ResponseSchema in latest build

[azaidiuk]

I am looking for responseschema in the latest build, has this moved or not implemented yet ?

[dosubot[bot]]

Hey @azaidiuk! I'm here to help you with any issues or questions you have. I'm a bot designed to assist with bug fixes, answer questions, and guide you on becoming a contributor. Let me know how I can assist you!

The ResponseSchema has been replaced by several new schemas in the latest build. Notable alternatives include ProcessResponse and RunResponse, among others.

For use cases previously handled by ResponseSchema, the ProcessResponse schema is recommended:

class ProcessResponse(BaseModel):
    """Process response schema."""

    result: Any
    status: Optional[str] = None
    task: Optional[TaskResponse] = None
    session_id: Optional[str] = None
    backend: Optional[str] = None

Additionally, the RunResponse schema can be used if your use case involves handling outputs from a run session:

class RunResponse(BaseModel):
    """Run response schema."""

    outputs: Optional[List[RunOutputs]] = []
    session_id: Optional[str] = None

    @model_serializer(mode="plain")
    def serialize(self):
        # Serialize all the outputs if they are base models
        serialized = {"session_id": self.session_id, "outputs": []}
        if self.outputs:
            serialized_outputs = []
            for output in self.outputs:
                if isinstance(output, BaseModel) and not isinstance(output, RunOutputs):
                    serialized_outputs.append(output.model_dump(exclude_none=True))
                else:
                    serialized_outputs.append(output)
            serialized["outputs"] = serialized_outputs
        return serialized

For more specific use cases, you might also consider other schemas such as PreloadResponse, TaskStatusResponse, ChatResponse, PromptResponse, FileResponse, and others ^[1][2].

To continue talking to Dosu, mention @dosu.

[azaidiuk]

Subflow is not working – the dropdown to select a workflow is not populating From: dosubot[bot] ***@***.***> Date: Tuesday, 18 June 2024 at 12:45 To: langflow-ai/langflow ***@***.***> Cc: azaidiuk ***@***.***>, Mention ***@***.***> Subject: Re: [langflow-ai/langflow] ResponseSchema in latest build (Discussion #2209) Hey @azaidiuk<https://github.com/azaidiuk>! I'm here to help you with any issues or questions you have. I'm a bot designed to assist with bug fixes, answer questions, and guide you on becoming a contributor. Let me know how I can assist you! The ResponseSchema has been replaced by several new schemas in the latest build. Notable alternatives include ProcessResponse and RunResponse, among others. For use cases previously handled by ResponseSchema, the ProcessResponse schema is recommended: class ProcessResponse(BaseModel): """Process response schema.""" result: Any status: Optional[str] = None task: Optional[TaskResponse] = None session_id: Optional[str] = None backend: Optional[str] = None Additionally, the RunResponse schema can be used if your use case involves handling outputs from a run session: class RunResponse(BaseModel): """Run response schema.""" outputs: Optional[List[RunOutputs]] = [] session_id: Optional[str] = None @model_serializer(mode="plain") def serialize(self): # Serialize all the outputs if they are base models serialized = {"session_id": self.session_id, "outputs": []} if self.outputs: serialized_outputs = [] for output in self.outputs: if isinstance(output, BaseModel) and not isinstance(output, RunOutputs): serialized_outputs.append(output.model_dump(exclude_none=True)) else: serialized_outputs.append(output) serialized["outputs"] = serialized_outputs return serialized For more specific use cases, you might also consider other schemas such as PreloadResponse, TaskStatusResponse, ChatResponse, PromptResponse, FileResponse, and others [1]<https://github.com/logspace-ai/langflow/blob/dev/src/backend/langflow/api/v1/schemas.py>[2]<https://github.com/logspace-ai/langflow/blob/dev/src/backend/base/langflow/api/v1/schemas.py>. To continue talking to Dosu<https://dosu.dev>, mention @dosu<https://github.com/dosu>. — Reply to this email directly, view it on GitHub<#2209 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AJIB6Y7DZYUNHSBNTRNLTKLZIAMUBAVCNFSM6AAAAABJP3D3Z2VHI2DSMVQWIX3LMV43SRDJONRXK43TNFXW4Q3PNVWWK3TUHM4TQMBVGQYTM>. You are receiving this because you were mentioned.Message ID: ***@***.***>

[dosubot[bot]]

The dropdown to select a workflow in the subflow feature is not populating because the options field for flow_name in the build_config is not being updated correctly. The update_build_config method is responsible for updating the options field with the available flow names by calling self.get_flow_names(). If this method is not being called or if self.get_flow_names() is not returning any flow names, the dropdown will remain empty.

Ensure that self.get_flow_names() is correctly implemented and returning a list of flow names. If self.list_flows() is not returning any flows, the dropdown will not populate. Here is the implementation of self.get_flow_names():

def get_flow_names(self) -> List[str]:
    flow_datas = self.list_flows()
    return [flow_data.data["name"] for flow_data in flow_datas]

Make sure that self.list_flows() is functioning correctly and returning the available flows. If there are no flows available, the dropdown will remain empty ^[1][2][3].

To continue talking to Dosu, mention @dosu.

[azaidiuk]

I am getting and error trace stating list is not supported from get_flow_names

…

On Tue, 16 Jul 2024 at 00:07, dosubot[bot] ***@***.***> wrote: The dropdown to select a workflow in the subflow feature is not populating because the options field for flow_name in the build_config is not being updated correctly. The update_build_config method is responsible for updating the options field with the available flow names by calling self.get_flow_names(). If this method is not being called or if self.get_flow_names() is not returning any flow names, the dropdown will remain empty. Ensure that self.get_flow_names() is correctly implemented and returning a list of flow names. If self.list_flows() is not returning any flows, the dropdown will not populate. Here is the implementation of self.get_flow_names(): def get_flow_names(self) -> List[str]: flow_datas = self.list_flows() return [flow_data.data["name"] for flow_data in flow_datas] Make sure that self.list_flows() is functioning correctly and returning the available flows. If there are no flows available, the dropdown will remain empty [1] <https://github.com/langflow-ai/langflow/blob/dev/src/backend/base/langflow/components/experimental/SubFlow.py> [2] <https://github.com/langflow-ai/langflow/blob/dev/src/backend/base/langflow/components/prototypes/SubFlow.py> [3] <https://github.com/langflow-ai/langflow/blob/dev/src/backend/base/langflow/components/deactivated/SubFlow.py> . *To continue talking to Dosu <https://dosu.dev>, mention @dosu <https://github.com/dosu>.* — Reply to this email directly, view it on GitHub <#2209 (reply in thread)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AJIB6Y3I7X7ZMNI5PID3X6LZMRI2HAVCNFSM6AAAAABJP3D3Z2VHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTAMBVGYYTQMY> . You are receiving this because you were mentioned.Message ID: ***@***.***>

[dosubot[bot]]

The issue with the get_flow_names method causing an error trace stating that a list is not supported might be due to the way the list_flows method is implemented or how the data is being accessed. However, based on the provided code, the get_flow_names method itself seems correctly implemented to return a list of flow names.

Here is the get_flow_names method for reference:

def get_flow_names(self) -> List[str]:
    flow_data = self.list_flows()
    return [flow_data.data["name"] for flow_data in flow_data]

To resolve the issue, ensure that the list_flows method returns a list of objects where each object has a data attribute that is a dictionary containing a name key. If list_flows is returning data in an unexpected format, it could cause the error.

If the list_flows method is correct, then the issue might be elsewhere in the code where the get_flow_names method is used. Specifically, in the update_build_config method, ensure that the build_config["flow_name"]["options"] is correctly set to the list of flow names.

Here is the relevant part of the update_build_config method:

def update_build_config(self, build_config: dotdict, field_value: Any, field_name: str | None = None):
    if field_name == "flow_name":
        build_config["flow_name"]["options"] = self.get_flow_names()
    return build_config

Ensure that build_config["flow_name"]["options"] is indeed a list of strings. If list_flows or any other part of the code is returning data in an unexpected format, it could cause the error.

If the issue persists, you may need to provide more details about the list_flows method or any other part of the code that interacts with get_flow_names ^[1][2][3][4].

To continue talking to Dosu, mention @dosu.

[Cristhianzl]

Hi! 👋

We are using other channels as our official means of communication with users. We apologize for the delayed response.
For faster assistance, please direct your questions to our Discord channel or open a GitHub issue, as we are much more active on these platforms.

Langflow Discord Server

Thank you for your understanding.

Best regards,
The Langflow Team