ENDEVSOLS/Long-Trainer
Production-ready RAG framework for Python — multi-tenant chatbots with streaming, tool calling, agent mode (LangGraph), vector search (FAISS), and persistent MongoDB memory. Built on LangChain.
Built on LangChain, LongTrainer abstracts multi-bot isolation, MongoDB-backed persistent chat memory with encryption, and document ingestion into simple APIs—eliminating boilerplate for production RAG deployments. The framework supports per-bot customization (custom LLMs, embeddings, retrieval configs), vision chat with image analysis, and dynamic tool integration from LangChain's ecosystem, enabling both RAG and agentic modes via LangGraph. It includes a zero-code CLI and FastAPI server with 18 REST endpoints for deployment without writing Python.
Stars
13
Forks
3
Language
Python
License
MIT
Category
Last pushed
Mar 09, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/ENDEVSOLS/Long-Trainer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
viddexa/autollm
Ship RAG based LLM web apps in seconds.
vinhnx/InkChatGPT
Retrieval-augmented generation (RAG) LLM app
ranguy9304/LangGraphRAG
LangGraphRAG: A terminal-based Retrieval-Augmented Generation system using LangGraph. Features...
pacificrm/RAG-Architecture
Multimodal Document Processing RAG with LangChain