Pass parameter betweens each Runnables in a chain

[eyurtsev]

Discussed in #479

^{Originally posted by shaojun February 22, 2024}
Hi,
I have a CustomUserType input request, and there's a field of shared_pass_through_parameter that contains non-nature language data which would be used in any followed Runnables (except the LLM node).
like the below sample code, the purpose of this field is to pass to final RunnableLambda(output_process) to output a customized content.

app = FastAPI(
    title="LangChain Server",
    version="1.0",
    description="A simple api server using Langchain's Runnable interfaces",
)

# model = ChatModelBuilder.Create()


class MyCustomRequest(CustomUserType):
    content: str
    prompt: str
    shared_pass_through_parameter: str = "No-natural language content"


def process(request: MyCustomRequest):
    from pydantic import BaseModel, create_model
    import json
    prompt = ChatPromptTemplate.from_messages([
        ("system", '{system_prompt}'),
        ("human", '{user_content}')
    ])
    return prompt.invoke({"system_prompt": request.prompt, "user_content": request.content})


def output_process(input: Any):
    # !!!HOW TO GET the shared_pass_through_parameter
    # if input.shared_pass_through_parameter == 'test':
    #     print('shared_pass_through_parameter is test')
    return input


model = ChatOpenAI()
add_routes(
    app,
    RunnableLambda(process).with_types(
        input_type=MyCustomRequest) | model | RunnableLambda(output_process),
    path="/MyService1",
)
if __name__ == "__main__":
    import uvicorn

    uvicorn.run(app, host="0.0.0.0", port=9000)

Obvious that field will be dropped as it's not included into the output of process.
I can see a solution that wrap all the route chain into a single function, but that will lose the feature of streaming of LLM.
any suggestion?

[eyurtsev]

Looking now

[eyurtsev]

Bug

from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnablePassthrough, RunnableGenerator
from langchain_core.beta.runnables.context import Context

async def to_dict(input):
    async for chunk in input:
        yield {
            'foo': chunk
        }

chain = Context.setter('input') | model | to_dict | Context.getter('input')

async for chunk in chain.astream('hello'):
    print(chunk)

[eyurtsev]

Issue will be tracked in LangChain since this is not a LangServe issue