bhaskatripathi/pdfGPT

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

7167 stars · 833 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

pdfGPT is an open-source Python application that lets users chat with the contents of PDF files using GPT capabilities. It implements a simple RAG-style architecture using Universal Sentence Encoder embeddings without a vector database or third-party frameworks like LangChain, and is deployed as a web app (e.g., on Hugging Face Spaces).

Use cases

• chat with a pdf document
• ask questions about a pdf file
• turn a pdf into a chatbot
• summarize and query long pdf documents
• avoid token limit issues when feeding pdfs to GPT
• get accurate answers from pdf content without hallucinations

When to choose

• you want a simple, dependency-light chat-with-PDF tool without LangChain or a vector DB
• you need accurate, precise answers from a single PDF
• you want a self-hostable open-source alternative to chatpdf.com
• you want a quick Hugging Face Spaces demo of PDF Q&A

When to avoid

• you need multi-PDF or OCR support (still on the roadmap)
• you need a production-grade RAG pipeline with modern vector stores and indexing
• you want a polished UI or actively updated documentation
• you need fully local/offline models without OpenAI API keys

Facets

application · maturity maintenance

rag nlp llm-inference pdf chatbot search-engine pdf large-language-models artificial-intelligence developer-tools python self-hosted cross-platform chat-with-pdf openai embeddings universal-sentence-encoder gradio question-answering document-chat natural-language-processing retrieval-augmented-generation web-server

Member repositories

For agents

markdown · JSON · MCP: product_card(name="bhaskatripathi/pdfGPT")