neuml/txtai

💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows

What it solves

txtai is an all-in-one AI framework designed to simplify the creation of semantic search, LLM orchestration, and language model workflows. It eliminates the need to piece together disparate remote services by providing a unified foundation for vector search and knowledge sources for LLM applications.

How it works

The framework is built around an embeddings database that combines vector indexes (both sparse and dense), graph networks, and relational databases. This foundation supports several key components:

  • Pipelines: Language model-powered processes for tasks like question-answering, transcription, translation, and summarization.
  • Workflows: Systems that join pipelines together to aggregate business logic into microservices or multi-model workflows.
  • Agents: Autonomous entities built on the smolagents framework that connect embeddings, pipelines, and workflows to solve complex problems.
  • Embeddings: Support for creating embeddings for text, documents, audio, images, and video.

Who it’s for

Developers looking to build AI applications such as semantic search engines, RAG (Retrieval Augmented Generation) systems, and autonomous agents without needing to manage multiple separate AI tools and databases.

Highlights

  • Multimodal Indexing: Supports vector search across text, audio, images, and video.
  • RAG Support: Built-in capabilities for Retrieval Augmented Generation to reduce LLM hallucinations.
  • Extensible API: Provides Web and Model Context Protocol (MCP) APIs with bindings for JavaScript, Java, Rust, and Go.
  • Local Execution: Ability to run locally to avoid shipping data to remote services.
  • Broad Model Compatibility: Works with Hugging Face Transformers, Sentence Transformers, and integrates with llama.cpp and LiteLLM.

Related

  • Project
    i-am-bee/beeai-framework

    A comprehensive toolkit for building production-ready autonomous agents and multi-agent systems in Python and TypeScript, featuring integrated RAG, memory, and multi-LLM support.

  • Project
    tryAGI/LangChain

    A C# implementation of the LangChain framework that enables .NET developers to build composable AI applications using LLMs, vector databases, and document loaders.

  • Project
    infiniflow/infinity

    An AI-native database providing high-speed hybrid search across dense and sparse embeddings, tensors, and full-text for LLM and RAG applications.

  • Project
    Abraxas-365/langchain-rust

    langchain-rust is a Rust implementation of LangChain, providing a framework for building LLM-powered applications with composable chains, agents, memory, document loaders, and integrations with many LLMs, embedding models, and vector stores.

  • Project
    SomeOddCodeGuy/WilmerAI

    A node-based workflow engine for advanced semantic prompt routing and multi-LLM orchestration, allowing users to create complex, context-aware AI agents.