Popular GitHub Repositories for Bge

Easy-to-Use RAG Framework; CCF AIOps International Challenge 2024 Top3 Solution; CCF AIOps 国际挑战赛 2024 季军方案

一种利用Langchain框架和本地向量库实现的对话式BI，它的目标是帮助用户寻找、理解数据知识，并能够分析数据、洞察结果，通过自然语言对话，降低数据分析的门槛。

Embeddings from sentence-transformers in Android! Supports all-MiniLM-L6-V2, bge-small-en, snowflake-arctic models and more

A demonstration of hybrid search with reranking using Qdrant and the BGE-M3 model. A showcase of dense and sparse retrieval combined with ColBERT reranking for optimal search results

RAG Based LLM Chatbot Built using Open Source Stack (Llama 3.2 Model, BGE Embeddings, and Qdrant running locally within a Docker Container)

Code associated with the blog post titled, "Fine-Tuning BGE Embeddings Using Synthetic Data from Amazon Bedrock"

LLM API Server , OpenAI 同时支持 ChatGLM3 ，Llama, Llama-3, Firefunction, Openfunctions ，BAAI/bge-m3 ,bge-large-zh-v1.5

Self-hostable pay for what you use embedding server for bge-large-en and arbitrary embedding models using crypto

A RAG system build with LangChain and Ollma. Llama 3.2 as generator and BGE as embedding model.

An AI based chatbot built for SaaS Entrepreneurs

A full-stack chatbot platform that utilizes dual-path Retrieval-Augmented Generation (RAG) for personalized medical Q&A. Built with a FastAPI backend, with both local and online LLM support and a modern Vite-based frontend (Vue). Uses FAISS and BGE embeddings for semantic search over mock user health records and a medical knowledge base.

Adaptive RAG (Web search + Corrective RAG) is an upgraded model of Agentic RAG

ONNX implementation of the BGE-M3 multilingual embedding model and tokenizer. Generates all three embedding types: dense vectors, sparse weights, and ColBERT vectors

The Q&A system uses LangChain and wechat mini program as support

Creating a insurance query engine using docker,qdrant vector similarity serch engine,and BAAI/bge-base-en-v1.5 model from hugging face

Build your own Custom RAG Chatbot using Gradio, Langchain and ChatGPT

Chitti is a retrieval-augmented-generation (RAG) application which utilizes a Mistral Large Language Model (LLM) for generation and a bge-m3 model developed by BAAI for retrieval. Chitti can help you answer questions about the IoT Summer Program, Projects in the program curriculum, Innovations of AIoT SMART Labs, Certification process and more!

ProfessorAI is an application that allows professors to upload course material into the platform, which in turn, learns and indexes all the information. Subsequently, students can use a chat application to ask the model any question pertaining to the course material.

RAG using Mistral 7B, llama-index and bge embeddings