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.

Self-hosted Chinese personal memory graph. Six sources, two LLMs, one graph.

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

Self-hosted intent radar — Reverse RAG for any input stream.

Event-driven desktop AI agent: YAML scenarios, plugin system with UI contributions, local RAG (BGE-M3 + Qdrant), LLM routing. Electron + React + Python.

Local-first semantic cache for AI agents. A small C daemon + CLI that remembers what your agent learned across sessions. Plugs into Claude Code, Codex, Gemini CLI, and Claude Desktop / ChatGPT via MCP. No LLM calls, no SaaS, no API key.

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

Optimised BAAI/bge-m3 serving with dense + sparse + ColBERT embeddings, async dynamic batching and pipeline GPU inference

🚀 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

Local SQL archive for your Super Whisper dictation history. Thin sqlite3 wrapper + multilingual semantic search via bge-m3 / Ollama. macOS, distributed via Homebrew.

AI real-estate automation platform: Telegram bot, RAG, apartment search, CRM workflows, voice agent, Langfuse observability, and Dockerized AI runtime.

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

Complete Workspace Template for OpenClaw - Full agent lifecycle with unified memory system (Markdown + SQLite), self-evolution, RAG. Not for SubAgent/Skill use.

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

Selective web content extraction for AI agents — URL + query returns only the chunks that matter (Python library + MCP server)

Multi-agent memory substrate for PostgreSQL — provenance-gated, vector-hybrid recall

RAG for researchers: page-level citations from your personal library, LLM access via MCP. Ask your entire archive, get answers with the intelligence of leading AI.

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

12-week lab-driven curriculum: cloud/infra engineer → AI Agent/LLM engineer. Local-first MLX stack, measured engineering, every claim grounded in a runnable RESULTS.md.

Axum HTTP server serving BGE-M3 dense and sparse embeddings via ONNX Runtime