01Utilizes pgvector backend for efficient storage and retrieval of vector embeddings.
02Flexible embedding providers: Ollama (local), HuggingFace ONNX (local fallback), OpenAI, Google Gemini, and Voyage AI.
03Optimized local embedding inference with hardware acceleration for Apple Silicon and NVIDIA GPUs, offering significant speedups.
04Seamless integration with popular AI clients including Claude Desktop, Claude Code, Cursor, and VS Code.
051 GitHub stars
06RAG-based semantic search over comprehensive WSO2 documentation (API Manager, Micro Integrator, Choreo, Ballerina, BI, Library).