Fidx – Local semantic search in one SQLite file, no LLM at query
Fidx is a local semantic search engine that combines BM25 full-text search with 768-dimensional vector embeddings, all stored in a single SQLite file. It requires no LLM calls during queries, only a single ONNX embedding pass, enabling millisecond-class queries on CPU. It can be used as a CLI, a private RAG retriever, or the search layer behind agent memory.
Fidx – Local semantic search in one SQLite file, no LLM at query
Report an error
The correction channel is not available yet. You can copy the article reference below for later.
Correction instructionsSummary only
Under the source content permission, this page provides an editorial summary, key points, and a link to the original article.