missing <think> tags
#2
by deepyes02 - opened
This specific qwen3-vl model seems to be responding in some form of jsond with a separate key 'reasoning' for streaming the reasoning data. However, the base model responds in tags inside the main "content" key, so I am confused because I want to use this vision model as a base model, and I loved the reasoning feature, but I am having difficulty implementing with libraries like ChatOpenAI or even ChatOllama with langchain.
Example request to
/v1/chat/completions:
curl --location 'http://xxx.xxx.x.x:11434/v1/chat/completions' \
--header 'Content-Type: application/json' \
--data '{
"model": "qwen3:14b /qwen3-vl:8b",
"messages": [
{"role": "user", "content": "Explain quantum mechanics, and how it has helped us understand the world better."}
],
"max_tokens": 100,
"stream": true
}'
Response:
Qwen3 Text Responds with <think> tag inside the key content :
data: {"id":"chatcmpl-681","object":"chat.completion.chunk","created":1770621334,"model":"qwen3:14b","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"\u003cthink\u003e"},"finish_reason":null}]}
data: {"id":"chatcmpl-681","object":"chat.completion.chunk","created":1770621334,"model":"qwen3:14b","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"},"finish_reason":null}]}
Qwen 3 Vision responds with thinking in a key reasoning :
data: {"id":"chatcmpl-298","object":"chat.completion.chunk","created":1770621544,"model":"qwen3-vl:8b","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"Okay"},"finish_reason":null}]}
data: {"id":"chatcmpl-298","object":"chat.completion.chunk","created":1770621544,"model":"qwen3-vl:8b","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":","},"finish_reason":null}]}
I am having trouble working with two different types of response from the same version of model....