Embeddings Pair
A 3-step recipe with Hugging Face. We can help you get access.
Recipe · 3 steps
Embeddings Pair
with Hugging Face · Artificial Intelligence Management
Embed a query and a document with the same model for similarity comparison.
- List the models available through the router to confirm the requested embedding model can be served before embedding.
- Create an embedding vector for the query text using the requested model.
- Create an embedding vector for the document text using the same model so it can be compared to the query vector.
What you'll need to have ready
- hfToken: Hugging Face access token used as a Bearer credential.
- modelId: The embedding model id to use.
- query: The query text to embed.
- document: The document text to embed for comparison against the query.
For your developer
Arazzo workflow hugging-face:embeddings-pair, 3 operations: getV1Models → createEmbeddings → createEmbeddings. Specs on APIs.io.