summary.csv
-  ```
-- **생성기 노드 라인 평가 결과**
-  ```bash
-  cd ./post_retrieve_node_line
-  summary.csv
-  ```
-- **생성 노드 평가 결과**
-  ```bash
-  cd ./post_retrieve_node_line/generator
-  summary.csv
-  ```
+| 평가 항목                 | 파일 경로                                           |
+| ------------------------- | --------------------------------------------------- |
+| **검색기 노드 라인 평가** | `./retrieve_node_line/summary.csv`                  |
+| **검색 노드 평가**        | `./retrieve_node_line/retrieval/summary.csv`        |
+| **리랭커 노드 평가**      | `./retrieve_node_line/passage_reranker/summary.csv` |
+| **생성기 노드 라인 평가** | `./post_retrieve_node_line/summary.csv`             |
+| **생성 노드 평가**        | `./post_retrieve_node_line/generator/summary.csv`   |
 
-> 📌 **참고:** `./projects/example_01` 폴더는 데이터 생성부터 평가까지 진행된 예제입니다.
+> 📌 `./projects/example_01` 폴더에는 데이터 생성부터 평가까지 진행된 예제 파일이 포함되어 있습니다.
 
 ---
-
-## 📊 평가 대시보드 실행
-
-```bash
-cd Autorag-workspace
-sh dashboard.sh
-```
-
-AutoRAG 평가 결과를 자세히 확인할 수 있습니다.
diff --git a/autorag-workspace/autorag/cli.py b/autorag-workspace/autorag/cli.py
deleted file mode 100644
index d114b83..0000000
--- a/autorag-workspace/autorag/cli.py
+++ /dev/null
@@ -1,209 +0,0 @@
-import importlib.resources
-import logging
-import os
-import pathlib
-import subprocess
-from pathlib import Path
-from typing import Optional
-
-import click
-import nest_asyncio
-
-from autorag import dashboard
-from autorag.deploy import extract_best_config as original_extract_best_config
-from autorag.deploy.api import ApiRunner
-from autorag.evaluator import Evaluator
-from autorag.validator import Validator
-
-logger = logging.getLogger("AutoRAG")
-
-autorag_dir = os.path.dirname(os.path.realpath(__file__))
-version_file = os.path.join(autorag_dir, "VERSION")
-with open(version_file, "r") as f:
-	__version__ = f.read().strip()
-
-
-@click.group()
-@click.version_option(__version__)
-def cli():
-	pass
-
-
-@click.command()
-@click.option(
-	"--config",
-	"-c",
-	help="Path to config yaml file. Must be yaml or yml file.",
-	type=str,
-)
-@click.option(
-	"--qa_data_path", help="Path to QA dataset. Must be parquet file.", type=str
-)
-@click.option(
-	"--corpus_data_path", help="Path to corpus dataset. Must be parquet file.", type=str
-)
-@click.option(
-	"--project_dir", help="Path to project directory.", type=str, default=None
-)
-@click.option(
-	"--skip_validation",
-	help="Skip validation or not. Default is False.",
-	type=bool,
-	default=False,
-)
-def evaluate(config, qa_data_path, corpus_data_path, project_dir, skip_validation):
-	if not config.endswith(".yaml") and not config.endswith(".yml"):
-		raise ValueError(f"Config file {config} is not a yaml or yml file.")
-	if not os.path.exists(config):
-		raise ValueError(f"Config file {config} does not exist.")
-	evaluator = Evaluator(qa_data_path, corpus_data_path, project_dir=project_dir)
-	evaluator.start_trial(config, skip_validation=skip_validation)
-
-
-@click.command()
-@click.option(
-	"--config_path", type=str, help="Path to extracted config yaml file.", default=None
-)
-@click.option("--host", type=str, default="0.0.0.0", help="Host address")
-@click.option("--port", type=int, default=8000, help="Port number")
-@click.option(
-	"--trial_dir",
-	type=click.Path(file_okay=False, dir_okay=True, exists=True),
-	default=None,
-	help="Path to trial directory.",
-)
-@click.option(
-	"--project_dir", help="Path to project directory.", type=str, default=None
-)
-@click.option(
-	"--remote", help="Run the API server in remote mode.", type=bool, default=False
-)
-def run_api(config_path, host, port, trial_dir, project_dir, remote: bool):
-	if trial_dir is None:
-		runner = ApiRunner.from_yaml(config_path, project_dir=project_dir)
-	else:
-		runner = ApiRunner.from_trial_folder(trial_dir)
-	logger.info(f"Running API server at {host}:{port}...")
-	nest_asyncio.apply()
-	runner.run_api_server(host, port, remote=remote)
-
-
-@click.command()
-@click.option(
-	"--yaml_path", type=click.Path(path_type=Path), help="Path to the YAML file."
-)
-@click.option(
-	"--project_dir",
-	type=click.Path(path_type=Path),
-	help="Path to the project directory.",
-)
-@click.option(
-	"--trial_path", type=click.Path(path_type=Path), help="Path to the trial directory."
-)
-def run_web(
-	yaml_path: Optional[str], project_dir: Optional[str], trial_path: Optional[str]
-):
-	try:
-		with importlib.resources.path("autorag", "web.py") as web_path:
-			web_py_path = str(web_path)
-	except ImportError:
-		raise ImportError(
-			"Could not locate the web.py file within the autorag package."
-			" Please ensure that autorag is correctly installed."
-		)
-
-	if not yaml_path and not trial_path:
-		raise ValueError("yaml_path or trial_path must be given.")
-	elif yaml_path and trial_path:
-		raise ValueError("yaml_path and trial_path cannot be given at the same time.")
-	elif yaml_path and not project_dir:
-		subprocess.run(
-			["streamlit", "run", web_py_path, "--", "--yaml_path", yaml_path]
-		)
-	elif yaml_path and project_dir:
-		subprocess.run(
-			[
-				"streamlit",
-				"run",
-				web_py_path,
-				"--",
-				"--yaml_path",
-				yaml_path,
-				"--project_dir",
-				project_dir,
-			]
-		)
-	elif trial_path:
-		subprocess.run(
-			["streamlit", "run", web_py_path, "--", "--trial_path", trial_path]
-		)
-
-
-@click.command()
-@click.option(
-	"--trial_dir",
-	type=click.Path(dir_okay=True, file_okay=False, exists=True),
-	required=True,
-)
-@click.option(
-	"--port", type=int, default=7690, help="Port number. The default is 7690."
-)
-def run_dashboard(trial_dir: str, port: int):
-	dashboard.run(trial_dir, port=port)
-
-
-@click.command()
-@click.option("--trial_path", type=click.Path(), help="Path to the trial directory.")
-@click.option(
-	"--output_path",
-	type=click.Path(),
-	help="Path to the output directory." " Must be .yaml or .yml file.",
-)
-def extract_best_config(trial_path: str, output_path: str):
-	original_extract_best_config(trial_path, output_path)
-
-
-@click.command()
-@click.option("--trial_path", help="Path to trial directory.", type=str)
-def restart_evaluate(trial_path):
-	if not os.path.exists(trial_path):
-		raise ValueError(f"trial_path {trial_path} does not exist.")
-	project_dir = str(pathlib.PurePath(trial_path).parent)
-	qa_data_path = os.path.join(project_dir, "data", "qa.parquet")
-	corpus_data_path = os.path.join(project_dir, "data", "corpus.parquet")
-	evaluator = Evaluator(qa_data_path, corpus_data_path, project_dir)
-	evaluator.restart_trial(trial_path)
-
-
-@click.command()
-@click.option(
-	"--config",
-	"-c",
-	help="Path to config yaml file. Must be yaml or yml file.",
-	type=str,
-)
-@click.option(
-	"--qa_data_path", help="Path to QA dataset. Must be parquet file.", type=str
-)
-@click.option(
-	"--corpus_data_path", help="Path to corpus dataset. Must be parquet file.", type=str
-)
-def validate(config, qa_data_path, corpus_data_path):
-	if not config.endswith(".yaml") and not config.endswith(".yml"):
-		raise ValueError(f"Config file {config} is not a parquet file.")
-	if not os.path.exists(config):
-		raise ValueError(f"Config file {config} does not exist.")
-	validator = Validator(qa_data_path=qa_data_path, corpus_data_path=corpus_data_path)
-	validator.validate(config)
-
-
-cli.add_command(evaluate, "evaluate")
-cli.add_command(run_api, "run_api")
-cli.add_command(run_web, "run_web")
-cli.add_command(run_dashboard, "dashboard")
-cli.add_command(extract_best_config, "extract_best_config")
-cli.add_command(restart_evaluate, "restart_evaluate")
-cli.add_command(validate, "validate")
-
-if __name__ == "__main__":
-	cli()
diff --git a/autorag-workspace/autorag/dashboard.py b/autorag-workspace/autorag/dashboard.py
deleted file mode 100644
index b55d2e9..0000000
--- a/autorag-workspace/autorag/dashboard.py
+++ /dev/null
@@ -1,199 +0,0 @@
-import ast
-import logging
-import os
-from typing import Dict, List
-
-import matplotlib.pyplot as plt
-import pandas as pd
-import panel as pn
-import seaborn as sns
-import yaml
-from bokeh.models import NumberFormatter, BooleanFormatter
-
-from autorag.utils.util import dict_to_markdown, dict_to_markdown_table
-
-pn.extension(
-	"terminal",
-	"tabulator",
-	"mathjax",
-	"ipywidgets",
-	console_output="disable",
-	sizing_mode="stretch_width",
-	css_files=[
-		"https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.4.2/css/all.min.css"
-	],
-)
-logger = logging.getLogger("AutoRAG")
-
-
-def find_node_dir(trial_dir: str) -> List[str]:
-	trial_summary_df = pd.read_csv(os.path.join(trial_dir, "summary.csv"))
-	result_paths = []
-	for idx, row in trial_summary_df.iterrows():
-		node_line_name = row["node_line_name"]
-		node_type = row["node_type"]
-		result_paths.append(os.path.join(trial_dir, node_line_name, node_type))
-	return result_paths
-
-
-def get_metric_values(node_summary_df: pd.DataFrame) -> Dict:
-	non_metric_column_names = [
-		"filename",
-		"module_name",
-		"module_params",
-		"execution_time",
-		"average_output_token",
-		"is_best",
-	]
-	best_row = node_summary_df.loc[node_summary_df["is_best"]].drop(
-		columns=non_metric_column_names, errors="ignore"
-	)
-	assert len(best_row) == 1, "The best module must be only one."
-	return best_row.iloc[0].to_dict()
-
-
-def make_trial_summary_md(trial_dir):
-	markdown_text = f"""# Trial Result Summary
-- Trial Directory : {trial_dir}
-
-"""
-	node_dirs = find_node_dir(trial_dir)
-	for node_dir in node_dirs:
-		node_summary_filepath = os.path.join(node_dir, "summary.csv")
-		node_type = os.path.basename(node_dir)
-		node_summary_df = pd.read_csv(node_summary_filepath)
-		best_row = node_summary_df.loc[node_summary_df["is_best"]].iloc[0]
-		metric_dict = get_metric_values(node_summary_df)
-		markdown_text += f"""---
-
-## {node_type} best module
-
-### Module Name
-
-{best_row['module_name']}
-
-### Module Params
-
-{dict_to_markdown(ast.literal_eval(best_row['module_params']), level=3)}
-
-### Metric Values
-
-{dict_to_markdown_table(metric_dict, key_column_name='metric_name', value_column_name='metric_value')}
-
-"""
-
-	return markdown_text
-
-
-def node_view(node_dir: str):
-	non_metric_column_names = [
-		"filename",
-		"module_name",
-		"module_params",
-		"execution_time",
-		"average_output_token",
-		"is_best",
-	]
-	summary_df = pd.read_csv(os.path.join(node_dir, "summary.csv"))
-	bokeh_formatters = {
-		"float": NumberFormatter(format="0.000"),
-		"bool": BooleanFormatter(),
-	}
-	first_df = pd.read_parquet(os.path.join(node_dir, "0.parquet"), engine="pyarrow")
-
-	each_module_df_widget = pn.widgets.Tabulator(
-		pd.DataFrame(columns=first_df.columns),
-		name="Module DataFrame",
-		formatters=bokeh_formatters,
-		pagination="local",
-		page_size=20,
-		widths=150,
-	)
-
-	def change_module_widget(event):
-		if event.column == "detail":
-			filename = summary_df["filename"].iloc[event.row]
-			filepath = os.path.join(node_dir, filename)
-			each_module_df = pd.read_parquet(filepath, engine="pyarrow")
-			each_module_df_widget.value = each_module_df
-
-	df_widget = pn.widgets.Tabulator(
-		summary_df,
-		name="Summary DataFrame",
-		formatters=bokeh_formatters,
-		buttons={"detail": '<i class="fa fa-eye"></i>'},
-		widths=150,
-	)
-	df_widget.on_click(change_module_widget)
-
-	try:
-		fig, ax = plt.subplots(figsize=(10, 5))
-		metric_df = summary_df.drop(columns=non_metric_column_names, errors="ignore")
-		sns.stripplot(data=metric_df, ax=ax)
-		strip_plot_pane = pn.pane.Matplotlib(fig, tight=True)
-
-		fig2, ax2 = plt.subplots(figsize=(10, 5))
-		sns.boxplot(data=metric_df, ax=ax2)
-		box_plot_pane = pn.pane.Matplotlib(fig2, tight=True)
-		plot_pane = pn.Row(strip_plot_pane, box_plot_pane)
-
-		layout = pn.Column(
-			"## Summary distribution plot",
-			plot_pane,
-			"## Summary DataFrame",
-			df_widget,
-			"## Module Result DataFrame",
-			each_module_df_widget,
-		)
-	except Exception as e:
-		logger.error(f"Skipping make boxplot and stripplot with error {e}")
-		layout = pn.Column("## Summary DataFrame", df_widget)
-	layout.servable()
-	return layout
-
-
-CSS = """
-div.card-margin:nth-child(1) {
-    max-height: 300px;
-}
-div.card-margin:nth-child(2) {
-    max-height: 400px;
-}
-"""
-
-
-def yaml_to_markdown(yaml_filepath):
-	markdown_content = ""
-	with open(yaml_filepath, "r", encoding="utf-8") as file:
-		try:
-			content = yaml.safe_load(file)
-			markdown_content += f"## {os.path.basename(yaml_filepath)}\n```yaml\n{yaml.safe_dump(content, allow_unicode=True)}\n```\n\n"
-		except yaml.YAMLError as exc:
-			print(f"Error in {yaml_filepath}: {exc}")
-	return markdown_content
-
-
-def run(trial_dir: str, port: int = 7690):
-	trial_summary_md = make_trial_summary_md(trial_dir=trial_dir)
-	trial_summary_tab = pn.pane.Markdown(trial_summary_md, sizing_mode="stretch_width")
-
-	node_views = [
-		(str(os.path.basename(node_dir)), node_view(node_dir))
-		for node_dir in find_node_dir(trial_dir)
-	]
-
-	yaml_file_markdown = yaml_to_markdown(os.path.join(trial_dir, "config.yaml"))
-
-	yaml_file = pn.pane.Markdown(yaml_file_markdown, sizing_mode="stretch_width")
-
-	tabs = pn.Tabs(
-		("Summary", trial_summary_tab),
-		*node_views,
-		("Used YAML file", yaml_file),
-		dynamic=True,
-	)
-
-	template = pn.template.FastListTemplate(
-		site="AutoRAG", title="Dashboard", main=[tabs], raw_css=[CSS]
-	).servable()
-	template.show(port=port)
diff --git a/autorag-workspace/dashboard.sh b/autorag-workspace/dashboard.sh
deleted file mode 100644
index cbc2e58..0000000
--- a/autorag-workspace/dashboard.sh
+++ /dev/null
@@ -1,8 +0,0 @@
-#!/bin/bash
-
-export BOKEH_ALLOW_WS_ORIGIN="localhost:7690,172.16.9.208:7690"
-
-python -m autorag.cli dashboard \
-    --trial_dir ../projects/daesan-dangjin_01/benchmark/1
-
-echo "📊 AutoRAG 대시보드 http://localhost:7690/..."
diff --git a/autorag-workspace/example/sample_config/chunk/chunk_full.yaml b/autorag-workspace/example/sample_config/chunk/chunk_full.yaml
deleted file mode 100644
index 429daef..0000000
--- a/autorag-workspace/example/sample_config/chunk/chunk_full.yaml
+++ /dev/null
@@ -1,32 +0,0 @@
-modules:
-  - module_type: llama_index_chunk
-    chunk_method: [ Token, Sentence ]
-    chunk_size: [ 1024, 512 ]
-    chunk_overlap: 24
-    add_file_name: en
-  - module_type: llama_index_chunk
-    chunk_method: [ SentenceWindow ]
-    window_size: 3
-    add_file_name: en
-  - module_type: llama_index_chunk
-    chunk_method: [ Semantic_llama_index ]
-    embed_model: openai
-    buffer_size: 1
-    breakpoint_percentile_threshold: 95
-    add_file_name: en
-  - module_type: llama_index_chunk
-    chunk_method: [ SemanticDoubleMerging ]
-    add_file_name: en
-  - module_type: llama_index_chunk
-    chunk_method: [ SimpleFile ]
-    add_file_name: en
-  - module_type: langchain_chunk
-    chunk_method: sentencetransformerstoken
-  - module_type: langchain_chunk
-    chunk_method: recursivecharacter
-    separators: [ " ", "\n" ]
-  - module_type: langchain_chunk
-    chunk_method: character
-    separator: ". "
-  - module_type: langchain_chunk
-    chunk_method: Konlpy
diff --git a/autorag-workspace/example/sample_config/chunk/chunk_ko.yaml b/autorag-workspace/example/sample_config/chunk/chunk_ko.yaml
deleted file mode 100644
index 322a971..0000000
--- a/autorag-workspace/example/sample_config/chunk/chunk_ko.yaml
+++ /dev/null
@@ -1,19 +0,0 @@
-modules:
-  - module_type: llama_index_chunk
-    chunk_method: [ Token, Sentence ]
-    chunk_size: [ 1024, 512 ]
-    chunk_overlap: 24
-    add_file_name: ko
-  - module_type: llama_index_chunk
-    chunk_method: [ SentenceWindow ]
-    sentence_splitter: kiwi
-    add_file_name: ko
-  - module_type: llama_index_chunk
-    chunk_method: [ Semantic_llama_index ]
-    embed_model: openai
-    add_file_name: ko
-  - module_type: llama_index_chunk
-    chunk_method: [ SimpleFile ]
-    add_file_name: ko
-  - module_type: langchain_chunk
-    chunk_method: KonlpyTextSplitter
diff --git a/autorag-workspace/example/sample_config/chunk/simple_chunk.yaml b/autorag-workspace/example/sample_config/chunk/simple_chunk.yaml
deleted file mode 100644
index 3f65aeb..0000000
--- a/autorag-workspace/example/sample_config/chunk/simple_chunk.yaml
+++ /dev/null
@@ -1,3 +0,0 @@
-modules:
-  - module_type: llama_index_chunk
-    chunk_method: Token
diff --git a/autorag-workspace/example/sample_config/parse/all_files_full.yaml b/autorag-workspace/example/sample_config/parse/all_files_full.yaml
deleted file mode 100644
index 9cdbf7e..0000000
--- a/autorag-workspace/example/sample_config/parse/all_files_full.yaml
+++ /dev/null
@@ -1,25 +0,0 @@
-# You can use only one of the following modules at a time.
-modules:
-  # Use Directory Parse
-  - module_type: langchain_parse
-    file_type: all_files
-    parse_method: directory
-  # Use Unstructured
-  - module_type: langchain_parse
-    file_type: all_files
-    parse_method: unstructured
-  # Use Upsatge Document Parse
-  - module_type: langchain_parse
-    file_type: all_files
-    parse_method: upstagedocumentparse
-  # Use Naver Clova OCR
-  - module_type: clova
-    file_type: all_files
-    table_detection: true
-  # Use Llama Parse
-  - module_type: llamaparse
-    file_type: all_files
-    result_type: markdown
-    language: ko
-    use_vendor_multimodal_model: true
-    vendor_multimodal_model_name: openai-gpt-4o-mini
diff --git a/autorag-workspace/example/sample_config/parse/file_types_full.yaml b/autorag-workspace/example/sample_config/parse/file_types_full.yaml
deleted file mode 100644
index 180842b..0000000
--- a/autorag-workspace/example/sample_config/parse/file_types_full.yaml
+++ /dev/null
@@ -1,26 +0,0 @@
-modules:
-  # PDF
-  - module_type: langchain_parse
-    file_type: pdf
-    parse_method: pdfminer
-  # CSV
-  - module_type: langchain_parse
-    file_type: csv
-    parse_method: csv
-  # JSON
-  - module_type: langchain_parse
-    file_type: json
-    parse_method: json
-    jq_schema: .content
-  # Markdown
-  - module_type: langchain_parse
-    file_type: md
-    parse_method: unstructuredmarkdown
-  # HTML
-  - module_type: langchain_parse
-    file_type: html
-    parse_method: bshtml
-  # XML
-  - module_type: langchain_parse
-    file_type: xml
-    parse_method: unstructuredxml
diff --git a/autorag-workspace/example/sample_config/parse/parse_hybird.yaml b/autorag-workspace/example/sample_config/parse/parse_hybird.yaml
deleted file mode 100644
index 1ea4c7f..0000000
--- a/autorag-workspace/example/sample_config/parse/parse_hybird.yaml
+++ /dev/null
@@ -1,12 +0,0 @@
-modules:
-  - module_type: table_hybrid_parse
-    file_type: pdf
-    text_parse_module: langchain_parse
-    text_params:
-      parse_method: pdfplumber
-    table_parse_module: llamaparse
-    table_params:
-      result_type: markdown
-      language: ko
-      use_vendor_multimodal_model: true
-      vendor_multimodal_model_name: openai-gpt-4o-mini
diff --git a/autorag-workspace/example/sample_config/parse/parse_ko.yaml b/autorag-workspace/example/sample_config/parse/parse_ko.yaml
deleted file mode 100644
index b216046..0000000
--- a/autorag-workspace/example/sample_config/parse/parse_ko.yaml
+++ /dev/null
@@ -1,11 +0,0 @@
-modules:
-  - module_type: llama_parse
-    file_type: all_files
-    result_type: markdown
-    language: ko
-  - module_type: clova
-    file_type: all_files
-    table_detection: true
-  - module_type: langchain_parse
-    file_type: all_files
-    parse_method: upstagedocumentparse
diff --git a/autorag-workspace/example/sample_config/parse/parse_multimodal.yaml b/autorag-workspace/example/sample_config/parse/parse_multimodal.yaml
deleted file mode 100644
index 9ced86e..0000000
--- a/autorag-workspace/example/sample_config/parse/parse_multimodal.yaml
+++ /dev/null
@@ -1,8 +0,0 @@
-modules:
-  - module_type: llamaparse
-    file_type: all_files
-    result_type: markdown
-    language: ko
-    use_vendor_multimodal_model: true
-    vendor_multimodal_model_name: openai-gpt-4o-mini
-    use_own_key: true
diff --git a/autorag-workspace/example/sample_config/parse/parse_ocr.yaml b/autorag-workspace/example/sample_config/parse/parse_ocr.yaml
deleted file mode 100644
index 4c0b757..0000000
--- a/autorag-workspace/example/sample_config/parse/parse_ocr.yaml
+++ /dev/null
@@ -1,10 +0,0 @@
-modules:
-  - module_type: langchain_parse
-    file_type: all_files
-    parse_method: upstagedocumentparse
-  - module_type: llama_parse
-    file_type: all_files
-    result_type: markdown
-  - module_type: clova
-    file_type: all_files
-    table_detection: true
diff --git a/autorag-workspace/example/sample_config/parse/simple_parse.yaml b/autorag-workspace/example/sample_config/parse/simple_parse.yaml
deleted file mode 100644
index 73ae58a..0000000
--- a/autorag-workspace/example/sample_config/parse/simple_parse.yaml
+++ /dev/null
@@ -1,4 +0,0 @@
-modules:
-  - module_type: langchain_parse
-    file_type: pdf
-    parse_method: pdfminer
diff --git a/autorag-workspace/example/sample_config/rag/english/gpu/compact_local.yaml b/autorag-workspace/example/sample_config/rag/english/gpu/compact_local.yaml
deleted file mode 100644
index 6f66932..0000000
--- a/autorag-workspace/example/sample_config/rag/english/gpu/compact_local.yaml
+++ /dev/null
@@ -1,50 +0,0 @@
-vectordb:
-  - name: mpnet_base_chroma
-    db_type: chroma
-    client_type: persistent
-    embedding_model: huggingface_all_mpnet_base_v2
-    collection_name: huggingface_all_mpnet_base_v2
-    path: ${PROJECT_DIR}/data/chroma
-node_lines:
-- node_line_name: retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: retrieval
-      strategy:
-        metrics: [retrieval_f1, retrieval_recall, retrieval_precision]
-      top_k: 20
-      modules:
-        - module_type: bm25
-        - module_type: vectordb
-          vectordb: mpnet_base_chroma
-        - module_type: hybrid_rrf
-        - module_type: hybrid_cc
-          normalize_method: [ mm, tmm, z, dbsf ]
-    - node_type: passage_reranker
-      strategy:
-        metrics: [retrieval_f1, retrieval_recall, retrieval_precision]
-      top_k: 3
-      modules:
-        - module_type: pass_reranker
-        - module_type: tart
-        - module_type: upr
-- node_line_name: post_retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: prompt_maker
-      strategy:
-        metrics: [bleu, meteor, rouge, sem_score]
-        generator_modules:
-          - module_type: vllm
-            llm: mistralai/Mistral-7B-Instruct-v0.2
-      modules:
-        - module_type: fstring
-          prompt:
-            - "Answer to given questions with the following passage: {retrieved_contents} \n\n Question: {query} \n\n Answer:"
-            - "There is a passages related to user question. Please response carefully to the following question. \n\n Passage: {retrieved_contents} \n\n Question: {query} \n\n Answer the question. Think step by step." # Zero-shot CoT prompt
-            - "{retrieved_contents} \n\n Read the passage carefully, and answer this question. \n\n Question: {query} \n\n Answer the question. Be concise." # concise prompt
-    - node_type: generator
-      strategy:
-        metrics: [bleu, meteor, rouge, sem_score]
-      modules:
-        - module_type: vllm
-          llm: mistralai/Mistral-7B-Instruct-v0.2
-          temperature: [0.1, 0.5, 1.1]
diff --git a/autorag-workspace/example/sample_config/rag/english/gpu/compact_openai.yaml b/autorag-workspace/example/sample_config/rag/english/gpu/compact_openai.yaml
deleted file mode 100644
index 26f2309..0000000
--- a/autorag-workspace/example/sample_config/rag/english/gpu/compact_openai.yaml
+++ /dev/null
@@ -1,101 +0,0 @@
-node_lines:
-- node_line_name: retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: retrieval
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision,
-                   retrieval_ndcg, retrieval_map, retrieval_mrr ]
-        speed_threshold: 10
-      top_k: 10
-      modules:
-        - module_type: bm25
-          bm25_tokenizer: [ porter_stemmer, space, gpt2 ]
-        - module_type: vectordb
-          vectordb: default
-        - module_type: hybrid_rrf
-          weight_range: (4,80)
-        - module_type: hybrid_cc
-          normalize_method: [ mm, tmm, z, dbsf ]
-          weight_range: (0.0, 1.0)
-          test_weight_size: 101
-    - node_type: passage_augmenter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      top_k: 5
-      embedding_model: openai
-      modules:
-        - module_type: pass_passage_augmenter
-        - module_type: prev_next_augmenter
-          mode: next
-    - node_type: passage_reranker
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 10
-      top_k: 5
-      modules:
-        - module_type: pass_reranker
-        - module_type: tart
-        - module_type: monot5
-        - module_type: upr
-        - module_type: rankgpt
-        - module_type: colbert_reranker
-        - module_type: sentence_transformer_reranker
-        - module_type: flag_embedding_reranker
-        - module_type: flag_embedding_llm_reranker
-        - module_type: time_reranker
-        - module_type: openvino_reranker
-        - module_type: flashrank_reranker
-    - node_type: passage_filter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      modules:
-        - module_type: pass_passage_filter
-        - module_type: similarity_threshold_cutoff
-          threshold: 0.85
-        - module_type: similarity_percentile_cutoff
-          percentile: 0.6
-        - module_type: threshold_cutoff
-          threshold: 0.85
-        - module_type: percentile_cutoff
-          percentile: 0.6
-- node_line_name: post_retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: prompt_maker
-      strategy:
-        metrics:
-          - metric_name: bleu
-          - metric_name: meteor
-          - metric_name: rouge
-          - metric_name: sem_score
-            embedding_model: openai
-        speed_threshold: 10
-        generator_modules:
-          - module_type: llama_index_llm
-            llm: openai
-            model: [gpt-4o-mini]
-      modules:
-        - module_type: fstring
-          prompt:
-            - "Answer to given questions with the following passage: {retrieved_contents} \n\n Question: {query} \n\n Answer:"
-            - "There is a passages related to user question. Please response carefully to the following question. \n\n Passage: {retrieved_contents} \n\n Question: {query} \n\n Answer the question. Think step by step." # Zero-shot CoT prompt
-            - "{retrieved_contents} \n\n Read the passage carefully, and answer this question. \n\n Question: {query} \n\n Answer the question. Be concise." # concise prompt
-        - module_type: long_context_reorder
-          prompt:
-            - "Answer to given questions with the following passage: {retrieved_contents} \n\n Question: {query} \n\n Answer:"
-            - "There is a passages related to user question. Please response carefully to the following question. \n\n Passage: {retrieved_contents} \n\n Question: {query} \n\n Answer the question. Think step by step." # Zero-shot CoT prompt
-            - "{retrieved_contents} \n\n Read the passage carefully, and answer this question. \n\n Question: {query} \n\n Answer the question. Be concise." # concise prompt
-    - node_type: generator
-      strategy:
-        metrics:
-          - metric_name: rouge
-          - embedding_model: openai
-            metric_name: sem_score
-          - metric_name: bert_score
-        speed_threshold: 10
-      modules:
-        - module_type: llama_index_llm
-          llm: [openai]
-          model: [gpt-4o-mini]
-          temperature: [0.5, 1.0]
diff --git a/autorag-workspace/example/sample_config/rag/english/gpu/full.yaml b/autorag-workspace/example/sample_config/rag/english/gpu/full.yaml
deleted file mode 100644
index dd1da67..0000000
--- a/autorag-workspace/example/sample_config/rag/english/gpu/full.yaml
+++ /dev/null
@@ -1,154 +0,0 @@
-vectordb:
-  - name: chroma_bge_m3
-    db_type: chroma
-    client_type: persistent
-    embedding_model: huggingface_bge_m3
-    collection_name: openai
-    path: ${PROJECT_DIR}/resources/chroma
-node_lines:
-- node_line_name: pre_retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: query_expansion
-      strategy:
-        metrics: [retrieval_f1, retrieval_recall, retrieval_precision]
-        speed_threshold: 10
-        top_k: 10
-        retrieval_modules:
-          - module_type: bm25
-            bm25_tokenizer: [ porter_stemmer, space, gpt2 ]
-          - module_type: vectordb
-            vectordb: chroma_bge_m3
-      modules:
-        - module_type: pass_query_expansion
-        - module_type: query_decompose
-          generator_module_type: llama_index_llm
-          llm: openai
-          model: [ gpt-4o-mini ]
-        - module_type: hyde
-          generator_module_type: llama_index_llm
-          llm: openai
-          model: [ gpt-4o-mini ]
-          max_token: 64
-        - module_type: multi_query_expansion
-          generator_module_type: llama_index_llm
-          llm: openai
-          temperature: [ 0.2, 1.0 ]
-- node_line_name: retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: retrieval
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision,
-                   retrieval_ndcg, retrieval_map, retrieval_mrr ]
-        speed_threshold: 10
-      top_k: 10
-      modules:
-        - module_type: bm25
-        - module_type: vectordb
-          vectordb: chroma_bge_m3
-        - module_type: hybrid_rrf
-          weight_range: (4,80)
-        - module_type: hybrid_cc
-          normalize_method: [ mm, tmm, z, dbsf ]
-          weight_range: (0.0, 1.0)
-          test_weight_size: 101
-    - node_type: passage_augmenter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      top_k: 5
-      embedding_model: openai
-      modules:
-        - module_type: pass_passage_augmenter
-        - module_type: prev_next_augmenter
-          mode: next
-    - node_type: passage_reranker
-      strategy:
-        metrics: [retrieval_f1, retrieval_recall, retrieval_precision]
-        speed_threshold: 10
-      top_k: 5
-      modules:
-        - module_type: pass_reranker
-        - module_type: tart
-        - module_type: monot5
-        - module_type: upr
-        - module_type: rankgpt
-        - module_type: colbert_reranker
-        - module_type: sentence_transformer_reranker
-        - module_type: flag_embedding_reranker
-        - module_type: flag_embedding_llm_reranker
-        - module_type: time_reranker
-        - module_type: openvino_reranker
-        - module_type: flashrank_reranker
-    - node_type: passage_filter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      modules:
-        - module_type: pass_passage_filter
-        - module_type: similarity_threshold_cutoff
-          threshold: 0.85
-        - module_type: similarity_percentile_cutoff
-          percentile: 0.6
-        - module_type: recency_filter
-          threshold_datetime: 2015-01-01 3:45:07
-        - module_type: threshold_cutoff
-          threshold: 0.85
-        - module_type: percentile_cutoff
-          percentile: 0.6
-    - node_type: passage_compressor
-      strategy:
-        metrics: [retrieval_token_f1, retrieval_token_recall, retrieval_token_precision]
-        speed_threshold: 10
-      modules:
-        - module_type: pass_compressor
-        - module_type: tree_summarize
-          llm: openai
-          model: gpt-4o-mini
-        - module_type: refine
-          llm: openai
-          model: gpt-4o-mini
-        - module_type: longllmlingua
-- node_line_name: post_retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: prompt_maker
-      strategy:
-        metrics:
-          - metric_name: bleu
-          - metric_name: meteor
-          - metric_name: rouge
-          - metric_name: sem_score
-            embedding_model: openai
-          - metric_name: g_eval
-        speed_threshold: 10
-        generator_modules:
-          - module_type: llama_index_llm
-            llm: openai
-            model: [gpt-4o-mini]
-      modules:
-        - module_type: fstring
-          prompt: ["Tell me something about the question: {query} \n\n {retrieved_contents}",
-                   "Question: {query} \n Something to read: {retrieved_contents} \n What's your answer?"]
-        - module_type: long_context_reorder
-          prompt: [ "Tell me something about the question: {query} \n\n {retrieved_contents}",
-                    "Question: {query} \n Something to read: {retrieved_contents} \n What's your answer?" ]
-        - module_type: window_replacement
-          prompt: [ "Tell me something about the question: {query} \n\n {retrieved_contents}",
-                    "Question: {query} \n Something to read: {retrieved_contents} \n What's your answer?" ]
-    - node_type: generator
-      strategy:
-        metrics:
-          - metric_name: bleu
-          - metric_name: meteor
-          - metric_name: rouge
-          - metric_name: sem_score
-            embedding_model: openai
-          - metric_name: g_eval  # LLM Judge Metric. Default Model: gpt-4-turbo
-        speed_threshold: 10
-      modules:
-        - module_type: llama_index_llm
-          llm: [openai]
-          model: [gpt-4o-mini]
-          temperature: [0.5, 1.0, 1.5]
-        - module_type: openai_llm
-          llm: gpt-4o-mini
-          temperature: 0.8
diff --git a/autorag-workspace/example/sample_config/rag/english/gpu/half.yaml b/autorag-workspace/example/sample_config/rag/english/gpu/half.yaml
deleted file mode 100644
index 9f25628..0000000
--- a/autorag-workspace/example/sample_config/rag/english/gpu/half.yaml
+++ /dev/null
@@ -1,121 +0,0 @@
-vectordb:
-  - name: chroma_bge_m3
-    db_type: chroma
-    client_type: persistent
-    embedding_model: huggingface_bge_m3
-    collection_name: openai
-    path: ${PROJECT_DIR}/resources/chroma
-node_lines:
-- node_line_name: retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: retrieval
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision,
-                   retrieval_ndcg, retrieval_map, retrieval_mrr ]
-        speed_threshold: 10
-      top_k: 10
-      modules:
-        - module_type: bm25
-          bm25_tokenizer: [ porter_stemmer, space, gpt2 ]
-        - module_type: vectordb
-          vectordb: chroma_bge_m3
-        - module_type: hybrid_rrf
-          weight_range: (4,80)
-        - module_type: hybrid_cc
-          normalize_method: [ mm, tmm, z, dbsf ]
-          weight_range: (0.0, 1.0)
-          test_weight_size: 101
-    - node_type: passage_augmenter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      top_k: 5
-      embedding_model: openai
-      modules:
-        - module_type: pass_passage_augmenter
-        - module_type: prev_next_augmenter
-          mode: next
-    - node_type: passage_reranker
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 10
-      top_k: 5
-      modules:
-        - module_type: pass_reranker
-        - module_type: tart
-        - module_type: monot5
-        - module_type: upr
-        - module_type: rankgpt
-        - module_type: colbert_reranker
-        - module_type: sentence_transformer_reranker
-        - module_type: flag_embedding_reranker
-        - module_type: flag_embedding_llm_reranker
-        - module_type: time_reranker
-        - module_type: openvino_reranker
-        - module_type: flashrank_reranker
-    - node_type: passage_filter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      modules:
-        - module_type: pass_passage_filter
-        - module_type: similarity_threshold_cutoff
-          threshold: 0.85
-        - module_type: similarity_percentile_cutoff
-          percentile: 0.6
-        - module_type: threshold_cutoff
-          threshold: 0.85
-        - module_type: percentile_cutoff
-          percentile: 0.6
-    - node_type: passage_compressor
-      strategy:
-        metrics: [retrieval_token_f1, retrieval_token_recall, retrieval_token_precision]
-        speed_threshold: 10
-      modules:
-        - module_type: pass_compressor
-        - module_type: tree_summarize
-          llm: openai
-          model: gpt-4o-mini
-        - module_type: refine
-          llm: openai
-          model: gpt-4o-mini
-        - module_type: longllmlingua
-- node_line_name: post_retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: prompt_maker
-      strategy:
-        metrics:
-          - metric_name: bleu
-          - metric_name: meteor
-          - metric_name: rouge
-          - metric_name: sem_score
-            embedding_model: openai
-        speed_threshold: 10
-        generator_modules:
-          - module_type: llama_index_llm
-            llm: openai
-            model: [gpt-4o-mini]
-      modules:
-        - module_type: fstring
-          prompt:
-            - "Answer to given questions with the following passage: {retrieved_contents} \n\n Question: {query} \n\n Answer:"
-            - "There is a passages related to user question. Please response carefully to the following question. \n\n Passage: {retrieved_contents} \n\n Question: {query} \n\n Answer the question. Think step by step." # Zero-shot CoT prompt
-            - "{retrieved_contents} \n\n Read the passage carefully, and answer this question. \n\n Question: {query} \n\n Answer the question. Be concise." # concise prompt
-        - module_type: long_context_reorder
-          prompt:
-            - "Answer to given questions with the following passage: {retrieved_contents} \n\n Question: {query} \n\n Answer:"
-            - "There is a passages related to user question. Please response carefully to the following question. \n\n Passage: {retrieved_contents} \n\n Question: {query} \n\n Answer the question. Think step by step." # Zero-shot CoT prompt
-            - "{retrieved_contents} \n\n Read the passage carefully, and answer this question. \n\n Question: {query} \n\n Answer the question. Be concise." # concise prompt
-    - node_type: generator
-      strategy:
-        metrics:
-          - metric_name: rouge
-          - embedding_model: openai
-            metric_name: sem_score
-          - metric_name: bert_score
-        speed_threshold: 10
-      modules:
-        - module_type: llama_index_llm
-          llm: [openai]
-          model: [gpt-4o-mini]
-          temperature: [0.5, 1.0]
diff --git a/autorag-workspace/example/sample_config/rag/english/gpu_api/compact.yaml b/autorag-workspace/example/sample_config/rag/english/gpu_api/compact.yaml
deleted file mode 100644
index fc286b9..0000000
--- a/autorag-workspace/example/sample_config/rag/english/gpu_api/compact.yaml
+++ /dev/null
@@ -1,105 +0,0 @@
-node_lines:
-- node_line_name: retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: retrieval
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision,
-                   retrieval_ndcg, retrieval_map, retrieval_mrr ]
-        speed_threshold: 10
-      top_k: 10
-      modules:
-        - module_type: bm25
-          bm25_tokenizer: [ porter_stemmer, space, gpt2 ]
-        - module_type: vectordb
-          vectordb: default
-        - module_type: hybrid_rrf
-          weight_range: (4,80)
-        - module_type: hybrid_cc
-          normalize_method: [ mm, tmm, z, dbsf ]
-          weight_range: (0.0, 1.0)
-          test_weight_size: 101
-    - node_type: passage_augmenter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      top_k: 5
-      embedding_model: openai
-      modules:
-        - module_type: pass_passage_augmenter
-        - module_type: prev_next_augmenter
-          mode: next
-    - node_type: passage_reranker
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 10
-      top_k: 5
-      modules:
-        - module_type: pass_reranker
-        - module_type: tart
-        - module_type: monot5
-        - module_type: upr
-        - module_type: cohere_reranker
-        - module_type: rankgpt
-        - module_type: jina_reranker
-        - module_type: colbert_reranker
-        - module_type: sentence_transformer_reranker
-        - module_type: flag_embedding_reranker
-        - module_type: flag_embedding_llm_reranker
-        - module_type: time_reranker
-        - module_type: openvino_reranker
-        - module_type: voyageai_reranker
-        - module_type: mixedbreadai_reranker
-        - module_type: flashrank_reranker
-    - node_type: passage_filter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      modules:
-        - module_type: pass_passage_filter
-        - module_type: similarity_threshold_cutoff
-          threshold: 0.85
-        - module_type: similarity_percentile_cutoff
-          percentile: 0.6
-        - module_type: threshold_cutoff
-          threshold: 0.85
-        - module_type: percentile_cutoff
-          percentile: 0.6
-- node_line_name: post_retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: prompt_maker
-      strategy:
-        metrics:
-          - metric_name: bleu
-          - metric_name: meteor
-          - metric_name: rouge
-          - metric_name: sem_score
-            embedding_model: openai
-        speed_threshold: 10
-        generator_modules:
-          - module_type: llama_index_llm
-            llm: openai
-            model: [gpt-4o-mini]
-      modules:
-        - module_type: fstring
-          prompt:
-            - "Answer to given questions with the following passage: {retrieved_contents} \n\n Question: {query} \n\n Answer:"
-            - "There is a passages related to user question. Please response carefully to the following question. \n\n Passage: {retrieved_contents} \n\n Question: {query} \n\n Answer the question. Think step by step." # Zero-shot CoT prompt
-            - "{retrieved_contents} \n\n Read the passage carefully, and answer this question. \n\n Question: {query} \n\n Answer the question. Be concise." # concise prompt
-        - module_type: long_context_reorder
-          prompt:
-            - "Answer to given questions with the following passage: {retrieved_contents} \n\n Question: {query} \n\n Answer:"
-            - "There is a passages related to user question. Please response carefully to the following question. \n\n Passage: {retrieved_contents} \n\n Question: {query} \n\n Answer the question. Think step by step." # Zero-shot CoT prompt
-            - "{retrieved_contents} \n\n Read the passage carefully, and answer this question. \n\n Question: {query} \n\n Answer the question. Be concise." # concise prompt
-    - node_type: generator
-      strategy:
-        metrics:
-          - metric_name: rouge
-          - embedding_model: openai
-            metric_name: sem_score
-          - metric_name: bert_score
-        speed_threshold: 10
-      modules:
-        - module_type: llama_index_llm
-          llm: [openai]
-          model: [gpt-4o-mini]
-          temperature: [0.5, 1.0]
diff --git a/autorag-workspace/example/sample_config/rag/english/gpu_api/full.yaml b/autorag-workspace/example/sample_config/rag/english/gpu_api/full.yaml
deleted file mode 100644
index a7435af..0000000
--- a/autorag-workspace/example/sample_config/rag/english/gpu_api/full.yaml
+++ /dev/null
@@ -1,151 +0,0 @@
-node_lines:
-- node_line_name: pre_retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: query_expansion
-      strategy:
-        metrics: [retrieval_f1, retrieval_recall, retrieval_precision]
-        speed_threshold: 10
-        top_k: 10
-        retrieval_modules:
-          - module_type: bm25
-            bm25_tokenizer: [ porter_stemmer, space, gpt2 ]
-          - module_type: vectordb
-            vectordb: default
-      modules:
-        - module_type: pass_query_expansion
-        - module_type: query_decompose
-          generator_module_type: llama_index_llm
-          llm: openai
-          model: [ gpt-4o-mini ]
-        - module_type: hyde
-          generator_module_type: llama_index_llm
-          llm: openai
-          model: [ gpt-4o-mini ]
-          max_token: 64
-        - module_type: multi_query_expansion
-          generator_module_type: llama_index_llm
-          llm: openai
-          temperature: [ 0.2, 1.0 ]
-- node_line_name: retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: retrieval
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision,
-                   retrieval_ndcg, retrieval_map, retrieval_mrr ]
-        speed_threshold: 10
-      top_k: 10
-      modules:
-        - module_type: bm25
-        - module_type: vectordb
-          vectordb: default
-        - module_type: hybrid_rrf
-          weight_range: (4,80)
-        - module_type: hybrid_cc
-          normalize_method: [ mm, tmm, z, dbsf ]
-          weight_range: (0.0, 1.0)
-          test_weight_size: 101
-    - node_type: passage_augmenter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      top_k: 5
-      embedding_model: openai
-      modules:
-        - module_type: pass_passage_augmenter
-        - module_type: prev_next_augmenter
-          mode: next
-    - node_type: passage_reranker
-      strategy:
-        metrics: [retrieval_f1, retrieval_recall, retrieval_precision]
-        speed_threshold: 10
-      top_k: 5
-      modules:
-        - module_type: pass_reranker
-        - module_type: tart
-        - module_type: monot5
-        - module_type: upr
-        - module_type: cohere_reranker
-        - module_type: rankgpt
-        - module_type: jina_reranker
-        - module_type: colbert_reranker
-        - module_type: sentence_transformer_reranker
-        - module_type: flag_embedding_reranker
-        - module_type: flag_embedding_llm_reranker
-        - module_type: time_reranker
-        - module_type: openvino_reranker
-        - module_type: voyageai_reranker
-        - module_type: mixedbreadai_reranker
-        - module_type: flashrank_reranker
-    - node_type: passage_filter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      modules:
-        - module_type: pass_passage_filter
-        - module_type: similarity_threshold_cutoff
-          threshold: 0.85
-        - module_type: similarity_percentile_cutoff
-          percentile: 0.6
-        - module_type: recency_filter
-          threshold_datetime: 2015-01-01 3:45:07
-        - module_type: threshold_cutoff
-          threshold: 0.85
-        - module_type: percentile_cutoff
-          percentile: 0.6
-    - node_type: passage_compressor
-      strategy:
-        metrics: [retrieval_token_f1, retrieval_token_recall, retrieval_token_precision]
-        speed_threshold: 10
-      modules:
-        - module_type: pass_compressor
-        - module_type: tree_summarize
-          llm: openai
-          model: gpt-4o-mini
-        - module_type: refine
-          llm: openai
-          model: gpt-4o-mini
-        - module_type: longllmlingua
-- node_line_name: post_retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: prompt_maker
-      strategy:
-        metrics:
-          - metric_name: bleu
-          - metric_name: meteor
-          - metric_name: rouge
-          - metric_name: sem_score
-            embedding_model: openai
-          - metric_name: g_eval
-        speed_threshold: 10
-        generator_modules:
-          - module_type: llama_index_llm
-            llm: openai
-            model: [gpt-4o-mini]
-      modules:
-        - module_type: fstring
-          prompt: ["Tell me something about the question: {query} \n\n {retrieved_contents}",
-                   "Question: {query} \n Something to read: {retrieved_contents} \n What's your answer?"]
-        - module_type: long_context_reorder
-          prompt: [ "Tell me something about the question: {query} \n\n {retrieved_contents}",
-                    "Question: {query} \n Something to read: {retrieved_contents} \n What's your answer?" ]
-        - module_type: window_replacement
-          prompt: [ "Tell me something about the question: {query} \n\n {retrieved_contents}",
-                    "Question: {query} \n Something to read: {retrieved_contents} \n What's your answer?" ]
-    - node_type: generator
-      strategy:
-        metrics:
-          - metric_name: bleu
-          - metric_name: meteor
-          - metric_name: rouge
-          - metric_name: sem_score
-            embedding_model: openai
-          - metric_name: g_eval  # LLM Judge Metric. Default Model: gpt-4-turbo
-        speed_threshold: 10
-      modules:
-        - module_type: llama_index_llm
-          llm: [openai]
-          model: [gpt-4o-mini]
-          temperature: [0.5, 1.0, 1.5]
-        - module_type: openai_llm
-          llm: gpt-4o-mini
-          temperature: 0.8
diff --git a/autorag-workspace/example/sample_config/rag/english/gpu_api/half.yaml b/autorag-workspace/example/sample_config/rag/english/gpu_api/half.yaml
deleted file mode 100644
index 75e1a0c..0000000
--- a/autorag-workspace/example/sample_config/rag/english/gpu_api/half.yaml
+++ /dev/null
@@ -1,118 +0,0 @@
-node_lines:
-- node_line_name: retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: retrieval
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision,
-                   retrieval_ndcg, retrieval_map, retrieval_mrr ]
-        speed_threshold: 10
-      top_k: 10
-      modules:
-        - module_type: bm25
-          bm25_tokenizer: [ porter_stemmer, space, gpt2 ]
-        - module_type: vectordb
-          vectordb: default
-        - module_type: hybrid_rrf
-          weight_range: (4,80)
-        - module_type: hybrid_cc
-          normalize_method: [ mm, tmm, z, dbsf ]
-          weight_range: (0.0, 1.0)
-          test_weight_size: 101
-    - node_type: passage_augmenter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      top_k: 5
-      embedding_model: openai
-      modules:
-        - module_type: pass_passage_augmenter
-        - module_type: prev_next_augmenter
-          mode: next
-    - node_type: passage_reranker
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 10
-      top_k: 5
-      modules:
-        - module_type: pass_reranker
-        - module_type: tart
-        - module_type: monot5
-        - module_type: upr
-        - module_type: cohere_reranker
-        - module_type: rankgpt
-        - module_type: jina_reranker
-        - module_type: colbert_reranker
-        - module_type: sentence_transformer_reranker
-        - module_type: flag_embedding_reranker
-        - module_type: flag_embedding_llm_reranker
-        - module_type: time_reranker
-        - module_type: openvino_reranker
-        - module_type: voyageai_reranker
-        - module_type: mixedbreadai_reranker
-        - module_type: flashrank_reranker
-    - node_type: passage_filter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      modules:
-        - module_type: pass_passage_filter
-        - module_type: similarity_threshold_cutoff
-          threshold: 0.85
-        - module_type: similarity_percentile_cutoff
-          percentile: 0.6
-        - module_type: threshold_cutoff
-          threshold: 0.85
-        - module_type: percentile_cutoff
-          percentile: 0.6
-    - node_type: passage_compressor
-      strategy:
-        metrics: [retrieval_token_f1, retrieval_token_recall, retrieval_token_precision]
-        speed_threshold: 10
-      modules:
-        - module_type: pass_compressor
-        - module_type: tree_summarize
-          llm: openai
-          model: gpt-4o-mini
-        - module_type: refine
-          llm: openai
-          model: gpt-4o-mini
-        - module_type: longllmlingua
-- node_line_name: post_retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: prompt_maker
-      strategy:
-        metrics:
-          - metric_name: bleu
-          - metric_name: meteor
-          - metric_name: rouge
-          - metric_name: sem_score
-            embedding_model: openai
-        speed_threshold: 10
-        generator_modules:
-          - module_type: llama_index_llm
-            llm: openai
-            model: [gpt-4o-mini]
-      modules:
-        - module_type: fstring
-          prompt:
-            - "Answer to given questions with the following passage: {retrieved_contents} \n\n Question: {query} \n\n Answer:"
-            - "There is a passages related to user question. Please response carefully to the following question. \n\n Passage: {retrieved_contents} \n\n Question: {query} \n\n Answer the question. Think step by step." # Zero-shot CoT prompt
-            - "{retrieved_contents} \n\n Read the passage carefully, and answer this question. \n\n Question: {query} \n\n Answer the question. Be concise." # concise prompt
-        - module_type: long_context_reorder
-          prompt:
-            - "Answer to given questions with the following passage: {retrieved_contents} \n\n Question: {query} \n\n Answer:"
-            - "There is a passages related to user question. Please response carefully to the following question. \n\n Passage: {retrieved_contents} \n\n Question: {query} \n\n Answer the question. Think step by step." # Zero-shot CoT prompt
-            - "{retrieved_contents} \n\n Read the passage carefully, and answer this question. \n\n Question: {query} \n\n Answer the question. Be concise." # concise prompt
-    - node_type: generator
-      strategy:
-        metrics:
-          - metric_name: rouge
-          - embedding_model: openai
-            metric_name: sem_score
-          - metric_name: bert_score
-        speed_threshold: 10
-      modules:
-        - module_type: llama_index_llm
-          llm: [openai]
-          model: [gpt-4o-mini]
-          temperature: [0.5, 1.0]
diff --git a/autorag-workspace/example/sample_config/rag/english/non_gpu/compact.yaml b/autorag-workspace/example/sample_config/rag/english/non_gpu/compact.yaml
deleted file mode 100644
index 63ad754..0000000
--- a/autorag-workspace/example/sample_config/rag/english/non_gpu/compact.yaml
+++ /dev/null
@@ -1,83 +0,0 @@
-node_lines:
-- node_line_name: retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: retrieval
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision,
-                   retrieval_ndcg, retrieval_map, retrieval_mrr ]
-        speed_threshold: 10
-      top_k: 10
-      modules:
-        - module_type: bm25
-          bm25_tokenizer: [ porter_stemmer, space, gpt2 ]
-        - module_type: vectordb
-          vectordb: default
-        - module_type: hybrid_rrf
-          weight_range: (4,80)
-        - module_type: hybrid_cc
-          normalize_method: [ mm, tmm, z, dbsf ]
-          weight_range: (0.0, 1.0)
-          test_weight_size: 101
-    - node_type: passage_augmenter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      top_k: 5
-      embedding_model: openai
-      modules:
-        - module_type: pass_passage_augmenter
-        - module_type: prev_next_augmenter
-          mode: next
-    - node_type: passage_filter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      modules:
-        - module_type: pass_passage_filter
-        - module_type: similarity_threshold_cutoff
-          threshold: 0.85
-        - module_type: similarity_percentile_cutoff
-          percentile: 0.6
-        - module_type: threshold_cutoff
-          threshold: 0.85
-        - module_type: percentile_cutoff
-          percentile: 0.6
-- node_line_name: post_retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: prompt_maker
-      strategy:
-        metrics:
-          - metric_name: bleu
-          - metric_name: meteor
-          - metric_name: rouge
-          - metric_name: sem_score
-            embedding_model: openai
-        speed_threshold: 10
-        generator_modules:
-          - module_type: llama_index_llm
-            llm: openai
-            model: [gpt-4o-mini]
-      modules:
-        - module_type: fstring
-          prompt:
-            - "Answer to given questions with the following passage: {retrieved_contents} \n\n Question: {query} \n\n Answer:"
-            - "There is a passages related to user question. Please response carefully to the following question. \n\n Passage: {retrieved_contents} \n\n Question: {query} \n\n Answer the question. Think step by step." # Zero-shot CoT prompt
-            - "{retrieved_contents} \n\n Read the passage carefully, and answer this question. \n\n Question: {query} \n\n Answer the question. Be concise." # concise prompt
-        - module_type: long_context_reorder
-          prompt:
-            - "Answer to given questions with the following passage: {retrieved_contents} \n\n Question: {query} \n\n Answer:"
-            - "There is a passages related to user question. Please response carefully to the following question. \n\n Passage: {retrieved_contents} \n\n Question: {query} \n\n Answer the question. Think step by step." # Zero-shot CoT prompt
-            - "{retrieved_contents} \n\n Read the passage carefully, and answer this question. \n\n Question: {query} \n\n Answer the question. Be concise." # concise prompt
-    - node_type: generator
-      strategy:
-        metrics:
-          - metric_name: rouge
-          - embedding_model: openai
-            metric_name: sem_score
-          - metric_name: bert_score
-        speed_threshold: 10
-      modules:
-        - module_type: llama_index_llm
-          llm: [openai]
-          model: [gpt-4o-mini]
-          temperature: [0.5, 1.0]
diff --git a/autorag-workspace/example/sample_config/rag/english/non_gpu/full.yaml b/autorag-workspace/example/sample_config/rag/english/non_gpu/full.yaml
deleted file mode 100644
index ba18f58..0000000
--- a/autorag-workspace/example/sample_config/rag/english/non_gpu/full.yaml
+++ /dev/null
@@ -1,129 +0,0 @@
-node_lines:
-- node_line_name: pre_retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: query_expansion
-      strategy:
-        metrics: [retrieval_f1, retrieval_recall, retrieval_precision]
-        speed_threshold: 10
-        top_k: 10
-        retrieval_modules:
-          - module_type: bm25
-            bm25_tokenizer: [ porter_stemmer, space, gpt2 ]
-          - module_type: vectordb
-            vectordb: default
-      modules:
-        - module_type: pass_query_expansion
-        - module_type: query_decompose
-          generator_module_type: llama_index_llm
-          llm: openai
-          model: [ gpt-4o-mini ]
-        - module_type: hyde
-          generator_module_type: llama_index_llm
-          llm: openai
-          model: [ gpt-4o-mini ]
-          max_token: 64
-        - module_type: multi_query_expansion
-          generator_module_type: llama_index_llm
-          llm: openai
-          temperature: [ 0.2, 1.0 ]
-- node_line_name: retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: retrieval
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision,
-                   retrieval_ndcg, retrieval_map, retrieval_mrr ]
-        speed_threshold: 10
-      top_k: 10
-      modules:
-        - module_type: bm25
-        - module_type: vectordb
-          embedding_model: openai
-          embedding_batch: 256
-        - module_type: hybrid_rrf
-          weight_range: (4,80)
-        - module_type: hybrid_cc
-          normalize_method: [ mm, tmm, z, dbsf ]
-          weight_range: (0.0, 1.0)
-          test_weight_size: 101
-    - node_type: passage_augmenter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      top_k: 5
-      embedding_model: openai
-      modules:
-        - module_type: pass_passage_augmenter
-        - module_type: prev_next_augmenter
-          mode: next
-    - node_type: passage_filter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      modules:
-        - module_type: pass_passage_filter
-        - module_type: similarity_threshold_cutoff
-          threshold: 0.85
-        - module_type: similarity_percentile_cutoff
-          percentile: 0.6
-        - module_type: recency_filter
-          threshold_datetime: 2015-01-01 3:45:07
-        - module_type: threshold_cutoff
-          threshold: 0.85
-        - module_type: percentile_cutoff
-          percentile: 0.6
-    - node_type: passage_compressor
-      strategy:
-        metrics: [retrieval_token_f1, retrieval_token_recall, retrieval_token_precision]
-        speed_threshold: 10
-      modules:
-        - module_type: pass_compressor
-        - module_type: tree_summarize
-          llm: openai
-          model: gpt-4o-mini
-        - module_type: refine
-          llm: openai
-          model: gpt-4o-mini
-- node_line_name: post_retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: prompt_maker
-      strategy:
-        metrics:
-          - metric_name: bleu
-          - metric_name: meteor
-          - metric_name: rouge
-          - metric_name: sem_score
-            embedding_model: openai
-          - metric_name: g_eval
-        speed_threshold: 10
-        generator_modules:
-          - module_type: llama_index_llm
-            llm: openai
-            model: [gpt-4o-mini]
-      modules:
-        - module_type: fstring
-          prompt: ["Tell me something about the question: {query} \n\n {retrieved_contents}",
-                   "Question: {query} \n Something to read: {retrieved_contents} \n What's your answer?"]
-        - module_type: long_context_reorder
-          prompt: [ "Tell me something about the question: {query} \n\n {retrieved_contents}",
-                    "Question: {query} \n Something to read: {retrieved_contents} \n What's your answer?" ]
-        - module_type: window_replacement
-          prompt: [ "Tell me something about the question: {query} \n\n {retrieved_contents}",
-                    "Question: {query} \n Something to read: {retrieved_contents} \n What's your answer?" ]
-    - node_type: generator
-      strategy:
-        metrics:
-          - metric_name: bleu
-          - metric_name: meteor
-          - metric_name: rouge
-          - metric_name: sem_score
-            embedding_model: openai
-          - metric_name: g_eval  # LLM Judge Metric. Default Model: gpt-4-turbo
-        speed_threshold: 10
-      modules:
-        - module_type: llama_index_llm
-          llm: [openai]
-          model: [gpt-4o-mini]
-          temperature: [0.5, 1.0, 1.5]
-        - module_type: openai_llm
-          llm: gpt-4o-mini
-          temperature: 0.8
diff --git a/autorag-workspace/example/sample_config/rag/english/non_gpu/half.yaml b/autorag-workspace/example/sample_config/rag/english/non_gpu/half.yaml
deleted file mode 100644
index 19aaf7a..0000000
--- a/autorag-workspace/example/sample_config/rag/english/non_gpu/half.yaml
+++ /dev/null
@@ -1,95 +0,0 @@
-node_lines:
-- node_line_name: retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: retrieval
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision,
-                   retrieval_ndcg, retrieval_map, retrieval_mrr ]
-        speed_threshold: 10
-      top_k: 10
-      modules:
-        - module_type: bm25
-          bm25_tokenizer: [ porter_stemmer, space, gpt2 ]
-        - module_type: vectordb
-          vectordb: default
-        - module_type: hybrid_rrf
-          weight_range: (4,80)
-        - module_type: hybrid_cc
-          normalize_method: [ mm, tmm, z, dbsf ]
-          weight_range: (0.0, 1.0)
-          test_weight_size: 101
-    - node_type: passage_augmenter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      top_k: 5
-      embedding_model: openai
-      modules:
-        - module_type: pass_passage_augmenter
-        - module_type: prev_next_augmenter
-          mode: next
-    - node_type: passage_filter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      modules:
-        - module_type: pass_passage_filter
-        - module_type: similarity_threshold_cutoff
-          threshold: 0.85
-        - module_type: similarity_percentile_cutoff
-          percentile: 0.6
-        - module_type: threshold_cutoff
-          threshold: 0.85
-        - module_type: percentile_cutoff
-          percentile: 0.6
-    - node_type: passage_compressor
-      strategy:
-        metrics: [retrieval_token_f1, retrieval_token_recall, retrieval_token_precision]
-        speed_threshold: 10
-      modules:
-        - module_type: pass_compressor
-        - module_type: tree_summarize
-          llm: openai
-          model: gpt-4o-mini
-        - module_type: refine
-          llm: openai
-          model: gpt-4o-mini
-- node_line_name: post_retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: prompt_maker
-      strategy:
-        metrics:
-          - metric_name: bleu
-          - metric_name: meteor
-          - metric_name: rouge
-          - metric_name: sem_score
-            embedding_model: openai
-        speed_threshold: 10
-        generator_modules:
-          - module_type: llama_index_llm
-            llm: openai
-            model: [gpt-4o-mini]
-      modules:
-        - module_type: fstring
-          prompt:
-            - "Answer to given questions with the following passage: {retrieved_contents} \n\n Question: {query} \n\n Answer:"
-            - "There is a passages related to user question. Please response carefully to the following question. \n\n Passage: {retrieved_contents} \n\n Question: {query} \n\n Answer the question. Think step by step." # Zero-shot CoT prompt
-            - "{retrieved_contents} \n\n Read the passage carefully, and answer this question. \n\n Question: {query} \n\n Answer the question. Be concise." # concise prompt
-        - module_type: long_context_reorder
-          prompt:
-            - "Answer to given questions with the following passage: {retrieved_contents} \n\n Question: {query} \n\n Answer:"
-            - "There is a passages related to user question. Please response carefully to the following question. \n\n Passage: {retrieved_contents} \n\n Question: {query} \n\n Answer the question. Think step by step." # Zero-shot CoT prompt
-            - "{retrieved_contents} \n\n Read the passage carefully, and answer this question. \n\n Question: {query} \n\n Answer the question. Be concise." # concise prompt
-    - node_type: generator
-      strategy:
-        metrics:
-          - metric_name: rouge
-          - embedding_model: openai
-            metric_name: sem_score
-          - metric_name: bert_score
-        speed_threshold: 10
-      modules:
-        - module_type: llama_index_llm
-          llm: [openai]
-          model: [gpt-4o-mini]
-          temperature: [0.5, 1.0]
diff --git a/autorag-workspace/example/sample_config/rag/english/non_gpu/simple_bedrock.yaml b/autorag-workspace/example/sample_config/rag/english/non_gpu/simple_bedrock.yaml
deleted file mode 100644
index e59fb63..0000000
--- a/autorag-workspace/example/sample_config/rag/english/non_gpu/simple_bedrock.yaml
+++ /dev/null
@@ -1,33 +0,0 @@
-vectordb:
-  - name: mpnet_base_chroma
-    db_type: chroma
-    client_type: persistent
-    embedding_model: huggingface_all_mpnet_base_v2
-    collection_name: huggingface_all_mpnet_base_v2
-    path: ${PROJECT_DIR}/data/chroma
-node_lines:
-  - node_line_name: retrieve_node_line
-    nodes:
-      - node_type: retrieval
-        strategy:
-          metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        top_k: 3
-        modules:
-          - module_type: vectordb
-            vectordb: mpnet_base_chroma
-  - node_line_name: post_retrieve_node_line
-    nodes:
-      - node_type: prompt_maker
-        strategy:
-          metrics: [ meteor, rouge, bert_score ]
-        modules:
-          - module_type: fstring
-            prompt: "Read the passages and answer the given question. \n Question: {query} \n Passage: {retrieved_contents} \n Answer : "
-      - node_type: generator
-        strategy:
-          metrics: [ bleu, rouge, bert_score ]
-        modules:
-          - module_type: llama_index_llm
-            llm: bedrock
-            model: amazon.titan-text-express-v1
-            profile_name: your_profile_name # Plz replace this with your profile name
diff --git a/autorag-workspace/example/sample_config/rag/english/non_gpu/simple_local.yaml b/autorag-workspace/example/sample_config/rag/english/non_gpu/simple_local.yaml
deleted file mode 100644
index f366b66..0000000
--- a/autorag-workspace/example/sample_config/rag/english/non_gpu/simple_local.yaml
+++ /dev/null
@@ -1,31 +0,0 @@
-vectordb:
-  - name: baai_chroma
-    db_type: chroma
-    client_type: persistent
-    embedding_model: huggingface_baai_bge_small
-    collection_name: huggingface_baai_bge_small
-    path: ${PROJECT_DIR}/data/chroma
-node_lines:
-- node_line_name: retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: retrieval
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-      top_k: 3
-      modules:
-        - module_type: vectordb
-          vectordb: baai_chroma
-- node_line_name: post_retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: prompt_maker
-      strategy:
-        metrics: [ meteor, rouge, bert_score ]
-      modules:
-        - module_type: fstring
-          prompt: "Read the passages and answer the given question. \n Question: {query} \n Passage: {retrieved_contents} \n Answer : "
-    - node_type: generator
-      strategy:
-        metrics: [ bleu, rouge, bert_score ]
-      modules:
-        - module_type: vllm
-          llm: mistralai/Mistral-7B-Instruct-v0.2
diff --git a/autorag-workspace/example/sample_config/rag/english/non_gpu/simple_ollama.yaml b/autorag-workspace/example/sample_config/rag/english/non_gpu/simple_ollama.yaml
deleted file mode 100644
index 32eb8ca..0000000
--- a/autorag-workspace/example/sample_config/rag/english/non_gpu/simple_ollama.yaml
+++ /dev/null
@@ -1,34 +0,0 @@
-vectordb:
-  - name: mpnet_base_chroma
-    db_type: chroma
-    client_type: persistent
-    embedding_model: huggingface_all_mpnet_base_v2
-    collection_name: huggingface_all_mpnet_base_v2
-    path: ${PROJECT_DIR}/data/chroma
-node_lines:
-  - node_line_name: retrieve_node_line
-    nodes:
-      - node_type: retrieval
-        strategy:
-          metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        top_k: 3
-        modules:
-          - module_type: vectordb
-            vectordb: mpnet_base_chroma
-  - node_line_name: post_retrieve_node_line
-    nodes:
-      - node_type: prompt_maker
-        strategy:
-          metrics: [ meteor, rouge, bert_score ]
-        modules:
-          - module_type: fstring
-            prompt: "Read the passages and answer the given question. \n Question: {query} \n Passage: {retrieved_contents} \n Answer : "
-      - node_type: generator
-        strategy:
-          metrics: [ bleu, rouge, bert_score ]
-        modules:
-          - module_type: llama_index_llm
-            llm: ollama
-            model: llama3
-            batch: 1
-            request_timeout: 100 # You can increase this value if your model is big (slow)
diff --git a/autorag-workspace/example/sample_config/rag/english/non_gpu/simple_openai.yaml b/autorag-workspace/example/sample_config/rag/english/non_gpu/simple_openai.yaml
deleted file mode 100644
index 923c490..0000000
--- a/autorag-workspace/example/sample_config/rag/english/non_gpu/simple_openai.yaml
+++ /dev/null
@@ -1,25 +0,0 @@
-node_lines:
-- node_line_name: retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: retrieval
-      strategy:
-        metrics: [retrieval_f1, retrieval_recall, retrieval_precision]
-      top_k: 3
-      modules:
-        - module_type: vectordb
-          vectordb: default
-- node_line_name: post_retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: prompt_maker
-      strategy:
-        metrics: [bleu, meteor, rouge]
-      modules:
-        - module_type: fstring
-          prompt: "Read the passages and answer the given question. \n Question: {query} \n Passage: {retrieved_contents} \n Answer : "
-    - node_type: generator
-      strategy:
-        metrics: [bleu, rouge]
-      modules:
-        - module_type: llama_index_llm
-          llm: openai
-          model: [ gpt-4o-mini ]
diff --git a/autorag-workspace/example/sample_config/rag/extracted_sample.yaml b/autorag-workspace/example/sample_config/rag/extracted_sample.yaml
deleted file mode 100644
index 01f48ed..0000000
--- a/autorag-workspace/example/sample_config/rag/extracted_sample.yaml
+++ /dev/null
@@ -1,47 +0,0 @@
-vectordb:
-  - name: default
-    db_type: chroma
-    client_type: persistent
-    embedding_model: openai
-    collection_name: openai
-    path: ${PROJECT_DIR}/data/chroma
-node_lines:
-- node_line_name: retrieve_node_line
-  nodes:
-  - node_type: retrieval
-    modules:
-    - module_type: vectordb
-      vectordb: default
-      top_k: 3
-    strategy:
-      metrics:
-      - retrieval_f1
-      - retrieval_recall
-      - retrieval_precision
-- node_line_name: post_retrieve_node_line
-  nodes:
-  - node_type: prompt_maker
-    modules:
-    - module_type: fstring
-      prompt: "Read the passages and answer the given question. \n Question: {query} \n Passage: {retrieved_contents} \n Answer : "
-    strategy:
-      generator_modules:
-      - batch: 2
-        llm: openai
-        module_type: llama_index_llm
-      metrics:
-      - bleu
-      - meteor
-      - rouge
-  - node_type: generator
-    modules:
-    - batch: 2
-      llm: openai
-      model: gpt-3.5-turbo-16k
-      module_type: llama_index_llm
-    strategy:
-      metrics:
-      - metric_name: bleu
-      - metric_name: meteor
-      - embedding_model: openai
-        metric_name: sem_score
diff --git a/autorag-workspace/example/sample_config/rag/full.yaml b/autorag-workspace/example/sample_config/rag/full.yaml
deleted file mode 100644
index 92fd748..0000000
--- a/autorag-workspace/example/sample_config/rag/full.yaml
+++ /dev/null
@@ -1,159 +0,0 @@
-vectordb:
-  - name: chroma_large
-    db_type: chroma
-    client_type: persistent
-    embedding_model: openai_embed_3_large
-    collection_name: openai_embed_3_large
-    path: ${PROJECT_DIR}/resources/chroma
-node_lines:
-- node_line_name: pre_retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: query_expansion
-      strategy:
-        metrics: [retrieval_f1, retrieval_recall, retrieval_precision]
-        speed_threshold: 10
-        top_k: 10
-        retrieval_modules:
-          - module_type: bm25
-            bm25_tokenizer: [ porter_stemmer, ko_kiwi, space, gpt2, ko_okt, ko_kkma, sudachipy ]
-          - module_type: vectordb
-            vectordb: chroma_large
-      modules:
-        - module_type: pass_query_expansion
-        - module_type: query_decompose
-          generator_module_type: llama_index_llm
-          llm: openai
-          model: [ gpt-3.5-turbo-16k, gpt-3.5-turbo-1106 ]
-        - module_type: hyde
-          generator_module_type: llama_index_llm
-          llm: openai
-          model: [ gpt-3.5-turbo-16k ]
-          max_token: 64
-        - module_type: multi_query_expansion
-          generator_module_type: llama_index_llm
-          llm: openai
-          temperature: [ 0.2, 1.0 ]
-- node_line_name: retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: retrieval
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision,
-                   retrieval_ndcg, retrieval_map, retrieval_mrr ]
-        speed_threshold: 10
-      top_k: 10
-      modules:
-        - module_type: bm25
-        - module_type: vectordb
-          vectordb: chroma_large
-          embedding_batch: 256
-        - module_type: hybrid_rrf
-          weight_range: (4,80)
-        - module_type: hybrid_cc
-          normalize_method: [ mm, tmm, z, dbsf ]
-          weight_range: (0.0, 1.0)
-          test_weight_size: 101
-    - node_type: passage_augmenter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      top_k: 5
-      embedding_model: openai
-      modules:
-        - module_type: pass_passage_augmenter
-        - module_type: prev_next_augmenter
-          mode: next
-    - node_type: passage_reranker
-      strategy:
-        metrics: [retrieval_f1, retrieval_recall, retrieval_precision]
-        speed_threshold: 10
-      top_k: 5
-      modules:
-        - module_type: pass_reranker
-        - module_type: tart
-        - module_type: monot5
-        - module_type: upr
-        - module_type: cohere_reranker
-        - module_type: rankgpt
-        - module_type: jina_reranker
-        - module_type: colbert_reranker
-        - module_type: sentence_transformer_reranker
-        - module_type: flag_embedding_reranker
-        - module_type: flag_embedding_llm_reranker
-        - module_type: time_reranker
-        - module_type: openvino_reranker
-        - module_type: voyageai_reranker
-        - module_type: mixedbreadai_reranker
-        - module_type: flashrank_reranker
-    - node_type: passage_filter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      modules:
-        - module_type: pass_passage_filter
-        - module_type: similarity_threshold_cutoff
-          threshold: 0.85
-        - module_type: similarity_percentile_cutoff
-          percentile: 0.6
-        - module_type: recency_filter
-          threshold_datetime: 2015-01-01 3:45:07
-        - module_type: threshold_cutoff
-          threshold: 0.85
-        - module_type: percentile_cutoff
-          percentile: 0.6
-    - node_type: passage_compressor
-      strategy:
-        metrics: [retrieval_token_f1, retrieval_token_recall, retrieval_token_precision]
-        speed_threshold: 10
-      modules:
-        - module_type: pass_compressor
-        - module_type: tree_summarize
-          llm: openai
-          model: gpt-3.5-turbo-16k
-        - module_type: refine
-          llm: openai
-          model: gpt-3.5-turbo-16k
-        - module_type: longllmlingua
-- node_line_name: post_retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: prompt_maker
-      strategy:
-        metrics:
-          - metric_name: bleu
-          - metric_name: meteor
-          - metric_name: rouge
-          - metric_name: sem_score
-            embedding_model: openai
-          - metric_name: g_eval
-        speed_threshold: 10
-        generator_modules:
-          - module_type: llama_index_llm
-            llm: openai
-            model: [gpt-3.5-turbo-16k, gpt-3.5-turbo-1106]
-      modules:
-        - module_type: fstring
-          prompt: ["Tell me something about the question: {query} \n\n {retrieved_contents}",
-                   "Question: {query} \n Something to read: {retrieved_contents} \n What's your answer?"]
-        - module_type: long_context_reorder
-          prompt: [ "Tell me something about the question: {query} \n\n {retrieved_contents}",
-                    "Question: {query} \n Something to read: {retrieved_contents} \n What's your answer?" ]
-        - module_type: window_replacement
-          prompt: [ "Tell me something about the question: {query} \n\n {retrieved_contents}",
-                    "Question: {query} \n Something to read: {retrieved_contents} \n What's your answer?" ]
-    - node_type: generator
-      strategy:
-        metrics:
-          - metric_name: bleu
-          - metric_name: meteor
-          - metric_name: rouge
-          - metric_name: sem_score
-            embedding_model: openai
-          - metric_name: g_eval
-        speed_threshold: 10
-      modules:
-        - module_type: llama_index_llm
-          llm: [openai]
-          model: [gpt-3.5-turbo-16k, gpt-3.5-turbo-1106]
-          temperature: [0.5, 1.0, 1.5]
-        - module_type: openai_llm
-          llm: gpt-3.5-turbo
-          temperature: 0.8
diff --git a/autorag-workspace/example/sample_config/rag/korean/gpu/compact_korean.yaml b/autorag-workspace/example/sample_config/rag/korean/gpu/compact_korean.yaml
deleted file mode 100644
index 3bcc84b..0000000
--- a/autorag-workspace/example/sample_config/rag/korean/gpu/compact_korean.yaml
+++ /dev/null
@@ -1,93 +0,0 @@
-vectordb:
-  - name: chroma_bge_m3
-    db_type: chroma
-    client_type: persistent
-    embedding_model: huggingface_bge_m3
-    collection_name: openai
-    path: ${PROJECT_DIR}/resources/chroma
-node_lines:
-- node_line_name: retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: retrieval
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision,
-                   retrieval_ndcg, retrieval_map, retrieval_mrr ]
-        speed_threshold: 10
-      top_k: 10
-      modules:
-        - module_type: bm25
-          bm25_tokenizer: [ ko_kiwi, ko_okt, ko_kkma ]
-        - module_type: vectordb
-          vectordb: chroma_bge_m3
-        - module_type: hybrid_rrf
-          weight_range: (4,80)
-        - module_type: hybrid_cc
-          normalize_method: [ mm, tmm, z, dbsf ]
-          weight_range: (0.0, 1.0)
-          test_weight_size: 101
-    - node_type: passage_augmenter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      top_k: 5
-      embedding_model: openai
-      modules:
-        - module_type: pass_passage_augmenter
-        - module_type: prev_next_augmenter
-          mode: next
-    - node_type: passage_reranker
-      modules:
-        - module_type: koreranker
-        - module_type: flag_embedding_llm_reranker  # Requires enough GPU resources
-        - module_type: pass_reranker
-      strategy:
-        metrics: [ retrieval_recall, retrieval_precision, retrieval_map ]
-      top_k: 3
-    - node_type: passage_filter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      modules:
-        - module_type: pass_passage_filter
-        - module_type: similarity_threshold_cutoff
-          threshold: 0.85
-        - module_type: similarity_percentile_cutoff
-          percentile: 0.6
-        - module_type: threshold_cutoff
-          threshold: 0.85
-        - module_type: percentile_cutoff
-          percentile: 0.6
-- node_line_name: post_retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: prompt_maker
-      strategy:
-        metrics:
-          - metric_name: bleu
-          - metric_name: meteor
-          - metric_name: rouge
-          - metric_name: sem_score
-            embedding_model: openai
-        speed_threshold: 10
-        generator_modules:
-          - module_type: llama_index_llm
-            llm: openai
-            model: [gpt-4o-mini]
-      modules:
-        - module_type: fstring
-          prompt: ["주어진 passage만을 이용하여 question에 따라 답하시오 passage: {retrieved_contents} \n\n Question: {query} \n\n Answer:"]
-        - module_type: long_context_reorder
-          prompt: ["주어진 passage만을 이용하여 question에 따라 답하시오 passage: {retrieved_contents} \n\n Question: {query} \n\n Answer:"]
-    - node_type: generator
-      strategy:
-        metrics:
-          - metric_name: rouge
-          - embedding_model: openai
-            metric_name: sem_score
-          - metric_name: bert_score
-            lang: ko
-        speed_threshold: 10
-      modules:
-        - module_type: llama_index_llm
-          llm: [openai]
-          model: [gpt-4o-mini]
-          temperature: [0.5, 1.0]
diff --git a/autorag-workspace/example/sample_config/rag/korean/gpu/full_korean.yaml b/autorag-workspace/example/sample_config/rag/korean/gpu/full_korean.yaml
deleted file mode 100644
index 70bc4b2..0000000
--- a/autorag-workspace/example/sample_config/rag/korean/gpu/full_korean.yaml
+++ /dev/null
@@ -1,157 +0,0 @@
-vectordb:
-  - name: chroma_bge_m3
-    db_type: chroma
-    client_type: persistent
-    embedding_model: huggingface_bge_m3
-    collection_name: openai
-    path: ${PROJECT_DIR}/resources/chroma
-node_lines:
-- node_line_name: pre_retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: query_expansion
-      strategy:
-        metrics: [retrieval_f1, retrieval_recall, retrieval_precision]
-        speed_threshold: 10
-        top_k: 10
-        retrieval_modules:
-          - module_type: bm25
-            bm25_tokenizer: [ porter_stemmer, space, gpt2 ]
-          - module_type: vectordb
-            vectordb: chroma_bge_m3
-      modules:
-        - module_type: pass_query_expansion
-        - module_type: hyde
-          generator_module_type: llama_index_llm
-          llm: openai
-          model: [ gpt-4o-mini ]
-          max_token: 64
-          prompt: "질문에 답하기 위한 단락을 작성해 주세요."
-        - module_type: multi_query_expansion
-          generator_module_type: llama_index_llm
-          llm: openai
-          temperature: [ 0.2, 1.0 ]
-          prompt: |
-            당신은 인공지능 언어 모델 어시스턴트입니다.
-            주어진 사용자 질문을 이용해 세 가지 버전의 새 질문을 생성하여 벡터 데이터베이스에서 관련 문서를 검색하는 것이 과제입니다.
-            주어진 질문에 대한 다양한 관점을 생성함으로써 사용자가 거리 기반 유사도 검색의 한계를 극복할 수 있도록 돕는 것이 목표입니다.
-            다음과 같은 대체 질문을 줄 바꿈으로 구분하여 제공하십시오.
-            원래 질문: {query}
-- node_line_name: retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: retrieval
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision,
-                   retrieval_ndcg, retrieval_map, retrieval_mrr ]
-        speed_threshold: 10
-      top_k: 10
-      modules:
-        - module_type: bm25
-          bm25_tokenizer: [ ko_kiwi, ko_okt, ko_kkma ]
-        - module_type: vectordb
-          vectordb: chroma_bge_m3
-        - module_type: hybrid_rrf
-          weight_range: (4,80)
-        - module_type: hybrid_cc
-          normalize_method: [ mm, tmm, z, dbsf ]
-          weight_range: (0.0, 1.0)
-          test_weight_size: 101
-    - node_type: passage_augmenter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      top_k: 5
-      embedding_model: openai
-      modules:
-        - module_type: pass_passage_augmenter
-        - module_type: prev_next_augmenter
-          mode: next
-    - node_type: passage_reranker
-      modules:
-        - module_type: koreranker
-        - module_type: flag_embedding_llm_reranker  # Requires enough GPU resources
-        - module_type: pass_reranker
-      strategy:
-        metrics: [ retrieval_recall, retrieval_precision, retrieval_map ]
-      top_k: 3
-    - node_type: passage_filter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      modules:
-        - module_type: pass_passage_filter
-        - module_type: similarity_threshold_cutoff
-          threshold: 0.85
-        - module_type: similarity_percentile_cutoff
-          percentile: 0.6
-        - module_type: threshold_cutoff
-          threshold: 0.85
-        - module_type: percentile_cutoff
-          percentile: 0.6
-    - node_type: passage_compressor
-      strategy:
-        metrics: [retrieval_token_f1, retrieval_token_recall, retrieval_token_precision]
-        speed_threshold: 10
-      modules:
-        - module_type: pass_compressor
-        - module_type: tree_summarize
-          llm: openai
-          model: gpt-4o-mini
-          prompt: |
-            여러 문맥 정보는 다음과 같습니다.\n
-            ---------------------\n
-            {context_str}\n
-            ---------------------\n
-            사전 지식이 아닌 여러 정보가 주어졌습니다,
-            질문에 대답하세요.\n
-            질문: {query_str}\n
-            답변:
-        - module_type: refine
-          llm: openai
-          model: gpt-4o-mini
-          prompt: |
-            원래 질문은 다음과 같습니다: {query_str}
-            기존 답변은 다음과 같습니다: {existing_answer}
-            아래에서 기존 답변을 정제할 수 있는 기회가 있습니다.
-            (필요한 경우에만) 아래에 몇 가지 맥락을 추가하여 기존 답변을 정제할 수 있습니다.
-            ------------
-            {context_msg}
-            ------------
-            새로운 문맥이 주어지면 기존 답변을 수정하여 질문에 대한 답변을 정제합니다.
-            맥락이 쓸모 없다면, 기존 답변을 그대로 답변하세요.
-            정제된 답변:
-        - module_type: longllmlingua
-- node_line_name: post_retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: prompt_maker
-      strategy:
-        metrics:
-          - metric_name: bleu
-          - metric_name: meteor
-          - metric_name: rouge
-          - metric_name: sem_score
-            embedding_model: openai
-        speed_threshold: 10
-        generator_modules:
-          - module_type: llama_index_llm
-            llm: openai
-            model: [gpt-4o-mini]
-      modules:
-        - module_type: fstring
-          prompt: ["주어진 passage만을 이용하여 question에 따라 답하시오 passage: {retrieved_contents} \n\n Question: {query} \n\n Answer:"]
-        - module_type: long_context_reorder
-          prompt: ["주어진 passage만을 이용하여 question에 따라 답하시오 passage: {retrieved_contents} \n\n Question: {query} \n\n Answer:"]
-    - node_type: generator
-      strategy:
-        metrics:
-          - metric_name: rouge
-          - embedding_model: openai
-            metric_name: sem_score
-          - metric_name: bert_score
-            lang: ko
-          - metric_name: g_eval  # LLM Judge Metric. Default Model: gpt-4-turbo
-        speed_threshold: 10
-      modules:
-        - module_type: llama_index_llm
-          llm: [openai]
-          model: [gpt-4o-mini]
-          temperature: [0.5, 1.0]
diff --git a/autorag-workspace/example/sample_config/rag/korean/gpu/half_korean.yaml b/autorag-workspace/example/sample_config/rag/korean/gpu/half_korean.yaml
deleted file mode 100644
index a20c356..0000000
--- a/autorag-workspace/example/sample_config/rag/korean/gpu/half_korean.yaml
+++ /dev/null
@@ -1,126 +0,0 @@
-vectordb:
-  - name: chroma_bge_m3
-    db_type: chroma
-    client_type: persistent
-    embedding_model: huggingface_bge_m3
-    collection_name: openai
-    path: ${PROJECT_DIR}/resources/chroma
-node_lines:
-- node_line_name: retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: retrieval
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision,
-                   retrieval_ndcg, retrieval_map, retrieval_mrr ]
-        speed_threshold: 10
-      top_k: 10
-      modules:
-        - module_type: bm25
-          bm25_tokenizer: [ ko_kiwi, ko_okt, ko_kkma ]
-        - module_type: vectordb
-          vectordb: chroma_bge_m3
-        - module_type: hybrid_rrf
-          weight_range: (4,80)
-        - module_type: hybrid_cc
-          normalize_method: [ mm, tmm, z, dbsf ]
-          weight_range: (0.0, 1.0)
-          test_weight_size: 101
-    - node_type: passage_augmenter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      top_k: 5
-      embedding_model: openai
-      modules:
-        - module_type: pass_passage_augmenter
-        - module_type: prev_next_augmenter
-          mode: next
-    - node_type: passage_reranker
-      modules:
-        - module_type: koreranker
-        - module_type: flag_embedding_llm_reranker  # Requires enough GPU resources
-        - module_type: pass_reranker
-      strategy:
-        metrics: [ retrieval_recall, retrieval_precision, retrieval_map ]
-      top_k: 3
-    - node_type: passage_filter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      modules:
-        - module_type: pass_passage_filter
-        - module_type: similarity_threshold_cutoff
-          threshold: 0.85
-        - module_type: similarity_percentile_cutoff
-          percentile: 0.6
-        - module_type: threshold_cutoff
-          threshold: 0.85
-        - module_type: percentile_cutoff
-          percentile: 0.6
-    - node_type: passage_compressor
-      strategy:
-        metrics: [retrieval_token_f1, retrieval_token_recall, retrieval_token_precision]
-        speed_threshold: 10
-      modules:
-        - module_type: pass_compressor
-        - module_type: tree_summarize
-          llm: openai
-          model: gpt-4o-mini
-          prompt: |
-            여러 문맥 정보는 다음과 같습니다.\n
-            ---------------------\n
-            {context_str}\n
-            ---------------------\n
-            사전 지식이 아닌 여러 정보가 주어졌습니다,
-            질문에 대답하세요.\n
-            질문: {query_str}\n
-            답변:
-        - module_type: refine
-          llm: openai
-          model: gpt-4o-mini
-          prompt: |
-            원래 질문은 다음과 같습니다: {query_str}
-            기존 답변은 다음과 같습니다: {existing_answer}
-            아래에서 기존 답변을 정제할 수 있는 기회가 있습니다.
-            (필요한 경우에만) 아래에 몇 가지 맥락을 추가하여 기존 답변을 정제할 수 있습니다.
-            ------------
-            {context_msg}
-            ------------
-            새로운 문맥이 주어지면 기존 답변을 수정하여 질문에 대한 답변을 정제합니다.
-            맥락이 쓸모 없다면, 기존 답변을 그대로 답변하세요.
-            정제된 답변:
-        - module_type: longllmlingua
-- node_line_name: post_retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: prompt_maker
-      strategy:
-        metrics:
-          - metric_name: bleu
-          - metric_name: meteor
-          - metric_name: rouge
-          - metric_name: sem_score
-            embedding_model: openai
-        speed_threshold: 10
-        generator_modules:
-          - module_type: llama_index_llm
-            llm: openai
-            model: [gpt-4o-mini]
-      modules:
-        - module_type: fstring
-          prompt: ["주어진 passage만을 이용하여 question에 따라 답하시오 passage: {retrieved_contents} \n\n Question: {query} \n\n Answer:"]
-        - module_type: long_context_reorder
-          prompt: ["주어진 passage만을 이용하여 question에 따라 답하시오 passage: {retrieved_contents} \n\n Question: {query} \n\n Answer:"]
-    - node_type: generator
-      strategy:
-        metrics:
-          - metric_name: rouge
-          - embedding_model: openai
-            metric_name: sem_score
-          - metric_name: bert_score
-            lang: ko
-        speed_threshold: 10
-      modules:
-        - module_type: llama_index_llm
-          llm: [openai]
-          model: [gpt-4o-mini]
-          temperature: [0.5, 1.0]
diff --git a/autorag-workspace/example/sample_config/rag/korean/gpu_api/compact_korean.yaml b/autorag-workspace/example/sample_config/rag/korean/gpu_api/compact_korean.yaml
deleted file mode 100644
index c60094d..0000000
--- a/autorag-workspace/example/sample_config/rag/korean/gpu_api/compact_korean.yaml
+++ /dev/null
@@ -1,87 +0,0 @@
-node_lines:
-- node_line_name: retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: retrieval
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision,
-                   retrieval_ndcg, retrieval_map, retrieval_mrr ]
-        speed_threshold: 10
-      top_k: 10
-      modules:
-        - module_type: bm25
-          bm25_tokenizer: [ ko_kiwi, ko_okt, ko_kkma ]
-        - module_type: vectordb
-          vectordb: default
-        - module_type: hybrid_rrf
-          weight_range: (4,80)
-        - module_type: hybrid_cc
-          normalize_method: [ mm, tmm, z, dbsf ]
-          weight_range: (0.0, 1.0)
-          test_weight_size: 101
-    - node_type: passage_augmenter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      top_k: 5
-      embedding_model: openai
-      modules:
-        - module_type: pass_passage_augmenter
-        - module_type: prev_next_augmenter
-          mode: next
-    - node_type: passage_reranker
-      modules:
-        - module_type: koreranker
-        - module_type: flag_embedding_llm_reranker  # Requires enough GPU resources
-        - module_type: cohere_reranker  # Set Environment Variable: COHERE_API_KEY
-        - module_type: pass_reranker
-      strategy:
-        metrics: [ retrieval_recall, retrieval_precision, retrieval_map ]
-      top_k: 3
-    - node_type: passage_filter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      modules:
-        - module_type: pass_passage_filter
-        - module_type: similarity_threshold_cutoff
-          threshold: 0.85
-        - module_type: similarity_percentile_cutoff
-          percentile: 0.6
-        - module_type: threshold_cutoff
-          threshold: 0.85
-        - module_type: percentile_cutoff
-          percentile: 0.6
-- node_line_name: post_retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: prompt_maker
-      strategy:
-        metrics:
-          - metric_name: bleu
-          - metric_name: meteor
-          - metric_name: rouge
-          - metric_name: sem_score
-            embedding_model: openai
-        speed_threshold: 10
-        generator_modules:
-          - module_type: llama_index_llm
-            llm: openai
-            model: [gpt-4o-mini]
-      modules:
-        - module_type: fstring
-          prompt: ["주어진 passage만을 이용하여 question에 따라 답하시오 passage: {retrieved_contents} \n\n Question: {query} \n\n Answer:"]
-        - module_type: long_context_reorder
-          prompt: ["주어진 passage만을 이용하여 question에 따라 답하시오 passage: {retrieved_contents} \n\n Question: {query} \n\n Answer:"]
-    - node_type: generator
-      strategy:
-        metrics:
-          - metric_name: rouge
-          - embedding_model: openai
-            metric_name: sem_score
-          - metric_name: bert_score
-            lang: ko
-        speed_threshold: 10
-      modules:
-        - module_type: llama_index_llm
-          llm: [openai]
-          model: [gpt-4o-mini]
-          temperature: [0.5, 1.0]
diff --git a/autorag-workspace/example/sample_config/rag/korean/gpu_api/full_korean.yaml b/autorag-workspace/example/sample_config/rag/korean/gpu_api/full_korean.yaml
deleted file mode 100644
index 5fe9f68..0000000
--- a/autorag-workspace/example/sample_config/rag/korean/gpu_api/full_korean.yaml
+++ /dev/null
@@ -1,151 +0,0 @@
-node_lines:
-- node_line_name: pre_retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: query_expansion
-      strategy:
-        metrics: [retrieval_f1, retrieval_recall, retrieval_precision]
-        speed_threshold: 10
-        top_k: 10
-        retrieval_modules:
-          - module_type: bm25
-            bm25_tokenizer: [ porter_stemmer, space, gpt2 ]
-          - module_type: vectordb
-            vectordb: default
-      modules:
-        - module_type: pass_query_expansion
-        - module_type: hyde
-          generator_module_type: llama_index_llm
-          llm: openai # 
-          model: [ gpt-4o-mini ] #
-          max_token: 64
-          prompt: "질문에 답하기 위한 단락을 작성해 주세요."
-        - module_type: multi_query_expansion
-          generator_module_type: llama_index_llm
-          llm: openai
-          temperature: [ 0.2, 1.0 ]
-          prompt: |
-            당신은 인공지능 언어 모델 어시스턴트입니다.
-            주어진 사용자 질문을 이용해 세 가지 버전의 새 질문을 생성하여 벡터 데이터베이스에서 관련 문서를 검색하는 것이 과제입니다.
-            주어진 질문에 대한 다양한 관점을 생성함으로써 사용자가 거리 기반 유사도 검색의 한계를 극복할 수 있도록 돕는 것이 목표입니다.
-            다음과 같은 대체 질문을 줄 바꿈으로 구분하여 제공하십시오.
-            원래 질문: {query}
-- node_line_name: retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: retrieval
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision,
-                   retrieval_ndcg, retrieval_map, retrieval_mrr ]
-        speed_threshold: 10
-      top_k: 10
-      modules:
-        - module_type: bm25
-          bm25_tokenizer: [ ko_kiwi, ko_okt, ko_kkma ] # ko_kiwi, ko_okt
-        - module_type: vectordb
-          vectordb: default
-        - module_type: hybrid_rrf
-          weight_range: (4,80)
-        - module_type: hybrid_cc
-          normalize_method: [ mm, tmm, z, dbsf ]
-          weight_range: (0.0, 1.0)
-          test_weight_size: 101
-    - node_type: passage_augmenter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      top_k: 5
-      embedding_model: openai
-      modules:
-        - module_type: pass_passage_augmenter
-        - module_type: prev_next_augmenter
-          mode: next
-    - node_type: passage_reranker
-      modules:
-        - module_type: koreranker
-        - module_type: flag_embedding_llm_reranker  # Requires enough GPU resources
-        - module_type: cohere_reranker  # Set Environment Variable: COHERE_API_KEY
-        - module_type: pass_reranker
-      strategy:
-        metrics: [ retrieval_recall, retrieval_precision, retrieval_map ]
-      top_k: 3
-    - node_type: passage_filter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      modules:
-        - module_type: pass_passage_filter
-        - module_type: similarity_threshold_cutoff
-          threshold: 0.85
-        - module_type: similarity_percentile_cutoff
-          percentile: 0.6
-        - module_type: threshold_cutoff
-          threshold: 0.85
-        - module_type: percentile_cutoff
-          percentile: 0.6
-    - node_type: passage_compressor
-      strategy:
-        metrics: [retrieval_token_f1, retrieval_token_recall, retrieval_token_precision]
-        speed_threshold: 10
-      modules:
-        - module_type: pass_compressor
-        - module_type: tree_summarize
-          llm: openai
-          model: gpt-4o-mini
-          prompt: |
-            여러 문맥 정보는 다음과 같습니다.\n
-            ---------------------\n
-            {context_str}\n
-            ---------------------\n
-            사전 지식이 아닌 여러 정보가 주어졌습니다,
-            질문에 대답하세요.\n
-            질문: {query_str}\n
-            답변:
-        - module_type: refine
-          llm: openai
-          model: gpt-4o-mini
-          prompt: |
-            원래 질문은 다음과 같습니다: {query_str}
-            기존 답변은 다음과 같습니다: {existing_answer}
-            아래에서 기존 답변을 정제할 수 있는 기회가 있습니다.
-            (필요한 경우에만) 아래에 몇 가지 맥락을 추가하여 기존 답변을 정제할 수 있습니다.
-            ------------
-            {context_msg}
-            ------------
-            새로운 문맥이 주어지면 기존 답변을 수정하여 질문에 대한 답변을 정제합니다.
-            맥락이 쓸모 없다면, 기존 답변을 그대로 답변하세요.
-            정제된 답변:
-        - module_type: longllmlingua
-- node_line_name: post_retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: prompt_maker
-      strategy:
-        metrics:
-          - metric_name: bleu
-          - metric_name: meteor
-          - metric_name: rouge
-          - metric_name: sem_score
-            embedding_model: openai
-        speed_threshold: 10
-        generator_modules:
-          - module_type: llama_index_llm
-            llm: openai
-            model: [gpt-4o-mini]
-      modules:
-        - module_type: fstring
-          prompt: ["주어진 passage만을 이용하여 question에 따라 답하시오 passage: {retrieved_contents} \n\n Question: {query} \n\n Answer:"]
-        - module_type: long_context_reorder
-          prompt: ["주어진 passage만을 이용하여 question에 따라 답하시오 passage: {retrieved_contents} \n\n Question: {query} \n\n Answer:"]
-    - node_type: generator
-      strategy:
-        metrics:
-          - metric_name: rouge
-          - embedding_model: openai
-            metric_name: sem_score
-          - metric_name: bert_score
-            lang: ko
-          - metric_name: g_eval  # LLM Judge Metric. Default Model: gpt-4-turbo
-        speed_threshold: 10
-      modules:
-        - module_type: llama_index_llm
-          llm: [openai]
-          model: [gpt-4o-mini]
-          temperature: [0.5, 1.0]
diff --git a/autorag-workspace/example/sample_config/rag/korean/gpu_api/half_korean.yaml b/autorag-workspace/example/sample_config/rag/korean/gpu_api/half_korean.yaml
deleted file mode 100644
index 965e9eb..0000000
--- a/autorag-workspace/example/sample_config/rag/korean/gpu_api/half_korean.yaml
+++ /dev/null
@@ -1,120 +0,0 @@
-node_lines:
-- node_line_name: retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: retrieval
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision,
-                   retrieval_ndcg, retrieval_map, retrieval_mrr ]
-        speed_threshold: 10
-      top_k: 10
-      modules:
-        - module_type: bm25
-          bm25_tokenizer: [ ko_kiwi, ko_okt, ko_kkma ]
-        - module_type: vectordb
-          vectordb: default
-        - module_type: hybrid_rrf
-          weight_range: (4,80)
-        - module_type: hybrid_cc
-          normalize_method: [ mm, tmm, z, dbsf ]
-          weight_range: (0.0, 1.0)
-          test_weight_size: 101
-    - node_type: passage_augmenter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      top_k: 5
-      embedding_model: openai
-      modules:
-        - module_type: pass_passage_augmenter
-        - module_type: prev_next_augmenter
-          mode: next
-    - node_type: passage_reranker
-      modules:
-        - module_type: koreranker
-        - module_type: flag_embedding_llm_reranker  # Requires enough GPU resources
-        - module_type: cohere_reranker  # Set Environment Variable: COHERE_API_KEY
-        - module_type: pass_reranker
-      strategy:
-        metrics: [ retrieval_recall, retrieval_precision, retrieval_map ]
-      top_k: 3
-    - node_type: passage_filter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      modules:
-        - module_type: pass_passage_filter
-        - module_type: similarity_threshold_cutoff
-          threshold: 0.85
-        - module_type: similarity_percentile_cutoff
-          percentile: 0.6
-        - module_type: threshold_cutoff
-          threshold: 0.85
-        - module_type: percentile_cutoff
-          percentile: 0.6
-    - node_type: passage_compressor
-      strategy:
-        metrics: [retrieval_token_f1, retrieval_token_recall, retrieval_token_precision]
-        speed_threshold: 10
-      modules:
-        - module_type: pass_compressor
-        - module_type: tree_summarize
-          llm: openai
-          model: gpt-4o-mini
-          prompt: |
-            여러 문맥 정보는 다음과 같습니다.\n
-            ---------------------\n
-            {context_str}\n
-            ---------------------\n
-            사전 지식이 아닌 여러 정보가 주어졌습니다,
-            질문에 대답하세요.\n
-            질문: {query_str}\n
-            답변:
-        - module_type: refine
-          llm: openai
-          model: gpt-4o-mini
-          prompt: |
-            원래 질문은 다음과 같습니다: {query_str}
-            기존 답변은 다음과 같습니다: {existing_answer}
-            아래에서 기존 답변을 정제할 수 있는 기회가 있습니다.
-            (필요한 경우에만) 아래에 몇 가지 맥락을 추가하여 기존 답변을 정제할 수 있습니다.
-            ------------
-            {context_msg}
-            ------------
-            새로운 문맥이 주어지면 기존 답변을 수정하여 질문에 대한 답변을 정제합니다.
-            맥락이 쓸모 없다면, 기존 답변을 그대로 답변하세요.
-            정제된 답변:
-        - module_type: longllmlingua
-- node_line_name: post_retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: prompt_maker
-      strategy:
-        metrics:
-          - metric_name: bleu
-          - metric_name: meteor
-          - metric_name: rouge
-          - metric_name: sem_score
-            embedding_model: openai
-        speed_threshold: 10
-        generator_modules:
-          - module_type: llama_index_llm
-            llm: openai
-            model: [gpt-4o-mini]
-      modules:
-        - module_type: fstring
-          prompt: ["주어진 passage만을 이용하여 question에 따라 답하시오 passage: {retrieved_contents} \n\n Question: {query} \n\n Answer:"]
-        - module_type: long_context_reorder
-          prompt: ["주어진 passage만을 이용하여 question에 따라 답하시오 passage: {retrieved_contents} \n\n Question: {query} \n\n Answer:"]
-    - node_type: generator
-      strategy:
-        metrics:
-          - metric_name: rouge
-          - embedding_model: openai
-            metric_name: sem_score
-          - metric_name: bert_score
-            lang: ko
-        speed_threshold: 10
-      modules:
-        - module_type: llama_index_llm
-          llm: [openai]
-          model: [gpt-4o-mini]
-          temperature: [0.5, 1.0]
diff --git a/autorag-workspace/example/sample_config/rag/korean/non_gpu/compact_korean.yaml b/autorag-workspace/example/sample_config/rag/korean/non_gpu/compact_korean.yaml
deleted file mode 100644
index e10bba6..0000000
--- a/autorag-workspace/example/sample_config/rag/korean/non_gpu/compact_korean.yaml
+++ /dev/null
@@ -1,78 +0,0 @@
-node_lines:
-- node_line_name: retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: retrieval
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision,
-                   retrieval_ndcg, retrieval_map, retrieval_mrr ]
-        speed_threshold: 10
-      top_k: 10
-      modules:
-        - module_type: bm25
-          bm25_tokenizer: [ ko_kiwi, ko_okt, ko_kkma ]
-        - module_type: vectordb
-          vectordb: default
-        - module_type: hybrid_rrf
-          weight_range: (4,80)
-        - module_type: hybrid_cc
-          normalize_method: [ mm, tmm, z, dbsf ]
-          weight_range: (0.0, 1.0)
-          test_weight_size: 101
-    - node_type: passage_augmenter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      top_k: 5
-      embedding_model: openai
-      modules:
-        - module_type: pass_passage_augmenter
-        - module_type: prev_next_augmenter
-          mode: next
-    - node_type: passage_filter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      modules:
-        - module_type: pass_passage_filter
-        - module_type: similarity_threshold_cutoff
-          threshold: 0.85
-        - module_type: similarity_percentile_cutoff
-          percentile: 0.6
-        - module_type: threshold_cutoff
-          threshold: 0.85
-        - module_type: percentile_cutoff
-          percentile: 0.6
-- node_line_name: post_retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: prompt_maker
-      strategy:
-        metrics:
-          - metric_name: bleu
-          - metric_name: meteor
-          - metric_name: rouge
-          - metric_name: sem_score
-            embedding_model: openai
-        speed_threshold: 10
-        generator_modules:
-          - module_type: llama_index_llm
-            llm: openai
-            model: [gpt-4o-mini]
-      modules:
-        - module_type: fstring
-          prompt: ["주어진 passage만을 이용하여 question에 따라 답하시오 passage: {retrieved_contents} \n\n Question: {query} \n\n Answer:"]
-        - module_type: long_context_reorder
-          prompt: ["주어진 passage만을 이용하여 question에 따라 답하시오 passage: {retrieved_contents} \n\n Question: {query} \n\n Answer:"]
-    - node_type: generator
-      strategy:
-        metrics:
-          - metric_name: rouge
-          - embedding_model: openai
-            metric_name: sem_score
-          - metric_name: bert_score
-            lang: ko
-        speed_threshold: 10
-      modules:
-        - module_type: llama_index_llm
-          llm: [openai]
-          model: [gpt-4o-mini]
-          temperature: [0.5, 1.0]
diff --git a/autorag-workspace/example/sample_config/rag/korean/non_gpu/full_korean.yaml b/autorag-workspace/example/sample_config/rag/korean/non_gpu/full_korean.yaml
deleted file mode 100644
index e6b6a65..0000000
--- a/autorag-workspace/example/sample_config/rag/korean/non_gpu/full_korean.yaml
+++ /dev/null
@@ -1,142 +0,0 @@
-node_lines:
-- node_line_name: pre_retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: query_expansion
-      strategy:
-        metrics: [retrieval_f1, retrieval_recall, retrieval_precision]
-        speed_threshold: 10
-        top_k: 10
-        retrieval_modules:
-          - module_type: bm25
-            bm25_tokenizer: [ porter_stemmer, space, gpt2 ]
-          - module_type: vectordb
-            vectordb: default
-      modules:
-        - module_type: pass_query_expansion
-        - module_type: hyde
-          generator_module_type: llama_index_llm
-          llm: openai
-          model: [ gpt-4o-mini ]
-          max_token: 64
-          prompt: "질문에 답하기 위한 단락을 작성해 주세요."
-        - module_type: multi_query_expansion
-          generator_module_type: llama_index_llm
-          llm: openai
-          temperature: [ 0.2, 1.0 ]
-          prompt: |
-            당신은 인공지능 언어 모델 어시스턴트입니다.
-            주어진 사용자 질문을 이용해 세 가지 버전의 새 질문을 생성하여 벡터 데이터베이스에서 관련 문서를 검색하는 것이 과제입니다.
-            주어진 질문에 대한 다양한 관점을 생성함으로써 사용자가 거리 기반 유사도 검색의 한계를 극복할 수 있도록 돕는 것이 목표입니다.
-            다음과 같은 대체 질문을 줄 바꿈으로 구분하여 제공하십시오.
-            원래 질문: {query}
-- node_line_name: retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: retrieval
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision,
-                   retrieval_ndcg, retrieval_map, retrieval_mrr ]
-        speed_threshold: 10
-      top_k: 10
-      modules:
-        - module_type: bm25
-          bm25_tokenizer: [ ko_kiwi, ko_okt, ko_kkma ]
-        - module_type: vectordb
-          vectordb: default
-        - module_type: hybrid_rrf
-          weight_range: (4,80)
-        - module_type: hybrid_cc
-          normalize_method: [ mm, tmm, z, dbsf ]
-          weight_range: (0.0, 1.0)
-          test_weight_size: 101
-    - node_type: passage_augmenter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      top_k: 5
-      embedding_model: openai
-      modules:
-        - module_type: pass_passage_augmenter
-        - module_type: prev_next_augmenter
-          mode: next
-    - node_type: passage_filter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      modules:
-        - module_type: pass_passage_filter
-        - module_type: similarity_threshold_cutoff
-          threshold: 0.85
-        - module_type: similarity_percentile_cutoff
-          percentile: 0.6
-        - module_type: threshold_cutoff
-          threshold: 0.85
-        - module_type: percentile_cutoff
-          percentile: 0.6
-    - node_type: passage_compressor
-      strategy:
-        metrics: [retrieval_token_f1, retrieval_token_recall, retrieval_token_precision]
-        speed_threshold: 10
-      modules:
-        - module_type: pass_compressor
-        - module_type: tree_summarize
-          llm: openai
-          model: gpt-4o-mini
-          prompt: |
-            여러 문맥 정보는 다음과 같습니다.\n
-            ---------------------\n
-            {context_str}\n
-            ---------------------\n
-            사전 지식이 아닌 여러 정보가 주어졌습니다,
-            질문에 대답하세요.\n
-            질문: {query_str}\n
-            답변:
-        - module_type: refine
-          llm: openai
-          model: gpt-4o-mini
-          prompt: |
-            원래 질문은 다음과 같습니다: {query_str}
-            기존 답변은 다음과 같습니다: {existing_answer}
-            아래에서 기존 답변을 정제할 수 있는 기회가 있습니다.
-            (필요한 경우에만) 아래에 몇 가지 맥락을 추가하여 기존 답변을 정제할 수 있습니다.
-            ------------
-            {context_msg}
-            ------------
-            새로운 문맥이 주어지면 기존 답변을 수정하여 질문에 대한 답변을 정제합니다.
-            맥락이 쓸모 없다면, 기존 답변을 그대로 답변하세요.
-            정제된 답변:
-        - module_type: longllmlingua
-- node_line_name: post_retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: prompt_maker
-      strategy:
-        metrics:
-          - metric_name: bleu
-          - metric_name: meteor
-          - metric_name: rouge
-          - metric_name: sem_score
-            embedding_model: openai
-        speed_threshold: 10
-        generator_modules:
-          - module_type: llama_index_llm
-            llm: openai
-            model: [gpt-4o-mini]
-      modules:
-        - module_type: fstring
-          prompt: ["주어진 passage만을 이용하여 question에 따라 답하시오 passage: {retrieved_contents} \n\n Question: {query} \n\n Answer:"]
-        - module_type: long_context_reorder
-          prompt: ["주어진 passage만을 이용하여 question에 따라 답하시오 passage: {retrieved_contents} \n\n Question: {query} \n\n Answer:"]
-    - node_type: generator
-      strategy:
-        metrics:
-          - metric_name: rouge
-          - embedding_model: openai
-            metric_name: sem_score
-          - metric_name: bert_score
-            lang: ko
-          - metric_name: g_eval  # LLM Judge Metric. Default Model: gpt-4-turbo
-        speed_threshold: 10
-      modules:
-        - module_type: llama_index_llm
-          llm: [openai]
-          model: [gpt-4o-mini]
-          temperature: [0.5, 1.0]
diff --git a/autorag-workspace/example/sample_config/rag/korean/non_gpu/half_korean.yaml b/autorag-workspace/example/sample_config/rag/korean/non_gpu/half_korean.yaml
deleted file mode 100644
index 18d098f..0000000
--- a/autorag-workspace/example/sample_config/rag/korean/non_gpu/half_korean.yaml
+++ /dev/null
@@ -1,111 +0,0 @@
-node_lines:
-- node_line_name: retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: retrieval
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision,
-                   retrieval_ndcg, retrieval_map, retrieval_mrr ]
-        speed_threshold: 10
-      top_k: 10
-      modules:
-        - module_type: bm25
-          bm25_tokenizer: [ ko_kiwi, ko_okt, ko_kkma ]
-        - module_type: vectordb
-          vectordb: default
-        - module_type: hybrid_rrf
-          weight_range: (4,80)
-        - module_type: hybrid_cc
-          normalize_method: [ mm, tmm, z, dbsf ]
-          weight_range: (0.0, 1.0)
-          test_weight_size: 101
-    - node_type: passage_augmenter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      top_k: 5
-      embedding_model: openai
-      modules:
-        - module_type: pass_passage_augmenter
-        - module_type: prev_next_augmenter
-          mode: next
-    - node_type: passage_filter
-      strategy:
-        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        speed_threshold: 5
-      modules:
-        - module_type: pass_passage_filter
-        - module_type: similarity_threshold_cutoff
-          threshold: 0.85
-        - module_type: similarity_percentile_cutoff
-          percentile: 0.6
-        - module_type: threshold_cutoff
-          threshold: 0.85
-        - module_type: percentile_cutoff
-          percentile: 0.6
-    - node_type: passage_compressor
-      strategy:
-        metrics: [retrieval_token_f1, retrieval_token_recall, retrieval_token_precision]
-        speed_threshold: 10
-      modules:
-        - module_type: pass_compressor
-        - module_type: tree_summarize
-          llm: openai
-          model: gpt-4o-mini
-          prompt: |
-            여러 문맥 정보는 다음과 같습니다.\n
-            ---------------------\n
-            {context_str}\n
-            ---------------------\n
-            사전 지식이 아닌 여러 정보가 주어졌습니다,
-            질문에 대답하세요.\n
-            질문: {query_str}\n
-            답변:
-        - module_type: refine
-          llm: openai
-          model: gpt-4o-mini
-          prompt: |
-            원래 질문은 다음과 같습니다: {query_str}
-            기존 답변은 다음과 같습니다: {existing_answer}
-            아래에서 기존 답변을 정제할 수 있는 기회가 있습니다.
-            (필요한 경우에만) 아래에 몇 가지 맥락을 추가하여 기존 답변을 정제할 수 있습니다.
-            ------------
-            {context_msg}
-            ------------
-            새로운 문맥이 주어지면 기존 답변을 수정하여 질문에 대한 답변을 정제합니다.
-            맥락이 쓸모 없다면, 기존 답변을 그대로 답변하세요.
-            정제된 답변:
-        - module_type: longllmlingua
-- node_line_name: post_retrieve_node_line  # Arbitrary node line name
-  nodes:
-    - node_type: prompt_maker
-      strategy:
-        metrics:
-          - metric_name: bleu
-          - metric_name: meteor
-          - metric_name: rouge
-          - metric_name: sem_score
-            embedding_model: openai
-        speed_threshold: 10
-        generator_modules:
-          - module_type: llama_index_llm
-            llm: openai
-            model: [gpt-4o-mini]
-      modules:
-        - module_type: fstring
-          prompt: ["주어진 passage만을 이용하여 question에 따라 답하시오 passage: {retrieved_contents} \n\n Question: {query} \n\n Answer:"]
-        - module_type: long_context_reorder
-          prompt: ["주어진 passage만을 이용하여 question에 따라 답하시오 passage: {retrieved_contents} \n\n Question: {query} \n\n Answer:"]
-    - node_type: generator
-      strategy:
-        metrics:
-          - metric_name: rouge
-          - embedding_model: openai
-            metric_name: sem_score
-          - metric_name: bert_score
-            lang: ko
-        speed_threshold: 10
-      modules:
-        - module_type: llama_index_llm
-          llm: [openai]
-          model: [gpt-4o-mini]
-          temperature: [0.5, 1.0]
diff --git a/autorag-workspace/example/sample_config/rag/korean/non_gpu/simple_korean.yaml b/autorag-workspace/example/sample_config/rag/korean/non_gpu/simple_korean.yaml
deleted file mode 100644
index 465baf2..0000000
--- a/autorag-workspace/example/sample_config/rag/korean/non_gpu/simple_korean.yaml
+++ /dev/null
@@ -1,30 +0,0 @@
-node_lines:
-  - node_line_name: retrieve_node_line  # Arbitrary node line name
-    nodes:
-      - node_type: retrieval
-        strategy:
-          metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
-        top_k: 3
-        modules:
-          - module_type: vectordb
-            vectordb: default
-  - node_line_name: post_retrieve_node_line  # Arbitrary node line name
-    nodes:
-      - node_type: prompt_maker
-        strategy:
-          metrics: [ bleu, meteor, rouge ]
-        modules:
-          - module_type: fstring
-            prompt: "주어진 passage만을 이용하여 question에 따라 답하시오 passage: {retrieved_contents} \n\n Question: {query} \n\n Answer:"
-      - node_type: generator
-        strategy:
-          metrics:
-            - metric_name: rouge
-            - embedding_model: openai
-              metric_name: sem_score
-            - metric_name: bert_score
-              lang: ko
-        modules:
-          - module_type: llama_index_llm
-            llm: openai
-            model: [ gpt-4o-mini ]
diff --git a/autorag-workspace/example/sample_dataset/README.md b/autorag-workspace/example/sample_dataset/README.md
deleted file mode 100644
index c249ad7..0000000
--- a/autorag-workspace/example/sample_dataset/README.md
+++ /dev/null
@@ -1,25 +0,0 @@
-# sample_dataset handling
-
-The sample_dataset folder does not includes a `qa.parquet`, `corpus.parquet` file that is significantly large and cannot be uploaded directly to Git due to size limitations.
-
-To prepare and use datasets available in the sample_dataset folder, specifically `triviaqa`, `hotpotqa`, `msmarco` and `eli5`, you can follow the outlined methods below.
-
-## Usage
-
- The example provided uses `triviaqa`, but the same approach applies to `msmarco`, `eli5` and `hotpotqa`.
-
-### 1. Run with a specified save path
-To execute the Python script from the terminal and save the dataset to a specified path, use the command:
-
-```bash
-python ./sample_dataset/triviaqa/load_triviaqa_dataset.py --save_path /path/to/save/dataset
-```
-This runs the `load_triviaqa_dataset.py` script located in the `./sample_dataset/triviaqa/` directory,
-using the `--save_path` argument to specify the dataset's save location.
-
-### 2. Run without specifying a save path
-If you run the script without the `--save_path` argument, the dataset will be saved to a default location, which is the directory containing the `load_triviaqa_dataset.py` file, essentially `./sample_dataset/triviaqa/`:
-```bash
-python ./sample_dataset/triviaqa/load_triviaqa_dataset.py
-```
-This behavior allows for a straightforward execution without needing to specify a path, making it convenient for quick tests or when working directly within the target directory.
diff --git a/autorag-workspace/example/sample_dataset/eli5/load_eli5_dataset.py b/autorag-workspace/example/sample_dataset/eli5/load_eli5_dataset.py
deleted file mode 100644
index 69a07d0..0000000
--- a/autorag-workspace/example/sample_dataset/eli5/load_eli5_dataset.py
+++ /dev/null
@@ -1,35 +0,0 @@
-import os
-import pathlib
-
-import click
-from datasets import load_dataset
-
-
-@click.command()
-@click.option(
-	"--save_path",
-	type=str,
-	default=pathlib.PurePath(__file__).parent,
-	help="Path to save sample eli5 dataset.",
-)
-def load_eli5_dataset(save_path):
-	# set file path
-	file_path = "MarkrAI/eli5_sample_autorag"
-
-	# load dataset
-	corpus_dataset = load_dataset(file_path, "corpus")["train"].to_pandas()
-	qa_train_dataset = load_dataset(file_path, "qa")["train"].to_pandas()
-	qa_test_dataset = load_dataset(file_path, "qa")["test"].to_pandas()
-
-	# save data
-	if os.path.exists(os.path.join(save_path, "corpus.parquet")) is True:
-		raise ValueError("corpus.parquet already exists")
-	if os.path.exists(os.path.join(save_path, "qa.parquet")) is True:
-		raise ValueError("qa.parquet already exists")
-	corpus_dataset.to_parquet(os.path.join(save_path, "corpus.parquet"))
-	qa_train_dataset.to_parquet(os.path.join(save_path, "qa_train.parquet"))
-	qa_test_dataset.to_parquet(os.path.join(save_path, "qa_test.parquet"))
-
-
-if __name__ == "__main__":
-	load_eli5_dataset()
diff --git a/autorag-workspace/example/sample_dataset/hotpotqa/load_hotpotqa_dataset.py b/autorag-workspace/example/sample_dataset/hotpotqa/load_hotpotqa_dataset.py
deleted file mode 100644
index 973d61c..0000000
--- a/autorag-workspace/example/sample_dataset/hotpotqa/load_hotpotqa_dataset.py
+++ /dev/null
@@ -1,35 +0,0 @@
-import os
-import pathlib
-
-import click
-from datasets import load_dataset
-
-
-@click.command()
-@click.option(
-	"--save_path",
-	type=str,
-	default=pathlib.PurePath(__file__).parent,
-	help="Path to save sample hotpotqa dataset.",
-)
-def load_hotpotqa_dataset(save_path):
-	# set file path
-	file_path = "gnekt/hotpotqa_small_sample_autorag"
-
-	# load dataset
-	corpus_dataset = load_dataset(file_path, "corpus")["train"].to_pandas()
-	qa_validation_dataset = load_dataset(file_path, "qa")["validation"].to_pandas()
-
-	# save corpus data
-	if os.path.exists(os.path.join(save_path, "corpus.parquet")) is True:
-		raise ValueError("corpus.parquet already exists")
-	if os.path.exists(os.path.join(save_path, "qa.parquet")) is True:
-		raise ValueError("qa.parquet already exists")
-	corpus_dataset.to_parquet(os.path.join(save_path, "corpus.parquet"), index=False)
-	qa_validation_dataset.to_parquet(
-		os.path.join(save_path, "qa_validation.parquet"), index=False
-	)
-
-
-if __name__ == "__main__":
-	load_hotpotqa_dataset()
diff --git a/autorag-workspace/example/sample_dataset/msmarco/load_msmarco_dataset.py b/autorag-workspace/example/sample_dataset/msmarco/load_msmarco_dataset.py
deleted file mode 100644
index 8a8abae..0000000
--- a/autorag-workspace/example/sample_dataset/msmarco/load_msmarco_dataset.py
+++ /dev/null
@@ -1,37 +0,0 @@
-import os
-import pathlib
-
-import click
-from datasets import load_dataset
-
-
-@click.command()
-@click.option(
-	"--save_path",
-	type=str,
-	default=pathlib.PurePath(__file__).parent,
-	help="Path to save sample msmarco dataset.",
-)
-def load_msmarco_dataset(save_path):
-	# set file path
-	file_path = "MarkrAI/msmarco_sample_autorag"
-
-	# load dataset
-	corpus_dataset = load_dataset(file_path, "corpus")["train"].to_pandas()
-	qa_train_dataset = load_dataset(file_path, "qa")["train"].to_pandas()
-	qa_test_dataset = load_dataset(file_path, "qa")["test"].to_pandas()
-
-	# save corpus data
-	if os.path.exists(os.path.join(save_path, "corpus.parquet")) is True:
-		raise ValueError("corpus.parquet already exists")
-	if os.path.exists(os.path.join(save_path, "qa.parquet")) is True:
-		raise ValueError("qa.parquet already exists")
-	corpus_dataset.to_parquet(os.path.join(save_path, "corpus.parquet"), index=False)
-	qa_train_dataset.to_parquet(
-		os.path.join(save_path, "qa_train.parquet"), index=False
-	)
-	qa_test_dataset.to_parquet(os.path.join(save_path, "qa_test.parquet"), index=False)
-
-
-if __name__ == "__main__":
-	load_msmarco_dataset()
diff --git a/autorag-workspace/example/sample_dataset/triviaqa/load_triviaqa_dataset.py b/autorag-workspace/example/sample_dataset/triviaqa/load_triviaqa_dataset.py
deleted file mode 100644
index 1067c17..0000000
--- a/autorag-workspace/example/sample_dataset/triviaqa/load_triviaqa_dataset.py
+++ /dev/null
@@ -1,37 +0,0 @@
-import os
-import pathlib
-
-import click
-from datasets import load_dataset
-
-
-@click.command()
-@click.option(
-	"--save_path",
-	type=str,
-	default=pathlib.PurePath(__file__).parent,
-	help="Path to save sample triviaqa dataset.",
-)
-def load_triviaqa_dataset(save_path):
-	# set file path
-	file_path = "MarkrAI/triviaqa_sample_autorag"
-
-	# load dataset
-	corpus_dataset = load_dataset(file_path, "corpus")["train"].to_pandas()
-	qa_train_dataset = load_dataset(file_path, "qa")["train"].to_pandas()
-	qa_test_dataset = load_dataset(file_path, "qa")["test"].to_pandas()
-
-	# save corpus data
-	if os.path.exists(os.path.join(save_path, "corpus.parquet")) is True:
-		raise ValueError("corpus.parquet already exists")
-	if os.path.exists(os.path.join(save_path, "qa.parquet")) is True:
-		raise ValueError("qa.parquet already exists")
-	corpus_dataset.to_parquet(os.path.join(save_path, "corpus.parquet"), index=False)
-	qa_train_dataset.to_parquet(
-		os.path.join(save_path, "qa_train.parquet"), index=False
-	)
-	qa_test_dataset.to_parquet(os.path.join(save_path, "qa_test.parquet"), index=False)
-
-
-if __name__ == "__main__":
-	load_triviaqa_dataset()
diff --git a/autorag-workspace/autorag/VERSION b/autorag/VERSION
similarity index 100%
rename from autorag-workspace/autorag/VERSION
rename to autorag/VERSION
diff --git a/autorag-workspace/autorag/__init__.py b/autorag/__init__.py
similarity index 100%
rename from autorag-workspace/autorag/__init__.py
rename to autorag/__init__.py
diff --git a/autorag-workspace/autorag/chunker.py b/autorag/chunker.py
similarity index 100%
rename from autorag-workspace/autorag/chunker.py
rename to autorag/chunker.py
diff --git a/autorag-workspace/autorag/data/__init__.py b/autorag/data/__init__.py
similarity index 100%
rename from autorag-workspace/autorag/data/__init__.py
rename to autorag/data/__init__.py
diff --git a/autorag-workspace/autorag/data/chunk/__init__.py b/autorag/data/chunk/__init__.py
similarity index 100%
rename from autorag-workspace/autorag/data/chunk/__init__.py
rename to autorag/data/chunk/__init__.py
diff --git a/autorag-workspace/autorag/data/chunk/base.py b/autorag/data/chunk/base.py
similarity index 100%
rename from autorag-workspace/autorag/data/chunk/base.py
rename to autorag/data/chunk/base.py
diff --git a/autorag-workspace/autorag/data/chunk/langchain_chunk.py b/autorag/data/chunk/langchain_chunk.py
similarity index 100%
rename from autorag-workspace/autorag/data/chunk/langchain_chunk.py
rename to autorag/data/chunk/langchain_chunk.py
diff --git a/autorag-workspace/autorag/data/chunk/llama_index_chunk.py b/autorag/data/chunk/llama_index_chunk.py
similarity index 100%
rename from autorag-workspace/autorag/data/chunk/llama_index_chunk.py
rename to autorag/data/chunk/llama_index_chunk.py
diff --git a/autorag-workspace/autorag/data/chunk/run.py b/autorag/data/chunk/run.py
similarity index 100%
rename from autorag-workspace/autorag/data/chunk/run.py
rename to autorag/data/chunk/run.py
diff --git a/autorag-workspace/autorag/data/legacy/__init__.py b/autorag/data/legacy/__init__.py
similarity index 100%
rename from autorag-workspace/autorag/data/legacy/__init__.py
rename to autorag/data/legacy/__init__.py
diff --git a/autorag-workspace/autorag/data/legacy/corpus/__init__.py b/autorag/data/legacy/corpus/__init__.py
similarity index 100%
rename from autorag-workspace/autorag/data/legacy/corpus/__init__.py
rename to autorag/data/legacy/corpus/__init__.py
diff --git a/autorag-workspace/autorag/data/legacy/corpus/langchain.py b/autorag/data/legacy/corpus/langchain.py
similarity index 100%
rename from autorag-workspace/autorag/data/legacy/corpus/langchain.py
rename to autorag/data/legacy/corpus/langchain.py
diff --git a/autorag-workspace/autorag/data/legacy/corpus/llama_index.py b/autorag/data/legacy/corpus/llama_index.py
similarity index 100%
rename from autorag-workspace/autorag/data/legacy/corpus/llama_index.py
rename to autorag/data/legacy/corpus/llama_index.py
diff --git a/autorag-workspace/autorag/data/legacy/qacreation/__init__.py b/autorag/data/legacy/qacreation/__init__.py
similarity index 100%
rename from autorag-workspace/autorag/data/legacy/qacreation/__init__.py
rename to autorag/data/legacy/qacreation/__init__.py
diff --git a/autorag-workspace/autorag/data/legacy/qacreation/base.py b/autorag/data/legacy/qacreation/base.py
similarity index 100%
rename from autorag-workspace/autorag/data/legacy/qacreation/base.py
rename to autorag/data/legacy/qacreation/base.py
diff --git a/autorag-workspace/autorag/data/legacy/qacreation/llama_index.py b/autorag/data/legacy/qacreation/llama_index.py
similarity index 100%
rename from autorag-workspace/autorag/data/legacy/qacreation/llama_index.py
rename to autorag/data/legacy/qacreation/llama_index.py
diff --git a/autorag-workspace/autorag/data/legacy/qacreation/llama_index_default_prompt.txt b/autorag/data/legacy/qacreation/llama_index_default_prompt.txt
similarity index 100%
rename from autorag-workspace/autorag/data/legacy/qacreation/llama_index_default_prompt.txt
rename to autorag/data/legacy/qacreation/llama_index_default_prompt.txt
diff --git a/autorag-workspace/autorag/data/legacy/qacreation/ragas.py b/autorag/data/legacy/qacreation/ragas.py
similarity index 100%
rename from autorag-workspace/autorag/data/legacy/qacreation/ragas.py
rename to autorag/data/legacy/qacreation/ragas.py
diff --git a/autorag-workspace/autorag/data/legacy/qacreation/simple.py b/autorag/data/legacy/qacreation/simple.py
similarity index 100%
rename from autorag-workspace/autorag/data/legacy/qacreation/simple.py
rename to autorag/data/legacy/qacreation/simple.py
diff --git a/autorag-workspace/autorag/data/parse/__init__.py b/autorag/data/parse/__init__.py
similarity index 100%
rename from autorag-workspace/autorag/data/parse/__init__.py
rename to autorag/data/parse/__init__.py
diff --git a/autorag-workspace/autorag/data/parse/base.py b/autorag/data/parse/base.py
similarity index 100%
rename from autorag-workspace/autorag/data/parse/base.py
rename to autorag/data/parse/base.py
diff --git a/autorag-workspace/autorag/data/parse/clova.py b/autorag/data/parse/clova.py
similarity index 100%
rename from autorag-workspace/autorag/data/parse/clova.py
rename to autorag/data/parse/clova.py
diff --git a/autorag-workspace/autorag/data/parse/langchain_parse.py b/autorag/data/parse/langchain_parse.py
similarity index 100%
rename from autorag-workspace/autorag/data/parse/langchain_parse.py
rename to autorag/data/parse/langchain_parse.py
diff --git a/autorag-workspace/autorag/data/parse/llamaparse.py b/autorag/data/parse/llamaparse.py
similarity index 100%
rename from autorag-workspace/autorag/data/parse/llamaparse.py
rename to autorag/data/parse/llamaparse.py
diff --git a/autorag-workspace/autorag/data/parse/run.py b/autorag/data/parse/run.py
similarity index 100%
rename from autorag-workspace/autorag/data/parse/run.py
rename to autorag/data/parse/run.py
diff --git a/autorag-workspace/autorag/data/parse/table_hybrid_parse.py b/autorag/data/parse/table_hybrid_parse.py
similarity index 100%
rename from autorag-workspace/autorag/data/parse/table_hybrid_parse.py
rename to autorag/data/parse/table_hybrid_parse.py
diff --git a/autorag-workspace/autorag/data/qa/__init__.py b/autorag/data/qa/__init__.py
similarity index 100%
rename from autorag-workspace/autorag/data/qa/__init__.py
rename to autorag/data/qa/__init__.py
diff --git a/autorag-workspace/autorag/data/qa/evolve/__init__.py b/autorag/data/qa/evolve/__init__.py
similarity index 100%
rename from autorag-workspace/autorag/data/qa/evolve/__init__.py
rename to autorag/data/qa/evolve/__init__.py
diff --git a/autorag-workspace/autorag/data/qa/evolve/llama_index_query_evolve.py b/autorag/data/qa/evolve/llama_index_query_evolve.py
similarity index 100%
rename from autorag-workspace/autorag/data/qa/evolve/llama_index_query_evolve.py
rename to autorag/data/qa/evolve/llama_index_query_evolve.py
diff --git a/autorag-workspace/autorag/data/qa/evolve/openai_query_evolve.py b/autorag/data/qa/evolve/openai_query_evolve.py
similarity index 100%
rename from autorag-workspace/autorag/data/qa/evolve/openai_query_evolve.py
rename to autorag/data/qa/evolve/openai_query_evolve.py
diff --git a/autorag-workspace/autorag/data/qa/evolve/prompt.py b/autorag/data/qa/evolve/prompt.py
similarity index 100%
rename from autorag-workspace/autorag/data/qa/evolve/prompt.py
rename to autorag/data/qa/evolve/prompt.py
diff --git a/autorag-workspace/autorag/data/qa/extract_evidence.py b/autorag/data/qa/extract_evidence.py
similarity index 100%
rename from autorag-workspace/autorag/data/qa/extract_evidence.py
rename to autorag/data/qa/extract_evidence.py
diff --git a/autorag-workspace/autorag/data/qa/filter/__init__.py b/autorag/data/qa/filter/__init__.py
similarity index 100%
rename from autorag-workspace/autorag/data/qa/filter/__init__.py
rename to autorag/data/qa/filter/__init__.py
diff --git a/autorag-workspace/autorag/data/qa/filter/dontknow.py b/autorag/data/qa/filter/dontknow.py
similarity index 100%
rename from autorag-workspace/autorag/data/qa/filter/dontknow.py
rename to autorag/data/qa/filter/dontknow.py
diff --git a/autorag-workspace/autorag/data/qa/filter/passage_dependency.py b/autorag/data/qa/filter/passage_dependency.py
similarity index 100%
rename from autorag-workspace/autorag/data/qa/filter/passage_dependency.py
rename to autorag/data/qa/filter/passage_dependency.py
diff --git a/autorag-workspace/autorag/data/qa/filter/prompt.py b/autorag/data/qa/filter/prompt.py
similarity index 100%
rename from autorag-workspace/autorag/data/qa/filter/prompt.py
rename to autorag/data/qa/filter/prompt.py
diff --git a/autorag-workspace/autorag/data/qa/generation_gt/__init__.py b/autorag/data/qa/generation_gt/__init__.py
similarity index 100%
rename from autorag-workspace/autorag/data/qa/generation_gt/__init__.py
rename to autorag/data/qa/generation_gt/__init__.py
diff --git a/autorag-workspace/autorag/data/qa/generation_gt/base.py b/autorag/data/qa/generation_gt/base.py
similarity index 100%
rename from autorag-workspace/autorag/data/qa/generation_gt/base.py
rename to autorag/data/qa/generation_gt/base.py
diff --git a/autorag-workspace/autorag/data/qa/generation_gt/llama_index_gen_gt.py b/autorag/data/qa/generation_gt/llama_index_gen_gt.py
similarity index 100%
rename from autorag-workspace/autorag/data/qa/generation_gt/llama_index_gen_gt.py
rename to autorag/data/qa/generation_gt/llama_index_gen_gt.py
diff --git a/autorag-workspace/autorag/data/qa/generation_gt/openai_gen_gt.py b/autorag/data/qa/generation_gt/openai_gen_gt.py
similarity index 100%
rename from autorag-workspace/autorag/data/qa/generation_gt/openai_gen_gt.py
rename to autorag/data/qa/generation_gt/openai_gen_gt.py
diff --git a/autorag-workspace/autorag/data/qa/generation_gt/prompt.py b/autorag/data/qa/generation_gt/prompt.py
similarity index 100%
rename from autorag-workspace/autorag/data/qa/generation_gt/prompt.py
rename to autorag/data/qa/generation_gt/prompt.py
diff --git a/autorag-workspace/autorag/data/qa/query/__init__.py b/autorag/data/qa/query/__init__.py
similarity index 100%
rename from autorag-workspace/autorag/data/qa/query/__init__.py
rename to autorag/data/qa/query/__init__.py
diff --git a/autorag-workspace/autorag/data/qa/query/llama_gen_query.py b/autorag/data/qa/query/llama_gen_query.py
similarity index 100%
rename from autorag-workspace/autorag/data/qa/query/llama_gen_query.py
rename to autorag/data/qa/query/llama_gen_query.py
diff --git a/autorag-workspace/autorag/data/qa/query/openai_gen_query.py b/autorag/data/qa/query/openai_gen_query.py
similarity index 100%
rename from autorag-workspace/autorag/data/qa/query/openai_gen_query.py
rename to autorag/data/qa/query/openai_gen_query.py
diff --git a/autorag-workspace/autorag/data/qa/query/prompt.py b/autorag/data/qa/query/prompt.py
similarity index 100%
rename from autorag-workspace/autorag/data/qa/query/prompt.py
rename to autorag/data/qa/query/prompt.py
diff --git a/autorag-workspace/autorag/data/qa/sample.py b/autorag/data/qa/sample.py
similarity index 100%
rename from autorag-workspace/autorag/data/qa/sample.py
rename to autorag/data/qa/sample.py
diff --git a/autorag-workspace/autorag/data/qa/schema.py b/autorag/data/qa/schema.py
similarity index 100%
rename from autorag-workspace/autorag/data/qa/schema.py
rename to autorag/data/qa/schema.py
diff --git a/autorag-workspace/autorag/data/utils/__init__.py b/autorag/data/utils/__init__.py
similarity index 100%
rename from autorag-workspace/autorag/data/utils/__init__.py
rename to autorag/data/utils/__init__.py
diff --git a/autorag-workspace/autorag/data/utils/util.py b/autorag/data/utils/util.py
similarity index 100%
rename from autorag-workspace/autorag/data/utils/util.py
rename to autorag/data/utils/util.py
diff --git a/autorag-workspace/autorag/deploy/__init__.py b/autorag/deploy/__init__.py
similarity index 100%
rename from autorag-workspace/autorag/deploy/__init__.py
rename to autorag/deploy/__init__.py
diff --git a/autorag-workspace/autorag/deploy/api.py b/autorag/deploy/api.py
similarity index 100%
rename from autorag-workspace/autorag/deploy/api.py
rename to autorag/deploy/api.py
diff --git a/autorag-workspace/autorag/deploy/base.py b/autorag/deploy/base.py
similarity index 100%
rename from autorag-workspace/autorag/deploy/base.py
rename to autorag/deploy/base.py
diff --git a/autorag-workspace/autorag/deploy/gradio.py b/autorag/deploy/gradio.py
similarity index 100%
rename from autorag-workspace/autorag/deploy/gradio.py
rename to autorag/deploy/gradio.py
diff --git a/autorag-workspace/autorag/deploy/swagger.yml b/autorag/deploy/swagger.yml
similarity index 100%
rename from autorag-workspace/autorag/deploy/swagger.yml
rename to autorag/deploy/swagger.yml
diff --git a/autorag-workspace/autorag/embedding/__init__.py b/autorag/embedding/__init__.py
similarity index 100%
rename from autorag-workspace/autorag/embedding/__init__.py
rename to autorag/embedding/__init__.py
diff --git a/autorag-workspace/autorag/embedding/base.py b/autorag/embedding/base.py
similarity index 100%
rename from autorag-workspace/autorag/embedding/base.py
rename to autorag/embedding/base.py
diff --git a/autorag-workspace/autorag/evaluation/__init__.py b/autorag/evaluation/__init__.py
similarity index 100%
rename from autorag-workspace/autorag/evaluation/__init__.py
rename to autorag/evaluation/__init__.py
diff --git a/autorag-workspace/autorag/evaluation/generation.py b/autorag/evaluation/generation.py
similarity index 100%
rename from autorag-workspace/autorag/evaluation/generation.py
rename to autorag/evaluation/generation.py
diff --git a/autorag-workspace/autorag/evaluation/metric/__init__.py b/autorag/evaluation/metric/__init__.py
similarity index 100%
rename from autorag-workspace/autorag/evaluation/metric/__init__.py
rename to autorag/evaluation/metric/__init__.py
diff --git a/autorag-workspace/autorag/evaluation/metric/deepeval_prompt.py b/autorag/evaluation/metric/deepeval_prompt.py
similarity index 100%
rename from autorag-workspace/autorag/evaluation/metric/deepeval_prompt.py
rename to autorag/evaluation/metric/deepeval_prompt.py
diff --git a/autorag-workspace/autorag/evaluation/metric/g_eval_prompts/coh_detailed.txt b/autorag/evaluation/metric/g_eval_prompts/coh_detailed.txt
similarity index 100%
rename from autorag-workspace/autorag/evaluation/metric/g_eval_prompts/coh_detailed.txt
rename to autorag/evaluation/metric/g_eval_prompts/coh_detailed.txt
diff --git a/autorag-workspace/autorag/evaluation/metric/g_eval_prompts/con_detailed.txt b/autorag/evaluation/metric/g_eval_prompts/con_detailed.txt
similarity index 100%
rename from autorag-workspace/autorag/evaluation/metric/g_eval_prompts/con_detailed.txt
rename to autorag/evaluation/metric/g_eval_prompts/con_detailed.txt
diff --git a/autorag-workspace/autorag/evaluation/metric/g_eval_prompts/flu_detailed.txt b/autorag/evaluation/metric/g_eval_prompts/flu_detailed.txt
similarity index 100%
rename from autorag-workspace/autorag/evaluation/metric/g_eval_prompts/flu_detailed.txt
rename to autorag/evaluation/metric/g_eval_prompts/flu_detailed.txt
diff --git a/autorag-workspace/autorag/evaluation/metric/g_eval_prompts/rel_detailed.txt b/autorag/evaluation/metric/g_eval_prompts/rel_detailed.txt
similarity index 100%
rename from autorag-workspace/autorag/evaluation/metric/g_eval_prompts/rel_detailed.txt
rename to autorag/evaluation/metric/g_eval_prompts/rel_detailed.txt
diff --git a/autorag-workspace/autorag/evaluation/metric/generation.py b/autorag/evaluation/metric/generation.py
similarity index 100%
rename from autorag-workspace/autorag/evaluation/metric/generation.py
rename to autorag/evaluation/metric/generation.py
diff --git a/autorag-workspace/autorag/evaluation/metric/retrieval.py b/autorag/evaluation/metric/retrieval.py
similarity index 100%
rename from autorag-workspace/autorag/evaluation/metric/retrieval.py
rename to autorag/evaluation/metric/retrieval.py
diff --git a/autorag-workspace/autorag/evaluation/metric/retrieval_contents.py b/autorag/evaluation/metric/retrieval_contents.py
similarity index 100%
rename from autorag-workspace/autorag/evaluation/metric/retrieval_contents.py
rename to autorag/evaluation/metric/retrieval_contents.py
diff --git a/autorag-workspace/autorag/evaluation/metric/util.py b/autorag/evaluation/metric/util.py
similarity index 100%
rename from autorag-workspace/autorag/evaluation/metric/util.py
rename to autorag/evaluation/metric/util.py
diff --git a/autorag-workspace/autorag/evaluation/retrieval.py b/autorag/evaluation/retrieval.py
similarity index 100%
rename from autorag-workspace/autorag/evaluation/retrieval.py
rename to autorag/evaluation/retrieval.py
diff --git a/autorag-workspace/autorag/evaluation/retrieval_contents.py b/autorag/evaluation/retrieval_contents.py
similarity index 100%
rename from autorag-workspace/autorag/evaluation/retrieval_contents.py
rename to autorag/evaluation/retrieval_contents.py
diff --git a/autorag-workspace/autorag/evaluation/util.py b/autorag/evaluation/util.py
similarity index 100%
rename from autorag-workspace/autorag/evaluation/util.py
rename to autorag/evaluation/util.py
diff --git a/autorag-workspace/autorag/evaluator.py b/autorag/evaluator.py
similarity index 100%
rename from autorag-workspace/autorag/evaluator.py
rename to autorag/evaluator.py
diff --git a/autorag-workspace/autorag/generator_models.py b/autorag/generator_models.py
similarity index 100%
rename from autorag-workspace/autorag/generator_models.py
rename to autorag/generator_models.py
diff --git a/autorag-workspace/autorag/node_line.py b/autorag/node_line.py
similarity index 100%
rename from autorag-workspace/autorag/node_line.py
rename to autorag/node_line.py
diff --git a/autorag-workspace/autorag/nodes/__init__.py b/autorag/nodes/__init__.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/__init__.py
rename to autorag/nodes/__init__.py
diff --git a/autorag-workspace/autorag/nodes/generator/__init__.py b/autorag/nodes/generator/__init__.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/generator/__init__.py
rename to autorag/nodes/generator/__init__.py
diff --git a/autorag-workspace/autorag/nodes/generator/base.py b/autorag/nodes/generator/base.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/generator/base.py
rename to autorag/nodes/generator/base.py
diff --git a/autorag-workspace/autorag/nodes/generator/llama_index_llm.py b/autorag/nodes/generator/llama_index_llm.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/generator/llama_index_llm.py
rename to autorag/nodes/generator/llama_index_llm.py
diff --git a/autorag-workspace/autorag/nodes/generator/openai_llm.py b/autorag/nodes/generator/openai_llm.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/generator/openai_llm.py
rename to autorag/nodes/generator/openai_llm.py
diff --git a/autorag-workspace/autorag/nodes/generator/run.py b/autorag/nodes/generator/run.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/generator/run.py
rename to autorag/nodes/generator/run.py
diff --git a/autorag-workspace/autorag/nodes/generator/vllm.py b/autorag/nodes/generator/vllm.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/generator/vllm.py
rename to autorag/nodes/generator/vllm.py
diff --git a/autorag-workspace/autorag/nodes/generator/vllm_api.py b/autorag/nodes/generator/vllm_api.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/generator/vllm_api.py
rename to autorag/nodes/generator/vllm_api.py
diff --git a/autorag-workspace/autorag/nodes/passageaugmenter/__init__.py b/autorag/nodes/passageaugmenter/__init__.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passageaugmenter/__init__.py
rename to autorag/nodes/passageaugmenter/__init__.py
diff --git a/autorag-workspace/autorag/nodes/passageaugmenter/base.py b/autorag/nodes/passageaugmenter/base.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passageaugmenter/base.py
rename to autorag/nodes/passageaugmenter/base.py
diff --git a/autorag-workspace/autorag/nodes/passageaugmenter/pass_passage_augmenter.py b/autorag/nodes/passageaugmenter/pass_passage_augmenter.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passageaugmenter/pass_passage_augmenter.py
rename to autorag/nodes/passageaugmenter/pass_passage_augmenter.py
diff --git a/autorag-workspace/autorag/nodes/passageaugmenter/prev_next_augmenter.py b/autorag/nodes/passageaugmenter/prev_next_augmenter.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passageaugmenter/prev_next_augmenter.py
rename to autorag/nodes/passageaugmenter/prev_next_augmenter.py
diff --git a/autorag-workspace/autorag/nodes/passageaugmenter/run.py b/autorag/nodes/passageaugmenter/run.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passageaugmenter/run.py
rename to autorag/nodes/passageaugmenter/run.py
diff --git a/autorag-workspace/autorag/nodes/passagecompressor/__init__.py b/autorag/nodes/passagecompressor/__init__.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagecompressor/__init__.py
rename to autorag/nodes/passagecompressor/__init__.py
diff --git a/autorag-workspace/autorag/nodes/passagecompressor/base.py b/autorag/nodes/passagecompressor/base.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagecompressor/base.py
rename to autorag/nodes/passagecompressor/base.py
diff --git a/autorag-workspace/autorag/nodes/passagecompressor/longllmlingua.py b/autorag/nodes/passagecompressor/longllmlingua.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagecompressor/longllmlingua.py
rename to autorag/nodes/passagecompressor/longllmlingua.py
diff --git a/autorag-workspace/autorag/nodes/passagecompressor/pass_compressor.py b/autorag/nodes/passagecompressor/pass_compressor.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagecompressor/pass_compressor.py
rename to autorag/nodes/passagecompressor/pass_compressor.py
diff --git a/autorag-workspace/autorag/nodes/passagecompressor/refine.py b/autorag/nodes/passagecompressor/refine.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagecompressor/refine.py
rename to autorag/nodes/passagecompressor/refine.py
diff --git a/autorag-workspace/autorag/nodes/passagecompressor/run.py b/autorag/nodes/passagecompressor/run.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagecompressor/run.py
rename to autorag/nodes/passagecompressor/run.py
diff --git a/autorag-workspace/autorag/nodes/passagecompressor/tree_summarize.py b/autorag/nodes/passagecompressor/tree_summarize.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagecompressor/tree_summarize.py
rename to autorag/nodes/passagecompressor/tree_summarize.py
diff --git a/autorag-workspace/autorag/nodes/passagefilter/__init__.py b/autorag/nodes/passagefilter/__init__.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagefilter/__init__.py
rename to autorag/nodes/passagefilter/__init__.py
diff --git a/autorag-workspace/autorag/nodes/passagefilter/base.py b/autorag/nodes/passagefilter/base.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagefilter/base.py
rename to autorag/nodes/passagefilter/base.py
diff --git a/autorag-workspace/autorag/nodes/passagefilter/pass_passage_filter.py b/autorag/nodes/passagefilter/pass_passage_filter.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagefilter/pass_passage_filter.py
rename to autorag/nodes/passagefilter/pass_passage_filter.py
diff --git a/autorag-workspace/autorag/nodes/passagefilter/percentile_cutoff.py b/autorag/nodes/passagefilter/percentile_cutoff.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagefilter/percentile_cutoff.py
rename to autorag/nodes/passagefilter/percentile_cutoff.py
diff --git a/autorag-workspace/autorag/nodes/passagefilter/recency.py b/autorag/nodes/passagefilter/recency.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagefilter/recency.py
rename to autorag/nodes/passagefilter/recency.py
diff --git a/autorag-workspace/autorag/nodes/passagefilter/run.py b/autorag/nodes/passagefilter/run.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagefilter/run.py
rename to autorag/nodes/passagefilter/run.py
diff --git a/autorag-workspace/autorag/nodes/passagefilter/similarity_percentile_cutoff.py b/autorag/nodes/passagefilter/similarity_percentile_cutoff.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagefilter/similarity_percentile_cutoff.py
rename to autorag/nodes/passagefilter/similarity_percentile_cutoff.py
diff --git a/autorag-workspace/autorag/nodes/passagefilter/similarity_threshold_cutoff.py b/autorag/nodes/passagefilter/similarity_threshold_cutoff.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagefilter/similarity_threshold_cutoff.py
rename to autorag/nodes/passagefilter/similarity_threshold_cutoff.py
diff --git a/autorag-workspace/autorag/nodes/passagefilter/threshold_cutoff.py b/autorag/nodes/passagefilter/threshold_cutoff.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagefilter/threshold_cutoff.py
rename to autorag/nodes/passagefilter/threshold_cutoff.py
diff --git a/autorag-workspace/autorag/nodes/passagereranker/__init__.py b/autorag/nodes/passagereranker/__init__.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagereranker/__init__.py
rename to autorag/nodes/passagereranker/__init__.py
diff --git a/autorag-workspace/autorag/nodes/passagereranker/base.py b/autorag/nodes/passagereranker/base.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagereranker/base.py
rename to autorag/nodes/passagereranker/base.py
diff --git a/autorag-workspace/autorag/nodes/passagereranker/cohere.py b/autorag/nodes/passagereranker/cohere.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagereranker/cohere.py
rename to autorag/nodes/passagereranker/cohere.py
diff --git a/autorag-workspace/autorag/nodes/passagereranker/colbert.py b/autorag/nodes/passagereranker/colbert.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagereranker/colbert.py
rename to autorag/nodes/passagereranker/colbert.py
diff --git a/autorag-workspace/autorag/nodes/passagereranker/dragonkue2.py b/autorag/nodes/passagereranker/dragonkue2.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagereranker/dragonkue2.py
rename to autorag/nodes/passagereranker/dragonkue2.py
diff --git a/autorag-workspace/autorag/nodes/passagereranker/flag_embedding.py b/autorag/nodes/passagereranker/flag_embedding.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagereranker/flag_embedding.py
rename to autorag/nodes/passagereranker/flag_embedding.py
diff --git a/autorag-workspace/autorag/nodes/passagereranker/flag_embedding_llm.py b/autorag/nodes/passagereranker/flag_embedding_llm.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagereranker/flag_embedding_llm.py
rename to autorag/nodes/passagereranker/flag_embedding_llm.py
diff --git a/autorag-workspace/autorag/nodes/passagereranker/flashrank.py b/autorag/nodes/passagereranker/flashrank.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagereranker/flashrank.py
rename to autorag/nodes/passagereranker/flashrank.py
diff --git a/autorag-workspace/autorag/nodes/passagereranker/jina.py b/autorag/nodes/passagereranker/jina.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagereranker/jina.py
rename to autorag/nodes/passagereranker/jina.py
diff --git a/autorag-workspace/autorag/nodes/passagereranker/koreranker.py b/autorag/nodes/passagereranker/koreranker.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagereranker/koreranker.py
rename to autorag/nodes/passagereranker/koreranker.py
diff --git a/autorag-workspace/autorag/nodes/passagereranker/mixedbreadai.py b/autorag/nodes/passagereranker/mixedbreadai.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagereranker/mixedbreadai.py
rename to autorag/nodes/passagereranker/mixedbreadai.py
diff --git a/autorag-workspace/autorag/nodes/passagereranker/monot5.py b/autorag/nodes/passagereranker/monot5.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagereranker/monot5.py
rename to autorag/nodes/passagereranker/monot5.py
diff --git a/autorag-workspace/autorag/nodes/passagereranker/openvino.py b/autorag/nodes/passagereranker/openvino.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagereranker/openvino.py
rename to autorag/nodes/passagereranker/openvino.py
diff --git a/autorag-workspace/autorag/nodes/passagereranker/pass_reranker.py b/autorag/nodes/passagereranker/pass_reranker.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagereranker/pass_reranker.py
rename to autorag/nodes/passagereranker/pass_reranker.py
diff --git a/autorag-workspace/autorag/nodes/passagereranker/rankgpt.py b/autorag/nodes/passagereranker/rankgpt.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagereranker/rankgpt.py
rename to autorag/nodes/passagereranker/rankgpt.py
diff --git a/autorag-workspace/autorag/nodes/passagereranker/run.py b/autorag/nodes/passagereranker/run.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagereranker/run.py
rename to autorag/nodes/passagereranker/run.py
diff --git a/autorag-workspace/autorag/nodes/passagereranker/sentence_transformer.py b/autorag/nodes/passagereranker/sentence_transformer.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagereranker/sentence_transformer.py
rename to autorag/nodes/passagereranker/sentence_transformer.py
diff --git a/autorag-workspace/autorag/nodes/passagereranker/tart/__init__.py b/autorag/nodes/passagereranker/tart/__init__.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagereranker/tart/__init__.py
rename to autorag/nodes/passagereranker/tart/__init__.py
diff --git a/autorag-workspace/autorag/nodes/passagereranker/tart/modeling_enc_t5.py b/autorag/nodes/passagereranker/tart/modeling_enc_t5.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagereranker/tart/modeling_enc_t5.py
rename to autorag/nodes/passagereranker/tart/modeling_enc_t5.py
diff --git a/autorag-workspace/autorag/nodes/passagereranker/tart/tart.py b/autorag/nodes/passagereranker/tart/tart.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagereranker/tart/tart.py
rename to autorag/nodes/passagereranker/tart/tart.py
diff --git a/autorag-workspace/autorag/nodes/passagereranker/tart/tokenization_enc_t5.py b/autorag/nodes/passagereranker/tart/tokenization_enc_t5.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagereranker/tart/tokenization_enc_t5.py
rename to autorag/nodes/passagereranker/tart/tokenization_enc_t5.py
diff --git a/autorag-workspace/autorag/nodes/passagereranker/time_reranker.py b/autorag/nodes/passagereranker/time_reranker.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagereranker/time_reranker.py
rename to autorag/nodes/passagereranker/time_reranker.py
diff --git a/autorag-workspace/autorag/nodes/passagereranker/upr.py b/autorag/nodes/passagereranker/upr.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagereranker/upr.py
rename to autorag/nodes/passagereranker/upr.py
diff --git a/autorag-workspace/autorag/nodes/passagereranker/voyageai.py b/autorag/nodes/passagereranker/voyageai.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/passagereranker/voyageai.py
rename to autorag/nodes/passagereranker/voyageai.py
diff --git a/autorag-workspace/autorag/nodes/promptmaker/__init__.py b/autorag/nodes/promptmaker/__init__.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/promptmaker/__init__.py
rename to autorag/nodes/promptmaker/__init__.py
diff --git a/autorag-workspace/autorag/nodes/promptmaker/base.py b/autorag/nodes/promptmaker/base.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/promptmaker/base.py
rename to autorag/nodes/promptmaker/base.py
diff --git a/autorag-workspace/autorag/nodes/promptmaker/fstring.py b/autorag/nodes/promptmaker/fstring.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/promptmaker/fstring.py
rename to autorag/nodes/promptmaker/fstring.py
diff --git a/autorag-workspace/autorag/nodes/promptmaker/long_context_reorder.py b/autorag/nodes/promptmaker/long_context_reorder.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/promptmaker/long_context_reorder.py
rename to autorag/nodes/promptmaker/long_context_reorder.py
diff --git a/autorag-workspace/autorag/nodes/promptmaker/run.py b/autorag/nodes/promptmaker/run.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/promptmaker/run.py
rename to autorag/nodes/promptmaker/run.py
diff --git a/autorag-workspace/autorag/nodes/promptmaker/window_replacement.py b/autorag/nodes/promptmaker/window_replacement.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/promptmaker/window_replacement.py
rename to autorag/nodes/promptmaker/window_replacement.py
diff --git a/autorag-workspace/autorag/nodes/queryexpansion/__init__.py b/autorag/nodes/queryexpansion/__init__.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/queryexpansion/__init__.py
rename to autorag/nodes/queryexpansion/__init__.py
diff --git a/autorag-workspace/autorag/nodes/queryexpansion/base.py b/autorag/nodes/queryexpansion/base.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/queryexpansion/base.py
rename to autorag/nodes/queryexpansion/base.py
diff --git a/autorag-workspace/autorag/nodes/queryexpansion/hyde.py b/autorag/nodes/queryexpansion/hyde.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/queryexpansion/hyde.py
rename to autorag/nodes/queryexpansion/hyde.py
diff --git a/autorag-workspace/autorag/nodes/queryexpansion/multi_query_expansion.py b/autorag/nodes/queryexpansion/multi_query_expansion.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/queryexpansion/multi_query_expansion.py
rename to autorag/nodes/queryexpansion/multi_query_expansion.py
diff --git a/autorag-workspace/autorag/nodes/queryexpansion/pass_query_expansion.py b/autorag/nodes/queryexpansion/pass_query_expansion.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/queryexpansion/pass_query_expansion.py
rename to autorag/nodes/queryexpansion/pass_query_expansion.py
diff --git a/autorag-workspace/autorag/nodes/queryexpansion/query_decompose.py b/autorag/nodes/queryexpansion/query_decompose.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/queryexpansion/query_decompose.py
rename to autorag/nodes/queryexpansion/query_decompose.py
diff --git a/autorag-workspace/autorag/nodes/queryexpansion/run.py b/autorag/nodes/queryexpansion/run.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/queryexpansion/run.py
rename to autorag/nodes/queryexpansion/run.py
diff --git a/autorag-workspace/autorag/nodes/retrieval/__init__.py b/autorag/nodes/retrieval/__init__.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/retrieval/__init__.py
rename to autorag/nodes/retrieval/__init__.py
diff --git a/autorag-workspace/autorag/nodes/retrieval/base.py b/autorag/nodes/retrieval/base.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/retrieval/base.py
rename to autorag/nodes/retrieval/base.py
diff --git a/autorag-workspace/autorag/nodes/retrieval/bm25.py b/autorag/nodes/retrieval/bm25.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/retrieval/bm25.py
rename to autorag/nodes/retrieval/bm25.py
diff --git a/autorag-workspace/autorag/nodes/retrieval/hybrid_cc.py b/autorag/nodes/retrieval/hybrid_cc.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/retrieval/hybrid_cc.py
rename to autorag/nodes/retrieval/hybrid_cc.py
diff --git a/autorag-workspace/autorag/nodes/retrieval/hybrid_rrf.py b/autorag/nodes/retrieval/hybrid_rrf.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/retrieval/hybrid_rrf.py
rename to autorag/nodes/retrieval/hybrid_rrf.py
diff --git a/autorag-workspace/autorag/nodes/retrieval/run.py b/autorag/nodes/retrieval/run.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/retrieval/run.py
rename to autorag/nodes/retrieval/run.py
diff --git a/autorag-workspace/autorag/nodes/retrieval/vectordb.py b/autorag/nodes/retrieval/vectordb.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/retrieval/vectordb.py
rename to autorag/nodes/retrieval/vectordb.py
diff --git a/autorag-workspace/autorag/nodes/util.py b/autorag/nodes/util.py
similarity index 100%
rename from autorag-workspace/autorag/nodes/util.py
rename to autorag/nodes/util.py
diff --git a/autorag-workspace/autorag/parser.py b/autorag/parser.py
similarity index 100%
rename from autorag-workspace/autorag/parser.py
rename to autorag/parser.py
diff --git a/autorag-workspace/autorag/schema/__init__.py b/autorag/schema/__init__.py
similarity index 100%
rename from autorag-workspace/autorag/schema/__init__.py
rename to autorag/schema/__init__.py
diff --git a/autorag-workspace/autorag/schema/base.py b/autorag/schema/base.py
similarity index 100%
rename from autorag-workspace/autorag/schema/base.py
rename to autorag/schema/base.py
diff --git a/autorag-workspace/autorag/schema/metricinput.py b/autorag/schema/metricinput.py
similarity index 100%
rename from autorag-workspace/autorag/schema/metricinput.py
rename to autorag/schema/metricinput.py
diff --git a/autorag-workspace/autorag/schema/module.py b/autorag/schema/module.py
similarity index 100%
rename from autorag-workspace/autorag/schema/module.py
rename to autorag/schema/module.py
diff --git a/autorag-workspace/autorag/schema/node.py b/autorag/schema/node.py
similarity index 100%
rename from autorag-workspace/autorag/schema/node.py
rename to autorag/schema/node.py
diff --git a/autorag-workspace/autorag/strategy.py b/autorag/strategy.py
similarity index 100%
rename from autorag-workspace/autorag/strategy.py
rename to autorag/strategy.py
diff --git a/autorag-workspace/autorag/support.py b/autorag/support.py
similarity index 100%
rename from autorag-workspace/autorag/support.py
rename to autorag/support.py
diff --git a/autorag-workspace/autorag/utils/__init__.py b/autorag/utils/__init__.py
similarity index 100%
rename from autorag-workspace/autorag/utils/__init__.py
rename to autorag/utils/__init__.py
diff --git a/autorag-workspace/autorag/utils/preprocess.py b/autorag/utils/preprocess.py
similarity index 100%
rename from autorag-workspace/autorag/utils/preprocess.py
rename to autorag/utils/preprocess.py
diff --git a/autorag-workspace/autorag/utils/util.py b/autorag/utils/util.py
similarity index 100%
rename from autorag-workspace/autorag/utils/util.py
rename to autorag/utils/util.py
diff --git a/autorag-workspace/autorag/validator.py b/autorag/validator.py
similarity index 100%
rename from autorag-workspace/autorag/validator.py
rename to autorag/validator.py
diff --git a/autorag-workspace/autorag/vectordb/__init__.py b/autorag/vectordb/__init__.py
similarity index 100%
rename from autorag-workspace/autorag/vectordb/__init__.py
rename to autorag/vectordb/__init__.py
diff --git a/autorag-workspace/autorag/vectordb/base.py b/autorag/vectordb/base.py
similarity index 100%
rename from autorag-workspace/autorag/vectordb/base.py
rename to autorag/vectordb/base.py
diff --git a/autorag-workspace/autorag/vectordb/chroma.py b/autorag/vectordb/chroma.py
similarity index 100%
rename from autorag-workspace/autorag/vectordb/chroma.py
rename to autorag/vectordb/chroma.py
diff --git a/autorag-workspace/autorag/vectordb/couchbase.py b/autorag/vectordb/couchbase.py
similarity index 100%
rename from autorag-workspace/autorag/vectordb/couchbase.py
rename to autorag/vectordb/couchbase.py
diff --git a/autorag-workspace/autorag/vectordb/milvus.py b/autorag/vectordb/milvus.py
similarity index 100%
rename from autorag-workspace/autorag/vectordb/milvus.py
rename to autorag/vectordb/milvus.py
diff --git a/autorag-workspace/autorag/vectordb/pinecone.py b/autorag/vectordb/pinecone.py
similarity index 100%
rename from autorag-workspace/autorag/vectordb/pinecone.py
rename to autorag/vectordb/pinecone.py
diff --git a/autorag-workspace/autorag/vectordb/qdrant.py b/autorag/vectordb/qdrant.py
similarity index 100%
rename from autorag-workspace/autorag/vectordb/qdrant.py
rename to autorag/vectordb/qdrant.py
diff --git a/autorag-workspace/autorag/vectordb/weaviate.py b/autorag/vectordb/weaviate.py
similarity index 100%
rename from autorag-workspace/autorag/vectordb/weaviate.py
rename to autorag/vectordb/weaviate.py
diff --git a/autorag-workspace/autorag/web.py b/autorag/web.py
similarity index 100%
rename from autorag-workspace/autorag/web.py
rename to autorag/web.py
diff --git a/docker-compose.yml b/docker-compose.yml
index dd74931..7b2488e 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -23,6 +23,7 @@ services:
       - autorag-ollama # Ollama가 먼저 실행되도록 설정
     networks:
       - autorag_network
+    command: ["bash"] # 기본 실행 명령
 
   autorag-ollama:
     image: ollama/ollama
diff --git a/entrypoint.sh b/entrypoint.sh
new file mode 100644
index 0000000..f938248
--- /dev/null
+++ b/entrypoint.sh
@@ -0,0 +1,24 @@
+#!/bin/bash
+
+set -e  # 오류 발생 시 즉시 종료
+
+# 실행 모드 설정
+case "$1" in
+    data-gen)
+        echo "데이터 생성 중..."
+        bash /usr/src/app/making.sh
+        ;;
+    evaluate)
+        echo "평가 실행 중..."
+        python /usr/src/app/main.py
+        ;;
+    bash)
+        echo "컨테이너 내부 접근"
+        exec /bin/bash
+        ;;
+    *)
+        echo "기본 default 실행 모드: bash"
+        echo "사용 가능한 실행 모드: data-gen | evaluate | bash"
+        exit 1
+        ;;
+esac
diff --git a/autorag-workspace/main.py b/main.py
similarity index 78%
rename from autorag-workspace/main.py
rename to main.py
index 4ddea57..b9021c0 100644
--- a/autorag-workspace/main.py
+++ b/main.py
@@ -6,13 +6,13 @@ from dotenv import load_dotenv
 
 from llama_index.llms.ollama import Ollama
 
-data_path = '../projects/daesan-dangjin_01' # 폴더명 확인
+data_path = './projects/example_01' # 폴더명 확인
 
 OLLAMA_BASE_URL = "autorag-ollama:11434"
 autorag.generator_models["ollama"] = autorag.LazyInit(Ollama, base_url=OLLAMA_BASE_URL, model="phi4", request_timeout=300, num_gpus=1)
 autorag.generator_models["ollama"] = autorag.LazyInit(Ollama, base_url=OLLAMA_BASE_URL, model="gemma3:12b", request_timeout=300, num_gpus=1)
-autorag.generator_models["ollama"] = autorag.LazyInit(Ollama, base_url=OLLAMA_BASE_URL, model="deepseek-r1:14b", request_timeout=300, num_gpus=1)
-autorag.generator_models["ollama"] = autorag.LazyInit(Ollama, base_url=OLLAMA_BASE_URL, model="aya-expanse:8b", request_timeout=300, num_gpus=1)
+# autorag.generator_models["ollama"] = autorag.LazyInit(Ollama, base_url=OLLAMA_BASE_URL, model="deepseek-r1:14b", request_timeout=300, num_gpus=1)
+# autorag.generator_models["ollama"] = autorag.LazyInit(Ollama, base_url=OLLAMA_BASE_URL, model="aya-expanse:8b", request_timeout=300, num_gpus=1)
 
 # autorag/embedding/base.py 임베딩 모델추가함
 
diff --git a/autorag-workspace/making.sh b/making.sh
similarity index 98%
rename from autorag-workspace/making.sh
rename to making.sh
index adf450f..c15bb0b 100644
--- a/autorag-workspace/making.sh
+++ b/making.sh
@@ -1,6 +1,6 @@
 #!/bin/bash
 
-PROJECT_DIR="../projects/daesan-dangjin_01"
+PROJECT_DIR="../projects/example_01"
 CONFIG_DIR="$PROJECT_DIR/config"
 RAW_DATA_DIR="$PROJECT_DIR/raw_data"
 
diff --git a/projects/example_01/benchmark/data/corpus.parquet b/projects/example_01/benchmark/data/corpus.parquet
new file mode 100644
index 0000000..2b7726f
Binary files /dev/null and b/projects/example_01/benchmark/data/corpus.parquet differ
diff --git a/projects/example_01/benchmark/data/qa.parquet b/projects/example_01/benchmark/data/qa.parquet
new file mode 100644
index 0000000..4a90b0b
Binary files /dev/null and b/projects/example_01/benchmark/data/qa.parquet differ
diff --git a/projects/src/check_corpus_ids.py b/projects/src/check_corpus_ids.py
deleted file mode 100644
index c6e997e..0000000
--- a/projects/src/check_corpus_ids.py
+++ /dev/null
@@ -1,12 +0,0 @@
-import pandas as pd
-
-# corpus.parquet 파일 로드
-corpus_path = "./original/corpus.parquet"
-corpus_data = pd.read_parquet(corpus_path)
-
-# 특정 문서 ID가 존재하는지 확인
-doc_id = "bac7dea6-9477-4290-b57b-861548f7020d"
-print(doc_id in corpus_data['doc_id'].values)  # True면 존재, False면 없음
-
-# corpus_data의 첫 5개 데이터 확인
-print(corpus_data.head())
\ No newline at end of file
diff --git a/projects/src/check_vectordb_corpus.py b/projects/src/check_vectordb_corpus.py
deleted file mode 100644
index c9da3c0..0000000
--- a/projects/src/check_vectordb_corpus.py
+++ /dev/null
@@ -1,14 +0,0 @@
-from chromadb import PersistentClient
-
-# ChromaDB 클라이언트 연결
-client = PersistentClient(path="./report_01/chroma")
-
-# 컬렉션 목록 확인
-print(client.list_collections())
-
-# 'document_collection' 컬렉션에서 데이터 조회
-collection = client.get_collection("document_collection")
-
-# 저장된 모든 문서 ID 조회
-stored_docs = collection.get(include=["ids"])
-print("Stored Document IDs:", stored_docs)
diff --git a/projects/src/check_vectordb_ingestion.py b/projects/src/check_vectordb_ingestion.py
deleted file mode 100644
index 78db362..0000000
--- a/projects/src/check_vectordb_ingestion.py
+++ /dev/null
@@ -1,11 +0,0 @@
-import chromadb
-
-# ChromaDB 연결
-client = chromadb.PersistentClient(path="./report_01/chroma")
-collection = client.get_collection("document_collection")
-
-# 저장된 문서 개수 확인
-print("Stored Document Count:", len(collection.get(include=['ids'])['ids']))
-
-# 일부 문서 ID 확인
-print("Example Document IDs:", collection.get(include=['ids'], limit=5)['ids'])
diff --git a/projects/src/convert_parquet_to_json.py b/projects/src/convert_parquet_to_json.py
deleted file mode 100644
index 0059d9d..0000000
--- a/projects/src/convert_parquet_to_json.py
+++ /dev/null
@@ -1,21 +0,0 @@
-import os
-import pandas as pd
-
-SOURCE_DIR = "/usr/src/app/projects/daesan-dangjin_01"
-TARGET_DIR = "/usr/src/app/projects/daesan-dangjin_01/json"
-os.makedirs(TARGET_DIR, exist_ok=True)
-
-parquet_files = [f for f in os.listdir(SOURCE_DIR) if f.endswith(".parquet")]
-
-
-for file in parquet_files:
-    parquet_path = os.path.join(SOURCE_DIR, file)
-    json_filename = os.path.splitext(file)[0] + ".json"
-    json_path = os.path.join(TARGET_DIR, json_filename)
-    
-    df = pd.read_parquet(parquet_path, engine="pyarrow")
-    df.to_json(json_path, orient="records", force_ascii=False, indent=2)
-
-    print(f"✅ 변환 완료: {json_path}")
-
-print(f"📁 모든 Parquet 파일이 JSON으로 변환되어 {TARGET_DIR}에 저장되었습니다.")
diff --git a/requirements.txt b/requirements.txt
index 6378e06..080e917 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,65 +1,362 @@
-pydantic<2.10.0 # incompatible with llama index
-numpy<2.0.0 # temporal not using numpy 2.0.0
-pandas>=2.1.0
-tqdm
-tiktoken>=0.7.0  # for counting token
-openai>=1.0.0
-rank_bm25  # for bm25 retrieval
-pyyaml  # for yaml file
-pyarrow  # for pandas with parquet
-fastparquet  # for pandas with parquet
-sacrebleu  # for bleu score
-evaluate  # for meteor and other scores
-rouge_score  # for rouge score
-rich  # for pretty logging
-click  # for cli
-cohere>=5.8.0 # for cohere services
-tokenlog>=0.0.2 # for token logging
-aiohttp # for async http requests
-voyageai # for voyageai reranker
-mixedbread-ai # for mixedbread-ai reranker
-llama-index-llms-bedrock
-scikit-learn
-emoji
-
-### Vector DB ###
-pymilvus>=2.3.0 # for using milvus vectordb
-chromadb>=0.5.0 # for chroma vectordb
-weaviate-client # for weaviate vectordb
-pinecone[grpc] # for pinecone vectordb
-couchbase # for couchbase vectordb
-qdrant-client # for qdrant vectordb
-
-### API server ###
-quart
-pyngrok
-### LlamaIndex ###
-llama-index>=0.11.0
-llama-index-core>=0.11.0
-# readers
-llama-index-readers-file
-# Embeddings
-llama-index-embeddings-openai
-llama-index-embeddings-ollama
-# LLMs
-llama-index-llms-openai>=0.2.7
-llama-index-llms-openai-like
-# Retriever
-llama-index-retrievers-bm25
-
-# WebUI
-streamlit
-gradio
-
-### Langchain ###
-langchain-core==0.3.0
-langchain-unstructured>=0.1.5
-langchain-upstage
-langchain-community>=0.3.0
-
-# autorag dashboard
-panel
-seaborn
-ipykernel
-ipywidgets
-ipywidgets_bokeh
\ No newline at end of file
+about-time==4.2.1
+absl-py==2.1.0
+accelerate==1.5.2
+aiofiles==23.2.1
+aiohappyeyeballs==2.6.1
+aiohttp==3.11.14
+aiolimiter==1.2.1
+aiosignal==1.3.2
+alive-progress==3.2.0
+altair==5.5.0
+annotated-types==0.7.0
+anthropic==0.28.1
+anyio==4.9.0
+asgiref==3.8.1
+asttokens==3.0.0
+async-timeout==4.0.3
+attrs==25.3.0
+Authlib==1.3.1
+autograd==1.7.0
+AutoRAG==0.3.13
+backoff==2.2.1
+bcrypt==4.3.0
+beautifulsoup4==4.13.3
+bert-score==0.3.13
+bleach==6.2.0
+blinker==1.9.0
+bm25s==0.2.9
+bokeh==3.6.3
+boto3==1.37.14
+botocore==1.37.14
+build==1.2.2.post1
+cachetools==5.5.2
+cbor==1.0.0
+certifi==2025.1.31
+cffi==1.17.1
+charset-normalizer==3.4.1
+chroma-hnswlib==0.7.6
+chromadb==0.6.3
+click==8.1.8
+cma==3.2.2
+cohere==5.14.0
+colorama==0.4.6
+coloredlogs==15.0.1
+comm==0.2.2
+contourpy==1.3.1
+couchbase==4.3.5
+cramjam==2.9.1
+cryptography==44.0.2
+cycler==0.12.1
+dataclasses-json==0.6.7
+datasets==3.2.0
+debugpy==1.8.13
+decorator==5.2.1
+Deprecated==1.2.18
+dill==0.3.8
+dirtyjson==1.0.8
+distro==1.9.0
+durationpy==0.9
+emoji==2.14.1
+eval_type_backport==0.2.2
+evaluate==0.4.3
+exceptiongroup==1.2.2
+executing==2.2.0
+fastapi==0.115.11
+fastavro==1.10.0
+fastparquet==2024.11.0
+ffmpy==0.5.0
+filelock==3.18.0
+filetype==1.2.0
+FlagEmbedding==1.3.4
+Flask==3.1.0
+flatbuffers==25.2.10
+fonttools==4.56.0
+frozenlist==1.5.0
+fsspec==2024.9.0
+gitdb==4.0.12
+GitPython==3.1.44
+google-auth==2.38.0
+googleapis-common-protos==1.69.2
+gradio==4.44.1
+gradio_client==1.3.0
+grapheme==0.6.0
+greenlet==3.1.1
+groovy==0.1.2
+grpcio==1.67.1
+grpcio-health-checking==1.67.1
+grpcio-tools==1.67.1
+h11==0.14.0
+h2==4.2.0
+hpack==4.1.0
+httpcore==1.0.7
+httptools==0.6.4
+httpx==0.27.2
+httpx-sse==0.4.0
+huggingface-hub==0.23.5
+humanfriendly==10.0
+Hypercorn==0.17.3
+hyperframe==6.1.0
+idna==3.10
+ijson==3.3.0
+importlib_metadata==8.6.1
+importlib_resources==6.5.2
+inscriptis==2.5.3
+ipykernel==6.29.5
+ipython==8.34.0
+ipywidgets==8.1.5
+ipywidgets_bokeh==1.6.0
+ir_datasets==0.5.10
+itsdangerous==2.2.0
+jedi==0.19.2
+Jinja2==3.1.6
+jiter==0.9.0
+jmespath==1.0.1
+joblib==1.4.2
+jpype1==1.5.2
+jsonpatch==1.33
+jsonpath-python==1.0.6
+jsonpointer==3.0.0
+jsonschema==4.23.0
+jsonschema-specifications==2024.10.1
+jstyleson==0.0.2
+jupyter_client==8.6.3
+jupyter_core==5.7.2
+jupyterlab_widgets==3.0.13
+kiwipiepy==0.20.4
+kiwipiepy_model==0.20.0
+kiwisolver==1.4.8
+konlpy==0.6.0
+kubernetes==32.0.1
+langchain==0.3.20
+langchain-community==0.3.19
+langchain-core==0.3.45
+langchain-openai==0.3.9
+langchain-text-splitters==0.3.6
+langchain-unstructured==0.1.6
+langchain-upstage==0.6.0
+langsmith==0.3.15
+linkify-it-py==2.0.3
+llama-cloud==0.1.14
+llama-cloud-services==0.6.5
+llama-index==0.11.22
+llama-index-agent-openai==0.3.4
+llama-index-cli==0.3.1
+llama-index-core==0.11.23
+llama-index-embeddings-huggingface==0.3.1
+llama-index-embeddings-ollama==0.3.1
+llama-index-embeddings-openai==0.2.5
+llama-index-indices-managed-llama-cloud==0.6.0
+llama-index-legacy==0.9.48.post4
+llama-index-llms-anthropic==0.2.1
+llama-index-llms-bedrock==0.2.6
+llama-index-llms-huggingface==0.3.5
+llama-index-llms-ollama==0.3.6
+llama-index-llms-openai==0.2.16
+llama-index-llms-openai-like==0.2.0
+llama-index-multi-modal-llms-openai==0.2.3
+llama-index-program-openai==0.2.0
+llama-index-question-gen-openai==0.2.0
+llama-index-readers-file==0.2.2
+llama-index-readers-llama-parse==0.3.0
+llama-index-retrievers-bm25==0.4.0
+llama-parse==0.6.4.post1
+llmlingua==0.2.2
+lxml==5.3.1
+lz4==4.4.3
+Markdown==3.7
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+marshmallow==3.26.1
+matplotlib==3.10.1
+matplotlib-inline==0.1.7
+mdit-py-plugins==0.4.2
+mdurl==0.1.2
+milvus-lite==2.4.11
+minijinja==2.8.0
+mixedbread-ai==2.2.6
+mmh3==5.1.0
+monotonic==1.6
+mpmath==1.3.0
+multidict==6.2.0
+multiprocess==0.70.16
+mypy-extensions==1.0.0
+narwhals==1.31.0
+natsort==8.4.0
+nest-asyncio==1.6.0
+networkx==3.3
+ninja==1.11.1.3
+nltk==3.9.1
+nncf==2.15.0
+numpy==1.26.4
+nvidia-cublas-cu12==12.4.5.8
+nvidia-cuda-cupti-cu12==12.4.127
+nvidia-cuda-nvrtc-cu12==12.4.127
+nvidia-cuda-runtime-cu12==12.4.127
+nvidia-cudnn-cu12==9.1.0.70
+nvidia-cufft-cu12==11.2.1.3
+nvidia-curand-cu12==10.3.5.147
+nvidia-cusolver-cu12==11.6.1.9
+nvidia-cusparse-cu12==12.3.1.170
+nvidia-cusparselt-cu12==0.6.2
+nvidia-nccl-cu12==2.21.5
+nvidia-nvjitlink-cu12==12.4.127
+nvidia-nvtx-cu12==12.4.127
+oauthlib==3.2.2
+ollama==0.3.3
+onnx==1.17.0
+onnxruntime==1.19.2
+openai==1.66.3
+opentelemetry-api==1.31.0
+opentelemetry-exporter-otlp-proto-common==1.31.0
+opentelemetry-exporter-otlp-proto-grpc==1.31.0
+opentelemetry-instrumentation==0.52b0
+opentelemetry-instrumentation-asgi==0.52b0
+opentelemetry-instrumentation-fastapi==0.52b0
+opentelemetry-proto==1.31.0
+opentelemetry-sdk==1.31.0
+opentelemetry-semantic-conventions==0.52b0
+opentelemetry-util-http==0.52b0
+openvino==2025.0.0
+openvino-telemetry==2025.1.0
+openvino-tokenizers==2025.0.0.0
+optimum==1.24.0
+optimum-intel==1.22.0
+orjson==3.10.15
+overrides==7.7.0
+packaging==24.2
+pandas==2.2.3
+panel==1.6.1
+param==2.2.0
+parso==0.8.4
+pdfminer.six==20231228
+pdfplumber==0.11.5
+peft==0.13.2
+pexpect==4.9.0
+pillow==10.4.0
+pinecone==6.0.2
+pinecone-plugin-interface==0.0.7
+platformdirs==4.3.6
+portalocker==2.10.1
+posthog==3.21.0
+priority==2.0.0
+prompt_toolkit==3.0.50
+propcache==0.3.0
+protobuf==5.29.3
+protoc-gen-openapiv2==0.0.1
+psutil==7.0.0
+ptyprocess==0.7.0
+pure_eval==0.2.3
+py-cpuinfo==9.0.0
+pyarrow==19.0.1
+pyasn1==0.6.1
+pyasn1_modules==0.4.1
+pycparser==2.22
+pydantic==2.9.2
+pydantic-settings==2.8.1
+pydantic_core==2.23.4
+pydeck==0.9.1
+pydot==2.0.0
+pydub==0.25.1
+Pygments==2.19.1
+pymilvus==2.5.5
+pymoo==0.6.1.3
+pyngrok==7.2.3
+pyparsing==3.2.1
+pypdf==4.3.1
+pypdfium2==4.30.1
+PyPika==0.48.9
+pyproject_hooks==1.2.0
+PyStemmer==2.2.0.3
+python-dateutil==2.8.2
+python-dotenv==1.0.1
+python-multipart==0.0.20
+pytz==2025.1
+pyviz_comms==3.0.4
+PyYAML==6.0.2
+pyzmq==26.3.0
+qdrant-client==1.13.3
+Quart==0.20.0
+rank-bm25==0.2.2
+referencing==0.36.2
+regex==2024.11.6
+requests==2.32.3
+requests-oauthlib==2.0.0
+requests-toolbelt==1.0.0
+rich==13.9.4
+rouge_score==0.1.2
+rpds-py==0.23.1
+rsa==4.9
+ruff==0.11.0
+s3transfer==0.11.4
+sacrebleu==2.5.1
+safehttpx==0.1.6
+safetensors==0.5.3
+scikit-learn==1.6.1
+scipy==1.15.2
+seaborn==0.13.2
+semantic-version==2.10.0
+sentence-transformers==3.4.1
+sentencepiece==0.2.0
+setuptools-scm==8.2.0
+shellingham==1.5.4
+six==1.17.0
+smmap==5.0.2
+sniffio==1.3.1
+soupsieve==2.6
+SQLAlchemy==2.0.39
+stack-data==0.6.3
+starlette==0.46.1
+streamlit==1.43.2
+striprtf==0.0.26
+sympy==1.13.1
+tabulate==0.9.0
+taskgroup==0.2.2
+tenacity==8.5.0
+text-generation==0.7.0
+threadpoolctl==3.6.0
+tiktoken==0.9.0
+tokenizers==0.19.1
+tokenlog==0.0.2
+toml==0.10.2
+tomli==2.2.1
+tomlkit==0.12.0
+torch==2.6.0
+tornado==6.4.2
+tqdm==4.67.1
+traitlets==5.14.3
+transformers==4.44.2
+trec-car-tools==2.6
+triton==3.2.0
+typer==0.15.2
+types-requests==2.32.0.20250306
+typing-inspect==0.9.0
+typing_extensions==4.12.2
+tzdata==2025.1
+uc-micro-py==1.0.3
+ujson==5.10.0
+unlzw3==0.2.3
+unstructured-client==0.27.0
+urllib3==2.3.0
+uvicorn==0.34.0
+uvloop==0.21.0
+validators==0.34.0
+voyageai==0.3.2
+warc3-wet==0.2.5
+warc3-wet-clueweb09==0.2.5
+watchdog==6.0.0
+watchfiles==1.0.4
+wcwidth==0.2.13
+weaviate-client==4.11.1
+webencodings==0.5.1
+websocket-client==1.8.0
+websockets==12.0
+Werkzeug==3.1.3
+widgetsnbextension==4.0.13
+wrapt==1.17.2
+wsproto==1.2.0
+xxhash==3.5.0
+xyzservices==2025.1.0
+yarl==1.18.3
+zipp==3.21.0
+zlib-state==0.1.9
+zstandard==0.23.0
\ No newline at end of file
diff --git a/requirements_custom.txt b/requirements_custom.txt
deleted file mode 100644
index 35bda56..0000000
--- a/requirements_custom.txt
+++ /dev/null
@@ -1,9 +0,0 @@
-# added library - 김용연
-llama_index.llms.ollama
-llama_index.embeddings.huggingface
-pdfplumber
-pypdfium2 
-pymupdf
-AutoRAG[gpu]
-AutoRAG[ko]
-konlpy
\ No newline at end of file