andreasjansson/flag-embedding

andreasjansson / flag-embedding

Public
19 runs

Run andreasjansson/flag-embedding 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
prompts	string		List of prompts, separated by prompt_separator. Maximum 100 prompts per prediction.
prompt_separator	string		Separator between prompts
short_queries_for_long_passages	boolean	False	Set this to true if you are providing short queries to match long passages. This will prefix all prompts with 'Represent this sentence for searching relevant passages: '

{
  "type": "object",
  "title": "Input",
  "required": [
    "prompts"
  ],
  "properties": {
    "prompts": {
      "type": "string",
      "title": "Prompts",
      "x-order": 0,
      "description": "List of prompts, separated by prompt_separator. Maximum 100 prompts per prediction."
    },
    "prompt_separator": {
      "type": "string",
      "title": "Prompt Separator",
      "default": "\n\n",
      "x-order": 1,
      "description": "Separator between prompts"
    },
    "short_queries_for_long_passages": {
      "type": "boolean",
      "title": "Short Queries For Long Passages",
      "default": false,
      "x-order": 2,
      "description": "Set this to true if you are providing short queries to match long passages. This will prefix all prompts with 'Represent this sentence for searching relevant passages: '"
    }
  }
}

Output schema

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

Schema

{
  "type": "array",
  "items": {
    "type": "array",
    "items": {
      "type": "number"
    }
  },
  "title": "Output"
}