Integrating M3E Embedding Model

Introduction

FastGPT uses OpenAI's embedding model by default. For private deployment, you can replace it with the M3E embedding model. M3E is a lightweight model with low resource requirements -- it can even run on CPU. The following tutorial is based on an image provided by community contributor "睡大觉".

Deploy the Image

Image: stawky/m3e-large-api:latest China mirror: registry.cn-hangzhou.aliyuncs.com/fastgpt_docker/m3e-large-api:latest Port: 6008 Environment variables:

# Set the security token (used as the channel key in OneAPI)
Default: sk-aaabbbcccdddeeefffggghhhiiijjjkkk
You can also set it via the environment variable: sk-key. Refer to Docker documentation for how to pass environment variables.

Connect to One API

Add a channel with the following parameters:

Test

curl example:

curl --location --request POST 'https://domain/v1/embeddings' \
--header 'Authorization: Bearer xxxx' \
--header 'Content-Type: application/json' \
--data-raw '{
  "model": "m3e",
  "input": ["What is laf"]
}'

Set Authorization to your sk-key. The model field should match the custom model name you entered in One API.

Integrate with FastGPT

Edit the config.json file and add the M3E model to vectorModels:

"vectorModels": [
    {
      "model": "text-embedding-ada-002",
      "name": "Embedding-2",
      "price": 0.2,
      "defaultToken": 500,
      "maxToken": 3000
    },
    {
      "model": "m3e",
      "name": "M3E (for testing)",
      "price": 0.1,
      "defaultToken": 500,
      "maxToken": 1800
    }
]

Usage

Select the M3E model when creating a Knowledge Base.

Note: once selected, the embedding model for the Knowledge Base cannot be changed.
Import data
Test search
Bind the Knowledge Base to an app

Note: an app can only bind Knowledge Bases that use the same embedding model -- cross-model binding is not supported. You may also need to adjust the similarity threshold, as different embedding models produce different similarity (distance) scores. Test and tune accordingly.