API File Library

Background

FastGPT supports local file imports, but in many cases users already have an existing document library. Re-importing files would create duplicate storage and complicate management. To address this, FastGPT offers an API File Library that connects to your existing document library through simple API endpoints, with flexible import options.

The API File Library lets you integrate your existing document library seamlessly. Implement a few endpoints that conform to FastGPT's API File Library specification, provide the service's baseURL and token when creating a knowledge base, and you can browse and selectively import files directly from the UI.

How to Use the API File Library

When creating a knowledge base, select the API File Library type and configure two key parameters: the baseURL of your file service and the request header for authentication. As long as your endpoints conform to FastGPT's specification, the system will automatically fetch and display the complete file list for selective import.

You need to provide two parameters:

baseURL: The base URL of your file service
authorization: The authentication request header, sent as Authorization: Bearer <token>

API Specification

Response format:

type ResponseType = {
  success: boolean;
  message: string;
  data: any;
}

Data types:

// Single file item in the file list
type FileListItem = {
  id: string;
  parentId: string | null;
  name: string;
  type: 'file' | 'folder';
  updateTime: Date;
  createTime: Date;
}

1. Get File Tree

parentId - Parent ID, optional or null.
searchKey - Search keyword, optional

curl --location --request POST '{{baseURL}}/v1/file/list' \
--header 'Authorization: Bearer {{authorization}}' \
--header 'Content-Type: application/json' \
--data-raw '{
    "parentId": null,
    "searchKey": ""
}'

{
    "code": 200,
    "success": true,
    "message": "",
    "data": [
        {
            "id": "xxxx",
            "parentId": "xxxx",
            "type": "file",  // file | folder
            "name":"test.json",
            "updateTime":"2024-11-26T03:05:24.759Z",
            "createTime":"2024-11-26T03:05:24.759Z"
        }
   ]
}

2. Get Single File Content (Text Content or Access Link)

curl --location --request GET '{{baseURL}}/v1/file/content?id=xx' \
--header 'Authorization: Bearer {{authorization}}'

{
    "code": 200,
    "success": true,
    "message": "",
    "data": {
        "title": "Document Title",
        "content": "FastGPT is an LLM-based knowledge base Q&A system with out-of-the-box data processing and model invocation capabilities. It also supports visual workflow orchestration via Flow for complex Q&A scenarios!\n",
        "previewUrl": "xxxx"
    }
}

title - File title.
content - File content, used directly.
previewUrl - File link; the system will request this URL to fetch the file content.

Return either content or previewUrl. If both are returned, content takes priority. When previewUrl is returned, the system will access that link to read the document content.

3. Get File Read Link (for Viewing the Original)

id is the file's ID.

curl --location --request GET '{{baseURL}}/v1/file/read?id=xx' \
--header 'Authorization: Bearer {{authorization}}'

{
    "code": 200,
    "success": true,
    "message": "",
    "data": {
        "url": "xxxx"
    }
}

url - File access link; opens automatically once retrieved.