txtai
Createdneuml
Enables semantic search, LLM orchestration, and language model workflows with an all-in-one embeddings database.
About
txtai is a versatile, open-source embeddings database designed to streamline semantic search and empower language model workflows. Functioning as a unified platform, it merges vector indexes, graph networks, and relational databases, providing a robust foundation for vector search and serving as a potent knowledge source for Large Language Model (LLM) applications. It allows users to construct autonomous agents, retrieval augmented generation (RAG) processes, and multi-model workflows, scaling from local operations to container orchestration with ease.
Key Features
- Pipelines powered by language models that run LLM prompts, question-answering, labeling, transcription, translation, summarization and more
- 10,724 GitHub stars
- Create embeddings for text, documents, audio, images and video
- Agents that intelligently connect embeddings, pipelines, workflows and other agents together to autonomously solve complex problems
- Vector search with SQL, object storage, topic modeling, graph analysis and multimodal indexing
- Workflows to join pipelines together and aggregate business logic
Use Cases
- Build semantic search applications
- LLM orchestration
- Language model workflows
