ai-agents-streaming-error-assertionerror-on-assert-generation-is-not-none-wh-92865d97

THEN Check if your AzureChatOpenAI deployment supports streaming. If not, avoid using .stream() and instead use .invoke() or .batch(). Alternatively, instantiate the model with streaming=False if the class accepts that parameter. For LangChain core, consider implementing a fallback to non-streaming when the model lacks streaming capability.

from langchain_openai import AzureChatOpenAI

# Instantiate without streaming
llm = AzureChatOpenAI(
    azure_deployment="my-deployment",
    azure_endpoint="https://my-resource.openai.azure.com/",
    api_version="2024-02-01",
    streaming=False  # if accepted
)

# Use .invoke() instead of .stream()
response = llm.invoke("Hello")
print(response.content)