{"repo":"cocoindex-io/patient-intake-extraction","free":true,"listed":false,"github":"https://github.com/cocoindex-io/patient-intake-extraction","clone":"git clone https://github.com/cocoindex-io/patient-intake-extraction.git","description":"Patient Intake Form Extraction using llm","language":"Python","stars":16,"topics":["etl","llm","ocr","data-indexing","healthcare","machine-learning","rag"],"license":"Apache-2.0","category":"ai-agents","readme_excerpt":"🥥 Patient Intake Extraction with CocoIndex Extract structured data from patient intake forms (PDF) using CocoIndex v1 and DSPy with a Gemini vision model. Each form is rendered to images, passed to the LLM, and written out as a validated JSON record — incrementally, so re-runs only reprocess forms that actually changed. ❤️ Please give CocoIndex on GitHub a star ⭐ to support us. A warm coconut hug 🥥🤗. What it does - Pydantic models ( models.py ) define the target schema — type-safe, validated Patient records. - DSPy module ( main.py ) extracts directly from page images via ChainOfThought with vision — no intermediate text/markdown step. - CocoIndex v1 app ( main.py ) processes each form as an independent component and writes JSON, recomputing only what changed. Prerequisites - Python 3.11+ - A Gemini API key — no Postgres, no Docker. Run 1. Install dependencies (sample PDFs are already in data/patient forms/ ): 2. Set your API key — copy the template and add your Gemini key: The template also sets COCOINDEX DB=./cocoindex.db (the local engine state path), which is required. 3. Extract: This reads each PDF in data/patient forms/ , extracts the patient record, and writes JSON to output patients/ : Incremental processing Re-running never redoes work that's already done — process patient form is memoized by file content: Add, replace, or remove a PDF and re-run — only the affected form is reprocessed, and a removed PDF's JSON is cleaned up automatically. How it works The pipeli","default_branch":null,"files":null,"tree":[],"storefront":"/r/cocoindex-io","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/cocoindex-io/patient-intake-extraction/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}