Integration with Third-Party Platforms

​

Dify

​

Coze

1. Select Add MCP Tool
2. Enter the MCP Server URL and authentication details (obtained from the Service Channels page in the console)
3. Select the retrieval / Q&A capabilities to expose

1. Create a custom plugin in Coze
2. Configure an HTTP request pointing to the DashScope retrieval endpoint
3. Map input parameters (query, top_k) and output parameters (list of chunks)

​

n8n

1. Add an HTTP Request node
2. Set method to POST and enter the retrieval endpoint URL (see details below)
3. In Headers, add Authorization: Bearer <API-Key>
4. Fill in retrieval parameters in the Body

• Knowledge Search (application-level, recommended):
  https://{workspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/indices/knowledge/search
  Parameters: query and agent_id; retrieval strategy is driven by the knowledge retrieval service configuration.
• Low-Level Retrieval:
  https://{workspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/indices/rag/index/retrieve
  Parameters: index_id, query, top_k; directly specifies the knowledge base ID.

​

LangChain

import requests

class DashScopeRetriever:
    def __init__(self, api_key, index_id):
        self.api_key = api_key
        self.index_id = index_id

    def get_relevant_documents(self, query):
        resp = requests.post(
            "https://{workspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/indices/rag/index/retrieve",
            headers={
                "Authorization": f"Bearer {self.api_key}",
                "Content-Type": "application/json",
            },
            json={
                "index_id": self.index_id,
                "query": query,
                "top_k": 5,
            },
        )
        nodes = resp.json().get("data", {}).get("nodes", [])
        return [{"page_content": n["text"], "metadata": n.get("metadata", {})} for n in nodes]