Possible to decide on pipeline via a filter?

[hasani114]

I have been working on creating multiple pipelines/workflows (really amazing feature) and was wondering if its possible to let a filter decide which pipeline to forward the chat to instead of having to select the pipeline from the model list every time?

I understand I can use a filter to intercept a request sent from the frontend but how do I pass it to a specific pipeline? Is it as simple as modifying the "model" parameter in the request body to the pipeline that I want to forward the request to?

[hasani114]

So I was able to figure this out (I think). And it works! i just created a filter and changed the model to whichever pipeline I want to run.

I will use an LLM to decide on the pipeline. Here is the code if anyone was wondering the same:

`
from typing import List, Optional
from pydantic import BaseModel
from schemas import OpenAIChatMessage

class Pipeline:
class Valves(BaseModel):
# List target pipeline ids (models) that this filter will be connected to.
# If you want to connect this filter to all pipelines, you can set pipelines to ["*"]
pipelines: List[str] = []

    # Assign a priority level to the filter pipeline.
    # The priority level determines the order in which the filter pipelines are executed.
    # The lower the number, the higher the priority.
    priority: int = 0

    # Add your custom parameters here
    pass

def __init__(self):
    # Pipeline filters are only compatible with Open WebUI
    # You can think of filter pipeline as a middleware that can be used to edit the form data before it is sent to the OpenAI API.
    self.type = "filter"

    # Optionally, you can set the id and name of the pipeline.
    # Best practice is to not specify the id so that it can be automatically inferred from the filename, so that users can install multiple versions of the same pipeline.
    # The identifier must be unique across all pipelines.
    # The identifier must be an alphanumeric string that can include underscores or hyphens. It cannot contain spaces, special characters, slashes, or backslashes.
    # self.id = "filter_pipeline"

    self.name = "Filter"

    self.valves = self.Valves(**{"pipelines": ["llama3:latest"]})

    pass

async def on_startup(self):
    # This function is called when the server is started.
    print(f"on_startup:{__name__}")
    pass

async def on_shutdown(self):
    # This function is called when the server is stopped.
    print(f"on_shutdown:{__name__}")
    pass

async def inlet(self, body: dict, user: Optional[dict] = None) -> dict:
    # This filter is applied to the form data before it is sent to the OpenAI API.
    print(f"inlet:{__name__}")

    # Change the value of the "model" key to "Another_Langchain_Pipeline"
    body["model"] = "another_langchain_pipeline"

    # If you'd like to check for title generation, you can add the following check
    if body.get("title", False):
        print("Title Generation Request")

    print(body)
    print(user)

    return body`