| openai_file_search_tool | R Documentation |
Configure the Responses API's hosted RAG over one or more vector stores you've uploaded to OpenAI.
openai_file_search_tool(
vector_store_ids,
max_num_results = NULL,
ranking_options = NULL
)
vector_store_ids |
Character vector of vector-store IDs to search. Required, non-empty. |
max_num_results |
Optional integer cap on how many chunks the model sees per call. |
ranking_options |
Optional named list for advanced ranking config
(e.g. |
A plain list ready to drop into tools = list(...).
## Not run:
generate_text(
model,
"What does the design doc say about caching?",
tools = list(openai_file_search_tool(c("vs_abc123")))
)
## End(Not run)
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.