API Reference

Rank passages by their relation to a query.

post
https://ai.api.nvidia.com/v1/retrieval/nvidia/llama-nemotron-rerank-vl-1b-v2/reranking

Order a list of passages by their relation to a query.

Note that if a given query + passage pair is longer than the ranking model's context window,
it will be automatically truncated.

Body Params
string
required
Defaults to nvidia/llama-nemotron-rerank-vl-1b-v2

The model to use for ranking.

query
object
required

The query to rank the passages against.

passages
array of objects
required
length between 1 and 1000

The list of passages to rank.

Passages*
string
required
length between 1 and 14598366
string

Optional image as a base64-encoded data URL (e.g. data:image/jpeg;base64,...).

string
enum
Defaults to END

How to truncate the input if it's too long for the model.

Allowed:
Responses

Updated 3 days ago

Language
Credentials
Bearer
Response 
Click Try It! to start a request and see the response here! Or choose an example:
application/json
Updated 3 days ago 




































country_code