{"id":30104932,"url":"https://github.com/aditya-ranjan1234/finquery","last_synced_at":"2025-08-09T23:16:52.632Z","repository":{"id":308144846,"uuid":"1031206488","full_name":"Aditya-Ranjan1234/FinQuery","owner":"Aditya-Ranjan1234","description":" Smart AI Assistant for Financial Document Retrieval","archived":false,"fork":false,"pushed_at":"2025-08-04T14:12:21.000Z","size":5237,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-08-04T14:17:12.124Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://fin-query.vercel.app","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Aditya-Ranjan1234.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-08-03T08:43:32.000Z","updated_at":"2025-08-04T14:13:28.000Z","dependencies_parsed_at":"2025-08-04T14:28:49.622Z","dependency_job_id":null,"html_url":"https://github.com/Aditya-Ranjan1234/FinQuery","commit_stats":null,"previous_names":["aditya-ranjan1234/finquery"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/Aditya-Ranjan1234/FinQuery","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Aditya-Ranjan1234%2FFinQuery","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Aditya-Ranjan1234%2FFinQuery/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Aditya-Ranjan1234%2FFinQuery/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Aditya-Ranjan1234%2FFinQuery/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Aditya-Ranjan1234","download_url":"https://codeload.github.com/Aditya-Ranjan1234/FinQuery/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Aditya-Ranjan1234%2FFinQuery/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":269649971,"owners_count":24453569,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-08-09T02:00:10.424Z","response_time":111,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-08-09T23:16:51.983Z","updated_at":"2025-08-09T23:16:52.615Z","avatar_url":"https://github.com/Aditya-Ranjan1234.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# HackRx 6.0 – LLM Document Processing System\n\nAn end-to-end, well-documented Python project that demonstrates how to build an **LLM-powered query–retrieval and decision engine** over large, unstructured documents (PDFs, Word, e-mails).\n\n## Features\n\n1. **Multi-format ingestion** – loaders for PDF, DOCX, and E-mail files extract text + metadata.\n2. **Semantic vector store** – documents are chunked, embedded via `sentence-transformers`, and indexed with FAISS for fast nearest-neighbour search.\n3. **Natural-language query parser** – rule-based + LLM fallback extracts structured fields (age, procedure, location, policy age, …).\n4. **Decision engine** – pluggable logic evaluates retrieved clauses and returns JSON containing:\n   ```json\n   {\n     \"decision\": \"approved | rejected\",\n     \"amount\": 12345.67,\n     \"justification\": \"Text explanation …\",\n     \"clauses\": [ {\"id\": \"…\", \"text\": \"…\"} ]\n   }\n   ```\n5. **CLI** – `python -m hackrx_llm --docs /path/to/folder --ask \"46M knee surgery Pune 3-month policy\"`.\n6. **Extensible** – swap embeddings, LLM provider, or decision logic.\n7. **Test-driven** – `pytest` covers parsing and retrieval.\n\n## Quick-start\n\n```bash\npython -m venv .venv \u0026\u0026 source .venv/bin/activate  # Windows: .venv\\Scripts\\activate\npip install -r requirements.txt\n\n# Build vector store (runs ingestion automatically)\npython -m hackrx_llm ingest --docs sample_docs\n\n# Ask a question\npython -m hackrx_llm ask --query \"46-year-old male, knee surgery in Pune, 3-month policy\" --top_k 5\n```\n\nIf an **OpenAI** key is present (`export OPENAI_API_KEY=…`), the parser will enrich/validate fields via GPT automatically; otherwise, rule-based extraction is used.\n\n## Project Structure\n\n```\n├── hackrx_llm/          ← Library package\n│   ├── ingestion/       ← PDF, Word, e-mail loaders\n│   ├── parser.py        ← Query → structured data\n│   ├── retriever.py     ← Vector store + semantic search\n│   ├── decision_engine.py\n│   ├── schema.py        ← Pydantic models\n│   ├── cli.py           ← Typer CLI\n│   └── __init__.py\n├── tests/               ← Unit tests (pytest)\n├── requirements.txt\n└── README.md            ← You are here\n```\n\n## Design Diagram\n\n```mermaid\ngraph TD\n    A(User Query) --\u003e B(Parser)\n    B --\u003e C[Structured Query]\n    C --\u003e D(Retriever)\n    D --\u003e E[Relevant Clauses]\n    C --\u003e F(Decision Engine)\n    E --\u003e F\n    F --\u003e G[JSON Response]\n```\n\n## Contributing\n\n1. Fork -\u003e git clone -\u003e create feature branch.\n2. Ensure `pytest` passes \u0026 run `black` / `ruff`.\n3. PR with clear description.\n\n## License\n\nMIT © 2025 Bajaj Finserv Health Ltd.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faditya-ranjan1234%2Ffinquery","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faditya-ranjan1234%2Ffinquery","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faditya-ranjan1234%2Ffinquery/lists"}