Build knowledge graphs with LLM-driven entity extraction

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 and more.

Up until txtai 7.0, semantic graphs only supported automatic relationship detection. Now relationships can be loaded directly into a txtai database. This article will demonstrate how to work with this new feature.

Install txtai …

build database databases embeddings extraction graph graphs knowledge knowledge graphs language language model llm machinelearning modeling networks nlp orchestration python relational relational databases retrieval retrieval augmented generation search semantic sql topic modeling union vector vector search workflows