Question Answering
Generative question-answering on your collection.
Generative QA returns relevant answers to the user input question.
Under the hood, we perform vector search and reranking on the input collection to retrieve the most relevant results, then use the results to generate an answer.
The collection to query.
The question from the user
The fields that you want the generation to be based on.
The fields that you want to be returned as reference. If not specified, it returns all fields as reference.
The conversation ID. This is returned in the response so you can use the one that has been automatically generated for you or you can also supply your own to keep track of the conversation on your side.
The minimum score.
If true
then there will be a moderation layer applied after the user inputs
a query and when the AI outputs to ensure that the generated content is not
harmful or violent.
The max number of documents to returned
Whether or not a stream response should be returned. See examples below for details.
Requires JSON Content Type