How to chain AzureOpenAI in LangChain?

Question

from openai import AzureOpenAI
client = AzureOpenAI(
        azure_endpoint=os.getenv("AZURE_OPENAI_ENDPOINT"),
        api_key=os.getenv("AZURE_OPENAI_API_KEY"),
        api_version="2024-05-01-preview"
    )

normal_chain = (
    ChatPromptTemplate.from_messages([("system", "write a tweet about {topic} in the style of Elon Musk") ])
    | client
    | StrOutputParser()
)

In this code, I am getting Expected type 'Runnable[Any, Other] | (Any) -> Other | (Iterator) -> Iterator[Other] | Mapping[str, Runnable[Any, Other] | (Any) -> Other | Any]', got 'AzureOpenAI' instead. How to make the client as Runnable? Is there any other way to do the same thing?

I tried all the available options from LangChain, but it is not working.

Answer 1

    client = AzureOpenAI(
        azure_endpoint=os.getenv("AZURE_OPENAI_ENDPOINT"),
        api_key=os.getenv("AZURE_OPENAI_API_KEY"),
        api_version="2024-05-01-preview"
    )

    completion = client.chat.completions.create(
        model=finetuned_deployment,
        messages=[
            {
                "role": "user",
                "content": f"Write a tweet about {topic}"
            }],
        max_tokens=800,
        temperature=0.7,
        top_p=0.95,
    )
    
completion.to_json()    

This code snippet worked.