Skip to content
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.

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

Fix regression while using localdocs with server API. #3410

Merged
merged 2 commits into from
Jan 24, 2025

Conversation

manyoso
Copy link
Collaborator

@manyoso manyoso commented Jan 23, 2025

We've had a regression since 3.5.x where the model was not using localdocs for N > 1 server api message. We weren't taking into account the idiosyncratic way the server uses the chatmodel so that we require an offset when updating the sources.

@manyoso manyoso requested a review from cebtenzzre January 23, 2025 15:03
Copy link
Member

@cebtenzzre cebtenzzre left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Should add a changelog entry under "Unreleased" as it's too late for v3.7.0.

gpt4all-chat/src/chatllm.cpp Outdated Show resolved Hide resolved
@manyoso manyoso force-pushed the localdocs_server_api_fix branch from 770f68c to d0a2b42 Compare January 24, 2025 15:25
@manyoso manyoso merged commit b98501c into main Jan 24, 2025
3 of 7 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants