file search tool
A provider-hosted retrieval tool that chunks, embeds and searches your uploaded files for the model, such as OpenAI's file search.
In more detail
It saves building a pipeline but hides chunking and ranking choices, so measure it on your own labelled questions like any retriever. Results come back with citations to the files they came from.
Related terms
- retrieval-augmented generation — Answering a question by first retrieving relevant passages from your own documents and adding them to the prompt, so the model answers from them.
- vector database — A database or extension that stores embedding vectors with their metadata and answers nearest-neighbour queries.
Taught in
- Chunking And Ingestion — AI Engineering: LLM Apps, RAG & Agents
- Grounded Answers With Citations — AI Engineering: LLM Apps, RAG & Agents