Skip to content
Cloudflare Docs
b

bge-m3

Text Embeddings • baai
@cf/baai/bge-m3

Multi-Functionality, Multi-Linguality, and Multi-Granularity embeddings model.

Model Info
Pricing$0.012 per M input tokens

Usage

Workers - TypeScript

 
export interface Env {
  AI: Ai;
}


export default {
  async fetch(request, env): Promise<Response> {


    // Can be a string or array of strings]
    const stories = [
      "This is a story about an orange cloud",
      "This is a story about a llama",
      "This is a story about a hugging emoji",
    ];


    const embeddings = await env.AI.run(
      "@cf/baai/bge-m3",
      {
        text: stories,
      }
    );


    return Response.json(embeddings);
  },
} satisfies ExportedHandler<Env>;

Python

 
import os
import requests




ACCOUNT_ID = "your-account-id"
AUTH_TOKEN = os.environ.get("CLOUDFLARE_AUTH_TOKEN")


stories = [
  'This is a story about an orange cloud',
  'This is a story about a llama',
  'This is a story about a hugging emoji'
]


response = requests.post(
  f"https://api.cloudflare.com/client/v4/accounts/{ACCOUNT_ID}/ai/run/@cf/baai/bge-m3",
  headers={"Authorization": f"Bearer {AUTH_TOKEN}"},
  json={"text": stories}
)


print(response.json())

curl
Terminal window
curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run/@cf/baai/bge-m3  \
  -X POST  \
  -H "Authorization: Bearer $CLOUDFLARE_API_TOKEN"  \
  -d '{ "text": ["This is a story about an orange cloud", "This is a story about a llama", "This is a story about a hugging emoji"] }'

Parameters

* indicates a required field

Input

  • BGE M3 Input Query and Contexts object

    • query string min 1

      A query you wish to perform against the provided contexts. If no query is provided the model with respond with embeddings for contexts

    • contexts * array

      List of provided contexts. Note that the index in this array is important, as the response will refer to it.

      • items object

        • text string min 1

          One of the provided context content

    • truncate_inputs boolean

      When provided with too long context should the model error out or truncate the context to fit?

  • BGE M3 Input Embedding object

    • text * one of

      • 0 string min 1

        The text to embed

      • 1 array

        Batch of text values to embed

        • items string min 1

          The text to embed

    • truncate_inputs boolean

      When provided with too long context should the model error out or truncate the context to fit?

Output

  • BGE M3 Ouput Query object

    • response array

      • items object

        • id integer

          Index of the context in the request

        • score number

          Score of the context under the index.

  • BGE M3 Output Embedding for Contexts object

    • response array

      • items array

        • items number

    • shape array

      • items number

    • pooling string

      The pooling method used in the embedding process.

  • BGE M3 Ouput Embedding object

    • shape array

      • items number

    • data array

      Embeddings of the requested text values

      • items array

        Floating point embedding representation shaped by the embedding model

        • items number

    • pooling string

      The pooling method used in the embedding process.

API Schemas

The following schemas are based on JSON Schema

{
    "type": "object",
    "oneOf": [
        {
            "title": "BGE M3 Input Query and Contexts",
            "properties": {
                "query": {
                    "type": "string",
                    "minLength": 1,
                    "description": "A query you wish to perform against the provided contexts. If no query is provided the model with respond with embeddings for contexts"
                },
                "contexts": {
                    "type": "array",
                    "items": {
                        "type": "object",
                        "properties": {
                            "text": {
                                "type": "string",
                                "minLength": 1,
                                "description": "One of the provided context content"
                            }
                        }
                    },
                    "description": "List of provided contexts. Note that the index in this array is important, as the response will refer to it."
                },
                "truncate_inputs": {
                    "type": "boolean",
                    "default": false,
                    "description": "When provided with too long context should the model error out or truncate the context to fit?"
                }
            },
            "required": [
                "contexts"
            ]
        },
        {
            "title": "BGE M3 Input Embedding",
            "properties": {
                "text": {
                    "oneOf": [
                        {
                            "type": "string",
                            "description": "The text to embed",
                            "minLength": 1
                        },
                        {
                            "type": "array",
                            "description": "Batch of text values to embed",
                            "items": {
                                "type": "string",
                                "description": "The text to embed",
                                "minLength": 1
                            },
                            "maxItems": 100
                        }
                    ]
                },
                "truncate_inputs": {
                    "type": "boolean",
                    "default": false,
                    "description": "When provided with too long context should the model error out or truncate the context to fit?"
                }
            },
            "required": [
                "text"
            ]
        }
    ]
}