Skip to content

UN-3323 NeuroSan: Use 'think' flag to alter thinking behavior of models via Ollama #294

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Noravee merged 1 commit into from
Jul 9, 2025
Merged

UN-3323 NeuroSan: Use 'think' flag to alter thinking behavior of models via Ollama #294

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions neuro_san/internals/run_context/langchain/llms/default_llm_info.hocon
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -746,6 +746,7 @@
"num_gpu": null,
"num_thread": null,
"num_predict": null, # Will use max_tokens
"reasoning": null, # Controls the reasoning/thinking mode for supported models. If None (Default), The model will use its default reasoning behavior.
"repeat_last_n": null,
"repeat_penalty": null,
"temperature": null,
Expand Down
1 change: 1 addition & 0 deletions neuro_san/internals/run_context/langchain/llms/standard_langchain_llm_factory.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -185,6 +185,7 @@ def create_base_chat_model(self, config: Dict[str, Any],
num_gpu=config.get("num_gpu"),
num_thread=config.get("num_thread"),
num_predict=config.get("num_predict", config.get("max_tokens")),
reasoning=config.get("reasoning"),
repeat_last_n=config.get("repeat_last_n"),
repeat_penalty=config.get("repeat_penalty"),
temperature=config.get("temperature"),
Expand Down