AI API Gateway

Appearance

RAGFlow — RAG 知识库 ​

网关地址: https://ai.ospreyai.cn（公网） 需要后端 Bearer Token（通过 X-Authorization 传入）

鉴权方式 ​

RAGFlow API Key 在 RAGFlow Web 界面中生成，格式为 ragflow-xxxxxx。

所有请求必须同时携带：

  • Authorization: Bearer sk-xxx — 网关层鉴权
  • X-Authorization: Bearer <ragflow-api-key> — 后端鉴权

列出知识库 ​

GET /api/v1/rag/datasets
Authorization: Bearer sk-xxx
X-Authorization: Bearer ragflow-xxxxxx
bash
curl -H "Authorization: Bearer $API_KEY" \
  -H "X-Authorization: Bearer ragflow-xxxxxx" \
  "$GW/api/v1/rag/datasets"

创建知识库 ​

POST /api/v1/rag/datasets
Content-Type: application/json
Authorization: Bearer sk-xxx
X-Authorization: Bearer ragflow-xxxxxx
bash
curl -H "Authorization: Bearer $API_KEY" \
  -H "X-Authorization: Bearer ragflow-xxxxxx" \
  -H "Content-Type: application/json" \
  -X POST "$GW/api/v1/rag/datasets" \
  -d '{"name": "我的知识库"}'

对话 ​

POST /api/v1/rag/chats
Authorization: Bearer sk-xxx
X-Authorization: Bearer ragflow-xxxxxx
Content-Type: application/json
bash
curl -H "Authorization: Bearer $API_KEY" \
  -H "X-Authorization: Bearer ragflow-xxxxxx" \
  -H "Content-Type: application/json" \
  -X POST "$GW/api/v1/rag/chats" \
  -d '{
    "question": "什么是深度学习？",
    "dataset_ids": ["你的知识库ID"]
  }'

Python 调用示例 ​

python
import requests

session = requests.Session()
session.headers.update({
    "Authorization": "Bearer sk-your-api-key",
    "X-Authorization": "Bearer ragflow-xxxxxx",
    "Content-Type": "application/json"
})

BASE = "https://ai.ospreyai.cn/api/v1/rag"

# 列出知识库
resp = session.get(f"{BASE}/datasets")
print(resp.json())

AI API Gateway Documentation