txtai

txtai

txtai is an all-in-one open-source embedding database that powers semantic search, LLM orchestration, and language model workflows. It combines a vector store, sparse retrieval, RAG pipelines, and workflow automation into a single lightweight library with minimal dependencies.

Key Features

• Embeddings database: vector + keyword hybrid search in a single index
• RAG pipelines: retrieval-augmented generation with any LLM (OpenAI, Hugging Face, Ollama)
• LLM workflows: chain extractors, summaries, translations, classifiers, and custom steps
• Graph networks: build knowledge graphs from document collections
• Multimodal: text, image, audio, video embeddings
• API server: YAML-config-driven REST API, no code needed

Quick Start

from txtai import Embeddings

embeddings = Embeddings(path="sentence-transformers/nli-mpnet-base-v2")
embeddings.index(["US tops all nations in gold medals",
                   "Weightlifting athlete sets new record"])

result = embeddings.search("athletic performance")
print(result)  # [(0, 0.75), (1, 0.63)]

Install via ai-supply

npx ai-supply add txtai-semantic-search-pipeline

Curated mirror of the open-source txtai (Apache-2.0). Get it from the source.