AllAboutAI-YT/easy-local-rag

Health v2 · maintenance only

Adoption not part of the score

1220 stars · 334 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A Python application providing 100% local retrieval-augmented generation (RAG) using Ollama for LLM inference and embeddings. It supports ingesting PDFs, text, and JSON files, plus a Gmail-based email RAG mode, with query rewriting and conversation history.

Use cases

• chat with my pdf documents locally
• run RAG without sending data to the cloud
• ask questions about my gmail emails with a local LLM
• set up a simple local RAG pipeline with Ollama
• query my text and JSON files with llama3
• improve retrieval on vague questions with query rewriting

When to choose

• you want a fully local, privacy-preserving RAG setup with Ollama
• you want a simple, tutorial-backed starter project for document or email Q&A
• you prefer running llama3/mistral and embeddings on your own machine

When to avoid

• you need a production-grade, scalable RAG service with a web UI
• you require multi-user or cloud deployment features
• you want a maintained library with an API rather than scripts

Facets

application · maturity active

rag llm-inference chatbot search-engine large-language-models artificial-intelligence email python cli self-hosted ollama local-llm email-rag embeddings tutorial-project retrieval-augmented-generation

Member repositories

For agents

markdown · JSON · MCP: product_card(name="AllAboutAI-YT/easy-local-rag")