Skip to content

feat: extract function calling syntax from a Jinja template #444

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

Jump to bottom
Merged
merged 33 commits into from
Mar 27, 2025
Merged

feat: extract function calling syntax from a Jinja template #444

merged 33 commits into from
Mar 27, 2025

Conversation

giladgd
Copy link
Contributor

@giladgd giladgd commented Mar 20, 2025 •
edited
Loading

Description of change

  • feat: extract function calling syntax from a Jinja template
  • feat: Full support for Qwen and QwQ via QwenChatWrapper
  • feat: export a llama instance getter on a model instance
  • fix: better handling for function calling with empty parameters
  • fix: reranking edge case crash
  • fix: limit the context size by default in the node-typescript template
  • fix: adapt to breaking llama.cpp changes
  • fix: bump min nodejs version to 20
  • fix: better husky setup
  • fix: defineChatSessionFunction type
  • docs: troubleshooting function calling when using JinjaTemplateChatWrapper (documentation: Function Calling Issues With JinjaTemplateChatWrapper)
  • docs: fix the command to scaffold a new Electron project
  • docs: debugging a native crash on Linux
  • test: make LlamaText snapshots more readable
  • chore: update modules

Resolves #440
Fixes #435

Pull-Request Checklist

  • Code is up-to-date with the master branch
  • npm run format to apply eslint formatting
  • npm run test passes with this change
  • This pull request links relevant issues as Fixes #0000
  • There are new or updated unit tests validating the change
  • Documentation has been updated to reflect this change
  • The new commits and pull request title follow conventions explained in pull request guidelines (PRs that do not follow this convention will not be merged)

@giladgd giladgd requested a review from ido-pluto March 20, 2025 01:50
@giladgd giladgd self-assigned this Mar 20, 2025
ido-pluto
ido-pluto approved these changes Mar 20, 2025
View reviewed changes
Copy link
Contributor

@ido-pluto ido-pluto left a comment

Choose a reason for hiding this comment

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

LGTM

@giladgd giladgd enabled auto-merge (squash) March 22, 2025 02:04
@giladgd giladgd disabled auto-merge March 22, 2025 19:21
giladgd added 6 commits March 22, 2025 21:31
@giladgd
fix: bump min nodejs version to 20
ff8170f 
Some dependencies already have this requirement,
so trying to install `node-llama-cpp` on nodejs 18 already generates a bunch of warnings anyway
@giladgd
docs: debugging native crash on Linux
6cd8d95
@giladgd
chore: update modules
b9726e6
@giladgd
fix: log level
a8dff21
@giladgd
chore: configure eslint
6ccbca3
@giladgd
fix: defineChatSessionFunction type
c3c0066
@giladgd giladgd merged commit c070e81 into master Mar 27, 2025
19 checks passed
@giladgd giladgd deleted the gilad/extractFunctionCallingTemplateFromJinja branch March 27, 2025 23:51
@github-actions GitHub Actions
Copy link

🎉 This PR is included in version 3.7.0 🎉

The release is available on:

Your semantic-release bot 📦🚀

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@ido-pluto ido-pluto ido-pluto approved these changes

Assignees

@giladgd giladgd

Labels
released
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

feat: Gemma 3 Support Limit default context size in the node template
2 participants
@giladgd @ido-pluto