Rerank documents
You can use the Inference API rerank endpoint to rerank documents, such as text passages, according to their relevance to a query.
To run through this guide in your browser, see the Rerank example notebook.
Before you begin
Ensure you have the following:
1. Install an SDK
You can access the rerank endpoint directly or use the latest Python, Node.js, Go, or Java SDK.
To install the latest SDK version, run the following command:
If you already have an SDK, upgrade to the latest version as follows:
2. Choose a model
Choose a reranking model hosted by Pinecone or an externally hosted reranking model.
3. Rerank documents
To rerank documents, use the inference.rerank operation. Specify a supported reranking model, and provide documents and a query as well as other model-specific parameters.
For example, the following request uses the bge-reranker-v2-m3 model to rerank the values of the documents.text field based on their relevance to the query, "The tech company Apple is known for its innovative products like the iPhone.".
With truncate set to "END", the input sequence (query + document) is truncated at the token limit (1024); to return an error instead, you’d set truncate to "NONE" or leave the parameter out.
The returned object contains documents with relevance scores:
Normalized between 0 and 1, the score represents the relevance of a passage to the query, with scores closer to 1 indicating higher relevance.
Rerank documents on a custom field
To rerank documents on a field other than documents.text, use the inference.rerank endpoint, and provide the rank_fields parameter to specify the fields on which to rerank.
For example, the following request reranks documents based on the values of the documents.my_field field:
Was this page helpful?