Using the Retrieval Endpoint
This guide shows how to access and use the retrieval endpoint for a RAG Pipeline in Vectorize.
Accessing the Retrieval Endpoint
Navigate to the RAG Pipelines section in the Vectorize dashboard.
Click on the name of your desired pipeline (e.g., "friends-scripts").
In the pipeline details view, click the Connect tab.
Retrieval Endpoint Details
In the Connect tab, you'll find:
Access Tokens
Use the "Manage access tokens" button to create or manage authentication tokens.
Retrieval Endpoint URL
The unique URL for your pipeline's retrieval endpoint is displayed here.
Click "Copy to Clipboard" to copy the URL.
Usage Information
The endpoint calculates a vector for the question text and performs a similarity search on the vector DB.
Results are passed to the Cohere reranking model. Relevance scores are included in each response.
Set
rerank
totrue
to order results by the rerank model's relevance score. Otherwise, results are ordered by similarity score.
Using the Endpoint
An example cURL request is provided:
Last updated