shlogg · Early preview
David Mezzetti @davidmezzetti

Generating Text With Graph Path Traversal And LLMs In Txtai

Generate short book on early medieval England using txtai: traverse Wikipedia graph, retrieve related articles & use Relevance-Aware Generator (RAG) to create content.

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 (RAG) and more.
A standard RAG process typically runs a single vector search query and returns the closest matches. Those matches are then passed into a LLM prompt and used to limit the context and help ensure more factually correct answers are generated. This works well with most simple cas...