Here are
1,022 public repositories
matching this topic...
Multimodal RAG over PDFs. Three parallel pipelines (LLM summaries, raw atomic content, CLIP visual) with HyDE expansion and cross encoder reranking, answers cited inline.
Updated
Jul 22, 2026
Jupyter Notebook
Transcription project consisting of Python scripting and usage of AI/ML text extraction models.
Updated
Sep 14, 2024
Python
RAG-based PDF intelligence system using LangChain, Hugging Face embeddings, and Pinecone for semantic document querying.
Updated
May 8, 2026
Python
OCR + LLM-enhanced parsing FastAPI service with structured JSON outputs, confidence scoring, Docker deployment, and API docs.
Updated
Jul 3, 2026
Python
Local OCR and LLM-based pipeline for extracting structured JSON from complex PDF documents.
Updated
May 12, 2026
Python
Updated
Aug 10, 2026
Python
AI decision workflows that turn enterprise documents into traceable decisions, executive artifacts and operational handoffs.
Updated
May 18, 2026
Python
Field-level evaluation for document extraction with vision language models. Tells you whether a change made your documents read better or worse — and whether the difference is real.
Updated
Aug 11, 2026
Python
Reliability-first VLM evidence platform with calibrated risk routing, constrained human review, and auditable promotion gates.
Updated
Aug 11, 2026
Python
Reproducible experiments for TableFormer and TFLOP transfer to scientific table recognition
Updated
Aug 13, 2026
Python
Fine-tuned open-weight LLMs (Mistral-7B, LLaMA-2) with LoRA/PEFT for document understanding — 92% accuracy, 40% GPU memory cut via mixed precision.
Updated
Jul 28, 2026
Python
Source-grounded document chatbot starter with citations, configurable AI providers, and local-first setup.
Updated
Aug 15, 2026
TypeScript
医结智控 MedLedger Agent｜非结构化医疗销售文档到可审计结算报表
Updated
Aug 17, 2026
Python
A private, citation-aware local RAG research assistant powered by Ollama, ChromaDB, and Streamlit.
Updated
Jul 18, 2026
Python
AudioPage: native iPhone and iPad read-aloud app for PDFs, books, articles, scans, and notes. On-device listening with document AI when you ask.
Updated
Jul 17, 2026
TypeScript
End-to-end receipt OCR pipeline using OpenCV and Tesseract OCR to extract structured data from images and PDFs.
Updated
Apr 26, 2026
Python
Governed agentic AI workflow for motor-insurance claims with extraction, validation, policy RAG, guarded tools, human review, memory, evaluations, and end-to-end observability.
Updated
Jul 20, 2026
TypeScript
Document-extraction RAG: 95.5% weighted field-level accuracy on 28-case offline CI replay; 202-case corpus (151+51). FastAPI + pgvector + Claude.
Updated
Aug 13, 2026
Python
Bangla handwritten document OCR: EAST detection, CRNN recognition, FastAPI + Gradio
Updated
Jul 15, 2026
Python
Improve this page
Add a description, image, and links to the
document-ai
topic page so that developers can more easily learn about it.
Curate this topic
Add this topic to your repo
To associate your repository with the
document-ai
topic, visit your repo's landing page and select "manage topics."
Learn more
You can’t perform that action at this time.