OpenAI: Embeddings Search

Deprecated

This function is deprecated and can no longer be added to new workflows. Existing workflows using it keep running. Use the generic Embeddings Search function instead.

Vectorize a single search query using OpenAI's embeddings API. Pair with a downstream vector-search node to retrieve relevant documents from a Qdrant / Pinecone collection populated with vectors produced by the same OpenAI model.

For a provider-agnostic version operating on a JSON record see AI::AIEmbeddingsSearch.

Pre-requisite: Install an OpenAI application from Profile > {Organization} > Applications.

Parameters

Applicationrequired

Configured OpenAI application.

Input

JSONrequired

Embeddings search request with model like:

{
   "query": <String>, # Actual text to generate embeddings from.
   "query_vector": [], # Empty before generation
   "filters": [ # Filter for metadata
     {
         "attribute": <String>, # which attribute to filter from
         "value": <String>, # which value matching given attribute to filter from
     }
   ],
   "limit": <Number>, # Own many vector to return from rag database
   "exact": <Bool>, # Whether to exact match on filters of not
}

Output

JSON

Same request with the query_vector field populated ([f32, f32, f32,...]), ready to feed into a vector-search node.