onlinepage/cogagent-chat

Public

44 runs

Run onlinepage/cogagent-chat with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

Input schema

The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.

Field	Type	Default value	Description
query	string	Describe this image.	Input query.
image	string		Input image.
history	string	[]	Input chat history in array [] string , format [(query,response)..]
max_length	integer	2048	max output length
temperature	number	0.9	temperature for the output.
top_p	number	0.8	top p for the VLM output.
use_cache	boolean	False	Whether to use cache for output or not (based on the transformers use_cache param)
do_sample	boolean	False	general transformer param do_sample.

{
  "type": "object",
  "title": "Input",
  "required": [
    "image"
  ],
  "properties": {
    "image": {
      "type": "string",
      "title": "Image",
      "format": "uri",
      "x-order": 1,
      "description": "Input image."
    },
    "query": {
      "type": "string",
      "title": "Query",
      "default": "Describe this image.",
      "x-order": 0,
      "description": "Input query."
    },
    "top_p": {
      "type": "number",
      "title": "Top P",
      "default": 0.8,
      "x-order": 5,
      "description": "top p for the VLM output."
    },
    "history": {
      "type": "string",
      "title": "History",
      "default": "[]",
      "x-order": 2,
      "description": "Input chat history in array [] string , format [(query,response)..]"
    },
    "do_sample": {
      "type": "boolean",
      "title": "Do Sample",
      "default": false,
      "x-order": 7,
      "description": "general transformer param do_sample."
    },
    "use_cache": {
      "type": "boolean",
      "title": "Use Cache",
      "default": false,
      "x-order": 6,
      "description": "Whether to use cache for output or not (based on the transformers use_cache param)"
    },
    "max_length": {
      "type": "integer",
      "title": "Max Length",
      "default": 2048,
      "x-order": 3,
      "description": "max output length"
    },
    "temperature": {
      "type": "number",
      "title": "Temperature",
      "default": 0.9,
      "x-order": 4,
      "description": "temperature for the output."
    }
  }
}

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema

{
  "type": "string",
  "title": "Output"
}