Initial commit

autorag-workspace/example/sample_config/chunk/chunk_full.yaml

@@ -0,0 +1,32 @@
+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

autorag-workspace/example/sample_config/chunk/chunk_ko.yaml

@@ -0,0 +1,19 @@
+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

autorag-workspace/example/sample_config/chunk/simple_chunk.yaml

@@ -0,0 +1,3 @@
+modules:
+  - module_type: llama_index_chunk
+    chunk_method: Token

autorag-workspace/example/sample_config/parse/all_files_full.yaml

@@ -0,0 +1,25 @@
+# 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

autorag-workspace/example/sample_config/parse/file_types_full.yaml

@@ -0,0 +1,26 @@
+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

autorag-workspace/example/sample_config/parse/parse_hybird.yaml

@@ -0,0 +1,12 @@
+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

autorag-workspace/example/sample_config/parse/parse_ko.yaml

@@ -0,0 +1,11 @@
+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

autorag-workspace/example/sample_config/parse/parse_multimodal.yaml

@@ -0,0 +1,8 @@
+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

autorag-workspace/example/sample_config/parse/parse_ocr.yaml

@@ -0,0 +1,10 @@
+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

autorag-workspace/example/sample_config/parse/simple_parse.yaml

@@ -0,0 +1,4 @@
+modules:
+  - module_type: langchain_parse
+    file_type: pdf
+    parse_method: pdfminer

autorag-workspace/example/sample_config/rag/english/gpu/compact_local.yaml

@@ -0,0 +1,50 @@
+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]

autorag-workspace/example/sample_config/rag/english/gpu/compact_openai.yaml

@@ -0,0 +1,101 @@
+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]

autorag-workspace/example/sample_config/rag/english/gpu/full.yaml

@@ -0,0 +1,154 @@
+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

autorag-workspace/example/sample_config/rag/english/gpu/half.yaml

@@ -0,0 +1,121 @@
+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]

autorag-workspace/example/sample_config/rag/english/gpu_api/compact.yaml

@@ -0,0 +1,105 @@
+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]

autorag-workspace/example/sample_config/rag/english/gpu_api/full.yaml

@@ -0,0 +1,151 @@
+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

autorag-workspace/example/sample_config/rag/english/gpu_api/half.yaml

@@ -0,0 +1,118 @@
+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]

autorag-workspace/example/sample_config/rag/english/non_gpu/compact.yaml

@@ -0,0 +1,83 @@
+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]

autorag-workspace/example/sample_config/rag/english/non_gpu/full.yaml

@@ -0,0 +1,129 @@
+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

autorag-workspace/example/sample_config/rag/english/non_gpu/half.yaml

@@ -0,0 +1,95 @@
+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]

autorag-workspace/example/sample_config/rag/english/non_gpu/simple_bedrock.yaml

@@ -0,0 +1,33 @@
+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

autorag-workspace/example/sample_config/rag/english/non_gpu/simple_local.yaml

@@ -0,0 +1,31 @@
+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

autorag-workspace/example/sample_config/rag/english/non_gpu/simple_ollama.yaml

@@ -0,0 +1,34 @@
+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)

autorag-workspace/example/sample_config/rag/english/non_gpu/simple_openai.yaml

@@ -0,0 +1,25 @@
+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 ]

autorag-workspace/example/sample_config/rag/extracted_sample.yaml

@@ -0,0 +1,47 @@
+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

autorag-workspace/example/sample_config/rag/full.yaml

@@ -0,0 +1,159 @@
+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

autorag-workspace/example/sample_config/rag/korean/gpu/compact_korean.yaml

@@ -0,0 +1,93 @@
+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]

autorag-workspace/example/sample_config/rag/korean/gpu/full_korean.yaml

@@ -0,0 +1,157 @@
+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]

autorag-workspace/example/sample_config/rag/korean/gpu/half_korean.yaml

@@ -0,0 +1,126 @@
+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]

autorag-workspace/example/sample_config/rag/korean/gpu_api/compact_korean.yaml

@@ -0,0 +1,87 @@
+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]

autorag-workspace/example/sample_config/rag/korean/gpu_api/full_korean.yaml

@@ -0,0 +1,151 @@
+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]

autorag-workspace/example/sample_config/rag/korean/gpu_api/half_korean.yaml

@@ -0,0 +1,120 @@
+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]

autorag-workspace/example/sample_config/rag/korean/non_gpu/compact_korean.yaml

@@ -0,0 +1,78 @@
+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]

autorag-workspace/example/sample_config/rag/korean/non_gpu/full_korean.yaml

@@ -0,0 +1,142 @@
+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]

autorag-workspace/example/sample_config/rag/korean/non_gpu/half_korean.yaml

@@ -0,0 +1,111 @@
+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]

autorag-workspace/example/sample_config/rag/korean/non_gpu/simple_korean.yaml

@@ -0,0 +1,30 @@
+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 ]

autorag-workspace/example/sample_dataset/README.md

@@ -0,0 +1,25 @@
+# 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.

autorag-workspace/example/sample_dataset/eli5/load_eli5_dataset.py

@@ -0,0 +1,35 @@
+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()

autorag-workspace/example/sample_dataset/hotpotqa/load_hotpotqa_dataset.py

@@ -0,0 +1,35 @@
+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()

autorag-workspace/example/sample_dataset/msmarco/load_msmarco_dataset.py

@@ -0,0 +1,37 @@
+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()

autorag-workspace/example/sample_dataset/triviaqa/load_triviaqa_dataset.py

@@ -0,0 +1,37 @@
+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()