Scripts2026年4月1日·1 分钟阅读

txtai — All-in-One Embeddings Database

txtai is an all-in-one embeddings database for semantic search, LLM orchestration, and language model workflows. 10.4K+ GitHub stars. Vector search + SQL + RAG pipelines. Apache 2.0.

TO
TokRepo精选 · Community
快速使用

先拿来用,再决定要不要深挖

这里应该同时让用户和 Agent 知道第一步该复制什么、安装什么、落到哪里。

# Install
pip install txtai

# Semantic search in 3 lines
python -c "
from txtai import Embeddings
embeddings = Embeddings()
embeddings.index(['AI is transforming search', 'Vector databases are fast', 'Python is great for ML'])
results = embeddings.search('machine learning', 1)
print(results)  # [(2, 0.85)]
"

介绍

txtai is an all-in-one embeddings database combining semantic search, LLM orchestration, and language model workflows in a single library. With 10,400+ GitHub stars and Apache 2.0 license, txtai provides vector search with SQL support, RAG pipelines, extractive QA, labeling, transcription, translation, summarization, and workflow automation. It supports local and cloud LLMs, and can be deployed as an API server. txtai is designed to be the simplest way to build semantic search and AI-powered applications.

Best for: Developers who want semantic search + LLM pipelines in one lightweight library Works with: Claude Code, OpenAI Codex, Cursor, Gemini CLI, Windsurf Features: Vector search, SQL, RAG, QA, translation, summarization


Key Features

  • Embeddings database: Vector search with SQL query support
  • RAG pipelines: Retrieval-augmented generation out of the box
  • LLM orchestration: Chain multiple AI models in workflows
  • Extractive QA: Answer questions from documents
  • Translation + summarization: Built-in NLP pipelines
  • API server: Deploy as a REST API with one command
  • Local + cloud: Works with local models and cloud providers

FAQ

Q: What is txtai? A: txtai is an all-in-one embeddings database with 10.4K+ stars for semantic search, RAG, and LLM workflows. Vector search + SQL + NLP pipelines in one library. Apache 2.0.

Q: How do I install txtai? A: Run pip install txtai. Create an Embeddings() instance, index() your data, and search() semantically.


🙏

来源与感谢

Created by NeuML. Licensed under Apache 2.0. neuml/txtai — 10,400+ GitHub stars

相关资产