gpt_server是一个用于生产级部署LLMs、Embedding、Reranker、ASR、TTS、文生图、图片编辑和文生视频的开源框架。

All Jina AI APIs as Unix CLI commands. Search, read, embed, rerank - with pipes.

A corporate law RAG system with innovative retrieval and contextual strategies

From Pipeline to Council — A lightweight agentic framework for search & recommendation. 五个 Agent 重构搜广推管线。

Unified LLM API client library for Python. Simple API for Chat, Embedding, Rerank, and Tokenizer. OpenAI-compatible with streaming support and unified usage tracking.

企業内文書向けの Role-aware RAG Platform。権限フィルタ、Excel 仕様書解析、hybrid search/rerank、FastAPI + React に対応。

Langchain integration package with LocalAI. It provides embeddings and reranker support

Automated fact-check

基于 LangGraph 实现的聊天机器人，接入 DeepSeek、Qwen、智谱 AI 多个 LLM 模型，支持在线搜索和文件解析。

Rapid Deployment of LLM and Embedding Based on VLLM Using Docker

🚀 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

A comprehensive RAG FastAPI service that handles document uploads and retrievals, built with Python. Uses PyMuPDF for document processing, turbopuffer for vector storage, OpenAI for models, and cohere for reranking.

🤖 An open-source Agentic RAG framework powered by ReAct Agent ��� LLM autonomously orchestrates hybrid retrieval, deep reading, and web search for traceable, evidence-first Q&A over your documents.

A Python project that deploys a Local RAG chatbot using Ollama API and vLLM API. Refines answers with internal RAG knowledge base, using both Embedding and Rerank models to improve accuracy of context provided to LLM models.

Multilingual Lightweight & High-Performance Hybrid Search Engine | Built for RAG

基于 BGE (BAAI General Embedding) Reranker 模型构建的高性能文本重排序服务，使用 FastAPI 提供 RESTful 接口，支持 ONNX 模型的推理加速。

基于《倚天屠龙记》的 RAG 智能问答系统示例：集成查询重写、BGE-Reranker 与 Gemini 3.1，支持多轮对话与页码溯源的深度武侠百科。

Корпоративный ИИ-Ассистент (On-Premise RAG): локальный поиск по базе знаний на Open-Source LLM (Ollama/Qwen2.5 + e5 + Chroma + BM25/RRF), KZ/RU, цитаты. Прототип под тех-задачу Petrel AI (Astana Hub).

Made a simple RAG evaluation system to learn about chunks, top K, rerank and how it affects latency

StatsRerank. Mod A = tvrdi statistički filter.