RCGAI/SimplyRetrieve
Lightweight chat AI platform featuring custom knowledge, open-source LLMs, prompt-engineering, retrieval analysis. Highly customizable. For Retrieval-Centric & Retrieval-Augmented Generation.
Built on Hugging Face, Gradio, PyTorch, and FAISS, it separates knowledge memorization (via vector retrieval with multilingual-e5-base embeddings) from context interpretation (using configurable open-source LLMs like Wizard-Vicuna), enabling efficient single-GPU deployment with multi-user concurrent access. The platform provides both GUI and REST API interfaces with on-the-fly knowledge base construction from multiple document formats (PDF, DOCX, HTML, etc.) and retrieval tuning through prompt engineering and analysis tools.
218 stars. No commits in the last 6 months.
Stars
218
Forks
14
Language
Python
License
MIT
Category
Last pushed
Feb 14, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/RCGAI/SimplyRetrieve"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
chatchat-space/Langchain-Chatchat
Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用...
Azure-Samples/azure-openai-rag-workshop
Create your own ChatGPT with Retrieval-Augmented-Generation workshop
byu-cpe/Maeser
A package for building RAG chatbot applications for educational contexts.
avrabyt/RAG-Chatbot
RAG enabled Chatbots using LangChain and Databutton
Storia-AI/sage
Chat with any codebase in under two minutes | Fully local or via third-party APIs