klbr/khoj
1
0
Fork 0
mirror of https://github.com/khoaliber/khoj.git synced 2026-03-02 13:18:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix max thinking budget for gemini models to generate final response

Browse Source
This commit is contained in:
Debanjum
2025-08-18 23:25:11 -07:00
parent 34dca8e114
commit ff73d30106
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/khoj/processor/conversation/google/utils.py
View File

@@ -326,7 +326,7 @@ async def gemini_chat_completion_with_backoff(
thinking_config = None
if deepthought and is_reasoning_model(model_name):
thinking_config = gtypes.ThinkingConfig(thinking_budget=-1, include_thoughts=True)
thinking_config = gtypes.ThinkingConfig(thinking_budget=MAX_REASONING_TOKENS_GEMINI, include_thoughts=True)
max_output_tokens = MAX_OUTPUT_TOKENS_FOR_STANDARD_GEMINI
if is_reasoning_model(model_name):