How to pass params or config to a Langserve Chain

[latifs]

Hi Guys, @dosu-bot,
I'd like to pass parameters to a LangServe chain that I have set up.
I'd like to be able to pass

• temperature and top_k to the model,
• prompts template,
• namespace to customize my retriever,

and anything that could be pertaining to tests that I am doing now.

Here is a simple chain available in the examples rag-pinecone that I'd like to be able to configure a little bit more.

Questions:
How to simply access the values passed to the chain and just print them for example?
How to call the runnable with RemoteRunnable and how to do it with requests in python?

vectorstore = PineconeVectorStore.from_existing_index(
    PINECONE_INDEX_NAME, OpenAIEmbeddings()
)
retriever = vectorstore.as_retriever()

# RAG prompt
template = """Answer the question based only on the following context:
{context}
Question: {question}
"""
prompt = ChatPromptTemplate.from_template(template)

# RAG
model = ChatOpenAI()
chain = (
    RunnableParallel({"context": retriever, "question": RunnablePassthrough()})
    | prompt
    | model
    | StrOutputParser()
)


# Add typing for input
class Question(RootModel):
    root: str

# chain = chain.with_types(input_type=Question)
chain = chain.with_types(input_type=Question)

Thanks