docs/how_to/streaming/

[giscus[bot]]

docs/how_to/streaming/

This guide assumes familiarity with the following concepts:

https://python.langchain.com/docs/how_to/streaming/

[cmoaciopm]

I'm using the below code snippet to learn "Working with Input Streams".

from langchain.chat_models import init_chat_model
from langchain_core.output_parsers import JsonOutputParser

model = init_chat_model(
    model_provider="openai",
    model="qwen3:8b",
    base_url="http://localhost:11434/v1",
    api_key="123456"
)

chain = model | JsonOutputParser()

for text in chain.stream(
    "output a list of the countries france, spain and japan and their populations in JSON format. "
    'Use a dict with an outer key of "countries" which contains a list of countries. '
    "Each country should have the key `name` and `population`"
):
    print(text, end="|", flush=True)

As you can see, I use Ollama to run qwen3 model. When I run the python code, nothing was printed in the console. However, if I switch to use other models like llama3 or deepseek-r1, I can find get the streaming log printed. Does that mean JsonOutputParser doesn't support streaming for qwen3 model? Thanks.

[hanW2039]

Qwen3 has a parameter named stream, which defaults to false. You can enable it by setting this parameter to true in your API request.