├── .gitignore ├── LICENSE ├── README.md ├── data ├── erc2_set │ ├── README.md │ ├── answers_1st_place_llama_70b.json │ ├── answers_1st_place_o3-mini.json │ ├── questions.json │ ├── subset.csv │ └── subset.json └── test_set │ ├── README.md │ ├── answers_max_nst_o3m.json │ ├── answers_max_nst_o3m_debug.json │ ├── databases.zip │ ├── debug_data.zip │ ├── pdf_reports │ ├── 194000c9109c6fa628f1fed33b44ae4c2b8365f4.pdf │ ├── 2779336b845a41544348abb7b3e6e5bd2ff893a2.pdf │ ├── 9d7a72445aba6860402c3acce75af02dc045f74d.pdf │ ├── ac9aa244462c80705c3ff046542c02c459989742.pdf │ └── e2b19d2cc2ccab2fd9022326b56b38fb0e772e73.pdf │ ├── questions.json │ └── subset.csv ├── env ├── main.py ├── requirements.txt ├── setup.py └── src ├── __init__.py ├── api_request_parallel_processor.py ├── api_requests.py ├── dummy_report.pdf ├── ingestion.py ├── parsed_reports_merging.py ├── pdf_parsing.py ├── pipeline.py ├── prompts.py ├── questions_processing.py ├── reranking.py ├── retrieval.py ├── tables_serialization.py └── text_splitter.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/README.md -------------------------------------------------------------------------------- /data/erc2_set/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/data/erc2_set/README.md -------------------------------------------------------------------------------- /data/erc2_set/answers_1st_place_llama_70b.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/data/erc2_set/answers_1st_place_llama_70b.json -------------------------------------------------------------------------------- /data/erc2_set/answers_1st_place_o3-mini.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/data/erc2_set/answers_1st_place_o3-mini.json -------------------------------------------------------------------------------- /data/erc2_set/questions.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/data/erc2_set/questions.json -------------------------------------------------------------------------------- /data/erc2_set/subset.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/data/erc2_set/subset.csv -------------------------------------------------------------------------------- /data/erc2_set/subset.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/data/erc2_set/subset.json -------------------------------------------------------------------------------- /data/test_set/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/data/test_set/README.md -------------------------------------------------------------------------------- /data/test_set/answers_max_nst_o3m.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/data/test_set/answers_max_nst_o3m.json -------------------------------------------------------------------------------- /data/test_set/answers_max_nst_o3m_debug.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/data/test_set/answers_max_nst_o3m_debug.json -------------------------------------------------------------------------------- /data/test_set/databases.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/data/test_set/databases.zip -------------------------------------------------------------------------------- /data/test_set/debug_data.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/data/test_set/debug_data.zip -------------------------------------------------------------------------------- /data/test_set/pdf_reports/194000c9109c6fa628f1fed33b44ae4c2b8365f4.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/data/test_set/pdf_reports/194000c9109c6fa628f1fed33b44ae4c2b8365f4.pdf -------------------------------------------------------------------------------- /data/test_set/pdf_reports/2779336b845a41544348abb7b3e6e5bd2ff893a2.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/data/test_set/pdf_reports/2779336b845a41544348abb7b3e6e5bd2ff893a2.pdf -------------------------------------------------------------------------------- /data/test_set/pdf_reports/9d7a72445aba6860402c3acce75af02dc045f74d.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/data/test_set/pdf_reports/9d7a72445aba6860402c3acce75af02dc045f74d.pdf -------------------------------------------------------------------------------- /data/test_set/pdf_reports/ac9aa244462c80705c3ff046542c02c459989742.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/data/test_set/pdf_reports/ac9aa244462c80705c3ff046542c02c459989742.pdf -------------------------------------------------------------------------------- /data/test_set/pdf_reports/e2b19d2cc2ccab2fd9022326b56b38fb0e772e73.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/data/test_set/pdf_reports/e2b19d2cc2ccab2fd9022326b56b38fb0e772e73.pdf -------------------------------------------------------------------------------- /data/test_set/questions.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/data/test_set/questions.json -------------------------------------------------------------------------------- /data/test_set/subset.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/data/test_set/subset.csv -------------------------------------------------------------------------------- /env: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/env -------------------------------------------------------------------------------- /main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/main.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/requirements.txt -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/setup.py -------------------------------------------------------------------------------- /src/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/api_request_parallel_processor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/src/api_request_parallel_processor.py -------------------------------------------------------------------------------- /src/api_requests.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/src/api_requests.py -------------------------------------------------------------------------------- /src/dummy_report.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/src/dummy_report.pdf -------------------------------------------------------------------------------- /src/ingestion.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/src/ingestion.py -------------------------------------------------------------------------------- /src/parsed_reports_merging.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/src/parsed_reports_merging.py -------------------------------------------------------------------------------- /src/pdf_parsing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/src/pdf_parsing.py -------------------------------------------------------------------------------- /src/pipeline.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/src/pipeline.py -------------------------------------------------------------------------------- /src/prompts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/src/prompts.py -------------------------------------------------------------------------------- /src/questions_processing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/src/questions_processing.py -------------------------------------------------------------------------------- /src/reranking.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/src/reranking.py -------------------------------------------------------------------------------- /src/retrieval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/src/retrieval.py -------------------------------------------------------------------------------- /src/tables_serialization.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/src/tables_serialization.py -------------------------------------------------------------------------------- /src/text_splitter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IlyaRice/RAG-Challenge-2/HEAD/src/text_splitter.py --------------------------------------------------------------------------------