ragflow

mirror of https://github.com/infiniflow/ragflow.git synced 2026-01-19 11:45:10 +08:00

Files

Pegasus b091ff2730 Fix enable_thinking parameter for Qwen3 models (#12603 )

### Issue

When using Qwen3 models (`qwen3-32b`, `qwen3-max`) through the
Tongyi-Qianwen provider for non-streaming calls (e.g., knowledge graph
generation), the API fails with:

Closes #12424

```
parameter.enable_thinking must be set to false for non-streaming calls
```

### Root Cause

In `LiteLLMBase.async_chat()`, the `extra_body={"enable_thinking":
False}` was set in `kwargs` but never forwarded to
`_construct_completion_args()`.

### What problem does this PR solve?

Pass merged kwargs to `_construct_completion_args()` using
`**{**gen_conf, **kwargs}` to safely handle potential duplicate
parameters.

### Changes

- `rag/llm/chat_model.py`: Forward kwargs containing `extra_body` to
`_construct_completion_args()` in `async_chat()`


_Briefly describe what this PR aims to solve. Include background context
that will help reviewers understand the purpose of the PR._

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

Contribution by Gittensor, see my contribution statistics at
https://gittensor.io/miners/details?githubId=42954461

2026-01-14 16:35:46 +08:00

advanced_rag

Feat: support tree structured deep-research policy. (#12559 )

2026-01-13 09:41:35 +08:00

app

refactor: remove debug print statements (#12534 )

2026-01-09 19:23:50 +08:00

flow

refactor: remove debug print statements (#12598 )

2026-01-14 10:05:34 +08:00

llm

Fix enable_thinking parameter for Qwen3 models (#12603 )