Initial commit

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