ai-agent

Local_Pdf_Chat_RAG: Fast Hybrid Retrieval for AI Apps

Name: Local_Pdf_Chat_RAG: Fast Hybrid Retrieval for AI Apps
Author: weiwill88

A pure‑Python RAG framework that blends FAISS and BM25 for rapid document Q&A, compatible with Ollama and SiliconFlow, perfect for founders building AI chat solutions.

From the repo · “Transparent Python RAG reference with FAISS + BM25 hybrid retrieval, reranking, Gradio UI, and FastAPI.”

958 stars183 forksPythonGuide quality 9/10 · reviewed Oct 10Updated 8/31/2026100% free · open source

What it does

Local_Pdf_Chat_RAG generates human-like text based on the content of local PDF files using retrieval-augmented generation, ideal for founders new to NLP and QA tools

When to use it

•You need to generate text based on a large corpus of local PDF files
•You want to build a QA system that can retrieve information from local PDF files
•You are looking for a simple, pure Python implementation of a RAG framework

Ready-to-paste prompt

Run `python app.py -p 'What is the main topic of the PDF file called example.pdf?'` to generate a response based on the content of the `example.pdf` file

Heads up: Make sure you have the required dependencies, including FAISS and BM25, installed and configured correctly, as specified in the README

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/local-pdf-chat-rag && curl -fsSL https://workflowstacks.com/api/skills/local-pdf-chat-rag/claude-skill -o ~/.claude/skills/local-pdf-chat-rag/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How Local_Pdf_Chat_RAG: Fast Hybrid Retrieval for AI Apps works

Codeflow

Free to inspect

Local_Pdf_Chat_RAG: Fast Hybrid Retrieval for AI Apps is a small Python project (~2.1k lines across 19 code files, plus 5 test files). Setup is light: install Python, run one command. Last commit 2 months ago, MIT license, has a test suite.

Size

Small codebase

~2.1k lines · 19 code files · 18 min skim

Setup

Light setup

Install Python, run one command.

Runs on

Python

No API keys detected

Python 100%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
requirements.txt
Dependencies and the commands it exposes
3
core/__init__.py
Inside core/ — the main logic begins here

What's in each folder

core/Core code — the actual logic9 files

openwiki/Folder24 files

features/Folder4 files

utils/Helper scripts2 files

.github/CI / automation (GitHub Actions)5 files

tests/Tests — proof it works5 files

images/Images & static assets4 files

READMEHas testsDocumentedCI checksMIT licenseUpdated 2 mo ago