Skip to content

feat: parallel function calling #225

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
giladgd merged 39 commits into from
Jun 8, 2024
Merged

feat: parallel function calling #225

giladgd merged 39 commits into from
Jun 8, 2024

Conversation

@giladgd
Copy link
Member

@giladgd giladgd commented Jun 5, 2024 •
edited
Loading

Description of change

  • feat: parallel function calling
  • feat: preload prompt
  • feat: prompt completion engine
  • feat: chat wrapper based system message support
  • feat: add prompt completion to the Electron example
  • feat: model compatibility warnings
  • feat: Functionary v2.llama3 support
  • feat: parallel function calling with plain Llama 3 Instruct
  • feat: improve function calling support for default chat wrapper
  • feat: parallel model downloads
  • feat: add the electron example to releases
  • feat: improve the electron example
  • feat: customStopTriggers for LlamaCompletion
  • fix: improve CUDA detection on Windows
  • fix: performance improvements
  • refactor: make functionCallMessageTemplate an object
  • chore: adapt to llama.cpp breaking changes

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 added 30 commits May 24, 2024 01:53
@giladgd
refactor: split LlamaChat implementation into smaller functions
23c3a05
@giladgd
feat: preload prompt and complete a preloaded prompt
86e86ac
@giladgd
chore: remove redundant setting in script
21629bc
@giladgd
fix: bug
c578ddb
@giladgd
feat: prompt completion engine
2d38a7e
@giladgd
feat: add prompt completion to the Electron example
2ea5265
@giladgd
test: fix test
33c7360
@giladgd
chore: update some dev dependencies
3dd6db1
@giladgd
feat: add action recommendations to the electron example
3da99a0
@giladgd
feat: build the electron example and add it to the published GitHub r…
68395b1 
…elease
@giladgd
feat: parallel function calling, chat wrapper based system message su…
e55c858 
…pport
@giladgd
feat: model compatibility warnings
0f9b7f3
@giladgd
fix: improve CUDA detection on Windows
ca93c0b
@giladgd
fix: bugs
c7957d3
@giladgd
feat: parallel model downloads
d664277
@giladgd
fix: small performance improvement
e624b5f
@giladgd
test: update tests
b79a950
@giladgd
feat: support Functionary v2.llama3
859b2a2
@giladgd
fix: bugs
ecb25e1
@giladgd
test: update models used in tests
c8ba7eb
@giladgd
chore: adapt to llama.cpp breaking changes
92ab710
@giladgd
test: update tests
0df534b
@giladgd
feat: call function calling handle functions earlier
2e4fca6
@giladgd
feat: improve function calling with plain Llama 3 Instruct
be06e0b
@giladgd
feat: parallel function calling with plain Llama 3 Instruct
2edd7f6
@giladgd
fix: bugs
0bc4542
@giladgd
test: test tokenizer
8066f08
@giladgd
refactor: make functionCallMessageTemplate an object
9d2959d
@giladgd
feat: improve function calling syntax for default chat wrapper
c9dd113
@giladgd
style: lint
20f03d6
@giladgd giladgd requested a review from ido-pluto June 5, 2024 23:33
@giladgd giladgd self-assigned this Jun 5, 2024
ido-pluto
ido-pluto approved these changes Jun 6, 2024
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 merged commit 95f4645 into beta Jun 8, 2024
@giladgd giladgd deleted the gilad/parallelFunctionCalls branch June 8, 2024 23:48
@github-actions
Copy link

github-actions bot commented Jun 9, 2024

🎉 This PR is included in version 3.0.0-beta.23 🎉

The release is available on:

Your semantic-release bot 📦🚀

@giladgd giladgd mentioned this pull request Jun 9, 2024
Merged
17 tasks
@giladgd giladgd mentioned this pull request Jul 28, 2024
Merged
7 tasks
@github-actions
Copy link

github-actions bot commented Sep 24, 2024 •
edited by giladgd
Loading

🎉 This PR is included in version 3.0.0 🎉

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 on @beta released

Projects

node-llama-cpp: roadmap
Status: Done

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@giladgd @ido-pluto