ONNX implementation of the BGE-M3 multilingual embedding model and tokenizer with native C#, Java, and Python implementations. Generates all three embedding types: dense, sparse, and ColBERT vectors.

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

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

Semantic media search with Qwen2.5-VL + bge-m3 embeddings and pgvector

Hybrid RAG system for translating Ancient Egyptian transliterations using the TLA dataset.

Example application for using the BGE-M3 embedding model and Google's Gemma-2-9B-Instruct generation model in a LangChain-based RAG pipeline to answer Lord of the Rings trivia questions

🚀 企业级私有化 RAG 知识库系统 | 💯 纯离线部署、无需联网 | 🔐 支持 LDAP/AD 统一认证与 RBAC 部门级权限隔离 | ⚡️ 基于 LlamaIndex + Ollama + BGE-M3/Rerank | 📝 支持多格式文档解析、上下文对话记忆及精准的 PDF 原文溯源高亮 | 📊 内置数据可视化仪表盘（🚀 Enterprise RAG Knowledge Base. 💯 Fully offline/air-gapped deployment. 🔐 Features LDAP/AD integration, RBAC & Department Isolation. ⚡️ Powered by LlamaIndex, Ollama, and Local R

This is a FastAPI-based service for generating text embeddings, supporting multiple architectures like intfloat/multilingual-e5-large and BAAI/bge-m3. It automatically configures prefixes and sequence lengths based on the selected model. It supports both single text and batch processing.

Asistente RAG que ingiere la carpeta de proyectos local, construye un índice en ChromaDB con embeddings avanzados BGE‑M3 y responde preguntas a través de un LLM DeepSeek.

Train a pooling Head for Dense Embeddings

Chinese Fake News Detection based on MacBERT

An intelligent Retrieval-Augmented Generation (RAG) system that helps students find answers within video lectures using semantic search and LLMs (Ollama/GPT). Automatically extracts subtitles, generates embeddings, retrieves relevant clips, and provides context-aware answers with timestamps.

Smart Berlin assistant cutting through bureaucracy with AI powered answers and personalized help.

Hybrid RAG for Thai ROV patch notes: normalize diffs → hybrid retrieve (BM25 + dense in Chroma, MMR, optional bge reranker) → citation-first answers via FastAPI with OpenAI/Ollama generators. | ระบบ RAG ภาษาไทยสำหรับแพตช์โน้ต ROV

Herramientas para procesar datos de desaparecidos: anonimización de narrativas con IA. Búsqueda semántica de casos similares mediante embeddings de texto (BGE-M3).

EasyRag shows you how to embed and query table documents from your own local LLM using a DiT

Telegram chatbot FAQ untuk membantu mahasiswa Universitas Lampung mengakses informasi Siakadu menggunakan semantic search (BGE-M3 + FAISS).

Multimodal Answer Engine generates answers with images and text. Uses only open source models with vllm inferencing with eagle speculative decoding.