txtai is an all-in-one embeddings database for semantic search, LLM orchestration and language model workflows. Embeddings databases enable vector search over text, documents, audio, images and video. Workflows integrate large language model (LLM) prompt chains, summarization, transcription, translation and more to build intelligent applications.

txtai provides the following features.

• 🔎 Vector search with SQL
• 💡 Pipelines powered by language models
• ↪️️ Workflows to join pipelines together and aggregate business logic
• ☁️ Run local or scale out with container orchestration

Want us to host your txtai applications? Then join the txtai.cloud preview to learn more.

Semantic search is a new category of search built on recent advances in Natural Language Processing (NLP). Large-scale general language models have rapidly pushed the field forward in ways unimaginable only a few years ago. This article gives a brief overview of semantic search and how it contrasts with keyword search.

txtchat is a framework for building retrieval augmented generation (RAG) powered search applications. A set of intelligent agents are available to integrate with messaging platforms. This article gives an introduction to how txtchat works.