What’s New in txtai 5.0

Semantic graph, external integrations and more

txtai is an open-source platform for semantic search and workflows powered by language models.

The following articles have previously covered txtai.

Introducing txtai, an AI-powered search engine built on Transformers

Run machine-learning workflows to transform data and build AI-powered text indices with txtai

Semantic search on the cheap

What’s New in txtai 4.0

Serverless Vector Search with txtai

Insights from the txtai console

txtai 5.0 brings a number of major feature enhancements, most importantly the semantic graph. This article will cover all the changes.

Semantic Graph

Semantic graphs, also known as knowledge graphs or semantic networks, build a graph network with semantic relationships connecting the nodes. In txtai, they can take advantage of the relationships inherently learned within an embeddings index. This opens exciting possibilities for exploring relationships, such as topics and interconnections in a dataset.

Semantic graphs in txtai can be used for topic modeling, graph traversal and analysis. Check out the following links for more.

Introducing the Semantic Graph

Google Colaboratory

External integrations

Want to run Weaviate as your txtai vector database, PostgreSQL for database storage and Neo4j for graphs? 5.0 makes it easier to integrate external vector engines, databases and graph stores.

Check out the following links to explore how modular embeddings index components can be connected together.

Embeddings index components

Google Colaboratory

Wrapping up

This article gave a quick overview of txtai 5.0. There are also a number of improvements and bug fixes. See the following links for more information.

• 5.0 Release on GitHub
• Documentation site
• Tutorial series on Hashnode | dev.to | Notebooks
• Newsletter