NVIDIA NIM

App · 3 actions

Chat with and create embeddings from the open models NVIDIA NIM serves, such as Llama, Mistral and Nemotron.

Actions

ActionWhat it does
Create chat completionSend a conversation to a model and get its reply.
Create embeddingsTurn text into embeddings, for search and comparing meaning.
List modelsList the models you can use.

Create chat completion

Send a conversation to a model and get its reply.

Inputs

ModelmodeltextRequired
Model.
MessagesmessageslistRequired
Messages.
Temperaturetemperaturenumber
Temperature.From 0 to 2.
Top ptop_pnumber
Top p.From 0 to 1.
Max tokensmax_tokensnumber
Max tokens.At least 1.
Seedseednumber
Seed.
Stopstoplist
Stop.

Outputs

dataobject
Response.
next_cursortext
Continuation token, when returned by the service.
Example output
{
  "data": {
    "choices": [],
    "id": "example",
    "model": "example",
    "usage": {
      "completion_tokens": 1,
      "prompt_tokens": 1,
      "total_tokens": 1
    }
  },
  "next_cursor": ""
}

Create embeddings

Turn text into embeddings, for search and comparing meaning.

Inputs

ModelmodeltextRequired
Model.
InputinputlistRequired
Input.
Input typeinput_typetext
Input type.One of: query, passage.
Truncatetruncatetext
Truncate.One of: NONE, START, END.

Outputs

dataobject
Response.
next_cursortext
Continuation token, when returned by the service.
Example output
{
  "data": {
    "data": [],
    "model": "example"
  },
  "next_cursor": ""
}

List models

List the models you can use.

Inputs

None.

Outputs

dataobject
Response.
next_cursortext
Continuation token, when returned by the service.
Example output
{
  "data": {
    "data": []
  },
  "next_cursor": ""
}

On this page