RustyRAG is a production-grade RAG (Retrieval-Augmented Generation) API server written in Rust, designed for sub-200ms time-to-first-token. It provides a complete pipeline: document ingestion (PDF, DOCX, PPTX, XLSX, HTML, TXT, ZIP) via Docling with layout-aware extraction, OCR, table recognition, and optional vision-model image descriptions; hybrid search using Milvus (dense HNSW vectors + BM25 sparse with Reciprocal Rank Fusion); cross-encoder reranking via Jina Reranker v3; and streaming LLM responses from Groq or Cerebras. The server exposes REST endpoints for document upload, semantic search, RAG chat (both full response and SSE streaming), collection backup, and an evaluation benchmark runner. The architecture follows a clean layered pattern: Actix-web handlers in `src/handlers/` orchestrate business logic, services in `src/services/` encapsulate external API clients (Milvus, embeddings, reranker, Docling, LLM), and schemas in `src/schemas/` define request/response types with OpenAPI annotations via utoipa. The Rust binary is a single self-contained server; GPU-accelerated sidecars (embeddings, reranker, Docling) run as Docker containers. Configuration is environment-driven with sensible defaults. Key entry points are the HTTP API at `/api/v1/` (Swagger UI at `/swagger-ui/`) and a built-in chat UI at `/static/chat.html`. The primary data flow for a RAG query is: embed user query β fire concurrent dense and BM25 searches in Milvus β merge via RRF β rerank top candidates β build context prompt β stream LLM response with source citations and timing metadata. The system is designed for low latency and high accuracy, with benchmark results showing 94.5% pass rate with reranker at ~279ms TTFT.
Milvus Java SDK is a comprehensive client library for the Milvus vector database, supporting both legacy (v1) and modern (v2) APIs. It covers all core operations: collection/index/partition management, vector insert/upsert/delete/search/query, RBAC, resource groups, CDC, snapshots, and bulk import via Parquet/CSV/JSON files. The SDK uses gRPC for communication, includes connection pooling, schema caching, and iterator support for large result sets. A separate bulk writer module handles cloud storage uploads (S3, Azure, GCP) and import job orchestration. The codebase is professionally structured with a builder pattern for all request/response objects, extensive unit and integration tests, and examples demonstrating real-world usage. While dual API versions increase maintenance, the SDK is actively developed with a rapid release cadence aligned to Milvus server versions.
This repository is a comprehensive Chinese-language educational tutorial and codebase for Retrieval-Augmented Generation (RAG) systems, created by Datawhale. It systematically covers the full RAG stack from fundamentals (data loading, chunking, embeddings) to advanced techniques (hybrid search, query construction, Text2SQL, reranking, agentic RAG, and Graph RAG). The code is organized by chapter, with runnable Python scripts demonstrating each concept using popular frameworks like LangChain, LlamaIndex, and LangGraph, alongside vector databases (Milvus, FAISS) and graph databases (Neo4j). While primarily an educational resource, the repository contains several well-crafted, reusable components such as a minimal Text2SQL agent framework, a clean LangGraph-based agentic RAG pattern, and a custom ColBERT reranker. The practical application is a Chinese recipe Q&A system ('ε°ε°εΈζ·‘'), which serves as a consistent domain for demonstrating various RAG techniques. The codebase is hybrid in nature, blending structured educational content with functional demo applications. The repository is actively maintained with a large community following. However, users should be aware of technical drift risks including vendored model code, hardcoded API dependencies, and the presence of AI-generated code sections. The core value lies in its structured curriculum and reusable RAG patterns rather than as a production-ready system.
This repository implements a full-stack AI-powered food recommendation application called 'δ»ε€©εδ»δΉ' (What to eat today). The system combines a Next.js frontend with a Python Flask backend that uses a GraphRAG (Retrieval-Augmented Generation) architecture leveraging Neo4j for graph-based recipe relationships and Milvus for vector similarity search. Users interact via a chat interface to receive personalized recipe recommendations with step-by-step cooking instructions. The application includes a comprehensive recipe knowledge base in markdown format, Docker-based deployment orchestration, and a modular RAG pipeline with intelligent query routing and session management.
This repository is the central index and deployment configuration for the trace.moe anime scene search engine. It contains no application code; the actual functionality is implemented in separate repositories (trace.moe-api, trace.moe-www, etc.). The primary artifact is a Docker Compose file that orchestrates the entire stack, including PostgreSQL, Milvus vector database, and the API server. This repo is useful for operators who want to deploy the trace.moe system, but developers looking for reusable code should look at the sub-repositories. The documentation provides clear, step-by-step deployment instructions. The system itself is an image-based scene search service that uses vector similarity search to identify anime scenes from screenshots.