txtai
ActiveDescription
All-in-one AI framework for semantic search, LLM orchestration, and language model workflows with agent support, RAG, and vector database
Key Features
- All-in-one AI framework for semantic search, LLM orchestration, and workflows
- Embeddings database combining vector indexes, graph networks, and relational DBs
- Multimodal embeddings for text, documents, audio, images, and video
- Autonomous agents connecting embeddings, pipelines, and workflows
- Web API and MCP API with bindings for JavaScript, Java, Rust, and Go
- pip install and ready to go with sensible defaults
Use Cases
💡 Semantic search and similarity retrieval applications
💡 Retrieval-augmented generation (RAG) systems
💡 Multi-model workflow and pipeline orchestration
💡 Knowledge graphs and semantic graph analysis
💡 Document Q&A and automatic labeling
Strengths & Limitations
✅ Strengths
- • Actively maintained, recent updates
- • High community interest (12.9k stars)
- • Permissive open-source license (Apache-2.0)
- • Responsive to issues, low backlog
Categories
Quick Start
Install with pip install txtai, then create an embeddings index in a few lines: import txtai; embeddings = txtai.Embeddings(); embeddings.index(["text1", "text2"]); embeddings.search("query", 1). Or start the API with a YAML config.