How can the Chatflow API be integrated?

[jinec]

Self Checks

• I have searched for existing issues search for existing issues, including closed ones.
• I confirm that I am using English to submit report (我已阅读并同意 Language Policy).
• [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:)
• Please do not modify this template :) and fill in all the required fields.

Provide a description of requested docs changes

I have now installed the OpenAI Compatible Dify APP plugin, and I have registered my Chatflow application inside it. Details are as follows:

What I understand is: I can only obtain the POST link address of this Chatflow. So the question arises: how can I use this POST link?

I then found the following code:
import json
from typing import Mapping
from werkzeug import Request, Response
from dify_plugin import Endpoint

class Duck(Endpoint):
def _invoke(self, r: Request, values: Mapping, settings: Mapping) -> Response:
"""
Invokes the endpoint with the given request.
"""
app_id = values["app_id"]

    def generator():
        response = self.session.app.workflow.invoke(
            app_id=app_id, inputs={}, response_mode="streaming", files=[]
        )

        for data in response:
            yield f"{json.dumps(data)} <br>"

    return Response(generator(), status=200, content_type="text/html")

However, this function requires me to provide an app_id, which I don't have. Then I didn't know what to do next.

[dosubot[bot]]

To integrate the Chatflow API, you need to obtain the app_id for your application. You can get the app_id from the app_config of the AdvancedChatAppGenerateEntity instance. This is typically done during the setup or configuration of your application within Dify. Here's an example of how the app_id is accessed in the code:

trace_manager = TraceQueueManager(
    app_id=app_model.id, user_id=user.id if isinstance(user, Account) else user.session_id
)

workflow_node_execution_repository = SQLAlchemyWorkflowNodeExecutionRepository(
    session_factory=session_factory,
    user=user,
    app_id=application_generate_entity.app_config.app_id,
    triggered_from=WorkflowNodeExecutionTriggeredFrom.WORKFLOW_RUN,
)

Once you have the app_id, you can use it in your code to invoke the workflow using the session.app.workflow.invoke method, as shown in your example. This method allows you to execute workflows by providing necessary parameters like app_id, inputs, response_mode, and files ^[1].

Additionally, I found a similar resolved issue where specifying the app_id when calling the /workflows/run API was discussed. The solution involved including the app_id as part of the URL path, although it seems the API key is primarily used to distinguish different apps ^[2].

To continue talking to Dosu, mention @dosu.

---

^{Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Bug Report | Other}

[jinec]

You didn't quite understand my true intention. What I actually want to do is embed a sub-Chatflow into a comprehensive Chatflow, and enable streaming output. What should I do?

My current plan is to first use the "OpenAI Compatible Dify App" plugin to convert the sub-Chatflow into an OpenAI-compatible API. But what should I do next? Am I doing the right thing now?

[XJTU-JP]

The same problem. May I ask if there is a solution？