automation

txtai: Automate Search

Get AI-powered semantic search with txtai, a framework.
intermediateโฑ 30 minutes๐Ÿ’ต Free tier + paid plans
12,909 stars884 forksPythonGuide quality 8/10Updated 8/27/2026100% free ยท open source
What it is

Use a pre-made AI framework to power your website or app with search capabilities.

Real use case example

"A founder of a small e-commerce site wants to let customers easily find products with a visually appealing description. They use this framework to integrate an AI-powered search bar, which saves them around 2 days of development time. The search bar goes live in a week."

When to use it
  • โ€ขBuilding a custom knowledge base search for your startup's documentation
  • โ€ขCreating an AI assistant that can understand context across your company's data
  • โ€ขAutomating information retrieval and summarization from large text collections
Ready-to-paste prompt
from txtai import Embeddings

embeddings = Embeddings({'path': 'sentence-transformers/all-MiniLM-L6-v2'})
embeddings.index([(0, 'first document'), (1, 'second document')])
results = embeddings.search('find documents about X', limit=3)
Saves to your device
Use with Claude
New

Skip the builder โ€” one click puts this in Claude, Cursor, Antigravity and more.

๐Ÿ› ๏ธ Technical setup

Expect 20โ€“40 minutes in a terminal โ€” or let your AI agent drive it.

Try it instantly โ€” no install
Claude Code
mkdir -p ~/.claude/skills/txtai && curl -fsSL https://workflowstacks.com/api/skills/txtai/claude-skill -o ~/.claude/skills/txtai/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go โ€” no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How txtai: Automate Search works
Codeflow
Free to inspect

Txtai: Automate Search is a large Python project (~28k lines across 287 code files, plus 97 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Apache-2.0 license, has a test suite.

Size
Large codebase
~28k lines ยท 287 code files ยท ~4 h to skim
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Python
No API keys detected
Python 100%
Where to start reading
  1. 1
    README.md
    Start here โ€” what it does and how to install it
  2. 2
    pyproject.toml
    Dependencies and the commands it exposes
  3. 3
    src/python/txtai/__init__.py
    Inside src/ โ€” the main logic begins here
  4. 4
    examples/01_Introducing_txtai.ipynb
    A worked example โ€” copy this to get going
What's in each folder
src/Core code โ€” the actual logic273 files
docs/Documentation142 files
examples/Examples you can copy96 files
docker/Deployment / infrastructure8 files
test/Tests โ€” proof it works97 files
.github/CI / automation (GitHub Actions)3 files
READMEHas testsDocumentedCI checksExamples includedApache-2.0 licenseUpdated this month
Quick Actions
Details
Creator
neuml
Language
Python
Category
automation
Published
8/9/2020

Are you the creator of this tool? Claim your listing โ†’ and earn 85% of every sale.