You're Invited:Meet the Socket Team at BlackHat and DEF CON in Las Vegas, Aug 7-8.RSVP
Sign inDemoInstall


Package Overview
File Explorer

Advanced tools

Socket logo

Install Socket

Detect and block malicious and high-risk dependencies



All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows



All-in-one embeddings database

Version GitHub last commit GitHub issues Join Slack Build Status Coverage Status

txtai is an all-in-one embeddings database for semantic search, LLM orchestration and language model workflows.


Embeddings databases are a union of vector indexes (sparse and dense), graph networks and relational databases. This enables vector search with SQL, topic modeling, retrieval augmented generation (RAG) and more.

Embeddings databases can stand on their own and/or serve as a powerful knowledge source for large language model (LLM) prompts.

Summary of txtai features:

  • 🔎 Vector search with SQL, object storage, topic modeling, graph analysis and multimodal indexing
  • 📄 Create embeddings for text, documents, audio, images and video
  • 💡 Pipelines powered by language models that run LLM prompts, question-answering, labeling, transcription, translation, summarization and more
  • ↪️️ Workflows to join pipelines together and aggregate business logic. txtai processes can be simple microservices or multi-model workflows.
  • ⚙️ Build with Python or YAML. API bindings available for JavaScript, Java, Rust and Go.
  • ☁️ Run local or scale out with container orchestration

txtai is built with Python 3.8+, Hugging Face Transformers, Sentence Transformers and FastAPI. txtai is open-source under an Apache 2.0 license.

Interested in an easy and secure way to run hosted txtai applications? Then join the preview to learn more.

Why txtai?


New vector databases, LLM frameworks and everything in between are sprouting up daily. Why build with txtai?

# Get started in a couple lines
import txtai

embeddings = txtai.Embeddings()
embeddings.index(["Correct", "Not what we hoped"])"positive", 1)
#[(0, 0.29862046241760254)]
  • Built-in API makes it easy to develop applications using your programming language of choice
# app.yml
    path: sentence-transformers/all-MiniLM-L6-v2
CONFIG=app.yml uvicorn "txtai.api:app"
curl -X GET "http://localhost:8000/search?query=positive"
  • Run local - no need to ship data off to disparate remote services
  • Work with micromodels all the way up to large language models (LLMs)
  • Low footprint - install additional dependencies and scale up when needed
  • Learn by example - notebooks cover all available functionality

Use Cases

The following sections introduce common txtai use cases. A comprehensive set of over 50 example notebooks and applications are also available.

Build semantic/similarity/vector/neural search applications.


Traditional search systems use keywords to find data. Semantic search has an understanding of natural language and identifies results that have the same meaning, not necessarily the same keywords.


Get started with the following examples.

Introducing txtai ▶️Overview of the functionality provided by txtaiOpen In Colab
Similarity search with imagesEmbed images and text into the same space for searchOpen In Colab
Build a QA databaseQuestion matching with semantic searchOpen In Colab
Semantic GraphsExplore topics, data connectivity and run network analysisOpen In Colab

LLM Orchestration

LLM chains, retrieval augmented generation (RAG), chat with your data, pipelines and workflows that interface with large language models (LLMs).


Integrate LLM chains (known as workflows in txtai), multiple LLM agents and self-critique.


See below to learn more.

Prompt templates and task chainsBuild model prompts and connect tasks together with workflowsOpen In Colab
Integrate LLM frameworksIntegrate llama.cpp, LiteLLM and custom generation frameworksOpen In Colab
Build knowledge graphs with LLMsBuild knowledge graphs with LLM-driven entity extractionOpen In Colab
Retrieval augmented generation

Retrieval augmented generation (RAG) reduces the risk of LLM hallucinations by constraining the output with a knowledge base as context. RAG is commonly used to "chat with your data".


A novel feature of txtai is that it can provide both an answer and source citation.

Build RAG pipelines with txtaiGuide on retrieval augmented generation including how to create citationsOpen In Colab
How RAG with txtai worksCreate RAG processes, API services and Docker instancesOpen In Colab
Advanced RAG with graph path traversalGraph path traversal to collect complex sets of data for advanced RAGOpen In Colab
Advanced RAG with guided generationRetrieval Augmented and Guided GenerationOpen In Colab

Language Model Workflows

Language model workflows, also known as semantic workflows, connect language models together to build intelligent applications.


While LLMs are powerful, there are plenty of smaller, more specialized models that work better and faster for specific tasks. This includes models for extractive question-answering, automatic summarization, text-to-speech, transcription and translation.

Run pipeline workflows ▶️Simple yet powerful constructs to efficiently process dataOpen In Colab
Building abstractive text summariesRun abstractive text summarizationOpen In Colab
Transcribe audio to textConvert audio files to textOpen In Colab
Translate text between languagesStreamline machine translation and language detectionOpen In Colab



The easiest way to install is via pip and PyPI

pip install txtai

Python 3.8+ is supported. Using a Python virtual environment is recommended.

See the detailed install instructions for more information covering optional dependencies, environment specific prerequisites, installing from source, conda support and how to run with containers.

Model guide


See the table below for the current recommended models. These models all allow commercial use and offer a blend of speed and performance.

Image CaptionsBLIP
Labels - Zero ShotBART-Large-MNLI
Labels - FixedFine-tune with training pipeline
Large Language Model (LLM)Mistral 7B OpenOrca
Text-to-SpeechESPnet JETS
TranslationOPUS Model Series

Models can be loaded as either a path from the Hugging Face Hub or a local directory. Model paths are optional, defaults are loaded when not specified. For tasks with no recommended model, txtai uses the default models as shown in the Hugging Face Tasks guide.

See the following links to learn more.

Powered by txtai

The following applications are powered by txtai.


txtchatRetrieval Augmented Generation (RAG) powered search
paperaiSemantic search and workflows for medical/scientific papers
codequestionSemantic search for developers
tldrstorySemantic search for headlines and story text

In addition to this list, there are also many other open-source projects, published research and closed proprietary/commercial projects that have built on txtai in production.

Further Reading



Full documentation on txtai including configuration settings for embeddings, pipelines, workflows, API and a FAQ with common questions/issues is available.


For those who would like to contribute to txtai, please see this guide.



Did you know?


Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.


Related posts

SocketSocket SOC 2 Logo


  • Package Alerts
  • Integrations
  • Docs
  • Pricing
  • FAQ
  • Roadmap
  • Changelog


Stay in touch

Get open source security insights delivered straight into your inbox.

  • Terms
  • Privacy
  • Security

Made with ⚡️ by Socket Inc