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

Update the recommended model for Google Gen AI #118323

Merged
merged 1 commit into from
May 29, 2024
Merged

Conversation

balloob
Copy link
Member

@balloob balloob commented May 28, 2024

Breaking change

Proposed change

Update the recommended model for Google Gen AI to be Gemini 1.5 Pro instead of Gemini 1.5 Flash. Pro is slower and more capable, giving better results for controlling Home Assistant. We were hoping to use Flash but the current results with the LLM API are not up to par.

Model(name='models/gemini-1.5-pro-latest',
      base_model_id='',
      version='001',
      display_name='Gemini 1.5 Pro Latest',
      description='Mid-size multimodal model that supports up to 1 million tokens',
      input_token_limit=1048576,
      output_token_limit=8192,
      supported_generation_methods=['generateContent', 'countTokens'],
      temperature=1.0,
      top_p=0.95,
      top_k=64)

Type of change

  • Dependency upgrade
  • Bugfix (non-breaking change which fixes an issue)
  • New integration (thank you!)
  • New feature (which adds functionality to an existing integration)
  • Deprecation (breaking change to happen in the future)
  • Breaking change (fix/feature causing existing functionality to break)
  • Code quality improvements to existing code or addition of tests

Additional information

  • This PR fixes or closes issue: fixes #
  • This PR is related to issue:
  • Link to documentation pull request:

Checklist

  • The code change is tested and works locally.
  • Local tests pass. Your PR cannot be merged unless tests pass
  • There is no commented out code in this PR.
  • I have followed the development checklist
  • I have followed the perfect PR recommendations
  • The code has been formatted using Ruff (ruff format homeassistant tests)
  • Tests have been added to verify that the new code works.

If user exposed functionality or configuration variables are added/changed:

If the code communicates with devices, web services, or third-party tools:

  • The manifest file has all fields filled out correctly.
    Updated and included derived files by running: python3 -m script.hassfest.
  • New or updated dependencies have been added to requirements_all.txt.
    Updated by running python3 -m script.gen_requirements_all.
  • For the updated dependencies - a link to the changelog, or at minimum a diff between library versions is added to the PR description.
  • Untested files have been added to .coveragerc.

To help with the load of incoming pull requests:

@home-assistant
Copy link

Hey there @tronikos, mind taking a look at this pull request as it has been labeled with an integration (google_generative_ai_conversation) you are listed as a code owner for? Thanks!

Code owner commands

Code owners of google_generative_ai_conversation can trigger bot actions by commenting:

  • @home-assistant close Closes the pull request.
  • @home-assistant rename Awesome new title Renames the pull request.
  • @home-assistant reopen Reopen the pull request.
  • @home-assistant unassign google_generative_ai_conversation Removes the current integration label and assignees on the pull request, add the integration domain after the command.
  • @home-assistant add-label needs-more-information Add a label (needs-more-information, problem in dependency, problem in custom component) to the pull request.
  • @home-assistant remove-label needs-more-information Remove a label (needs-more-information, problem in dependency, problem in custom component) on the pull request.

@balloob balloob merged commit 0cf574d into dev May 29, 2024
24 checks passed
@balloob balloob deleted the update-google-genai-default branch May 29, 2024 01:21
raman325 added a commit to raman325/home-assistant that referenced this pull request May 29, 2024
* dev: (751 commits)
  Use runtime_data in ping (home-assistant#118332)
  Fix last_reported_timestamp not being updated when last_reported is changed (home-assistant#118341)
  Replace pop calls with del where the result is discarded in restore_state (home-assistant#118339)
  Improve websocket message coalescing to handle thundering herds better (home-assistant#118268)
  Add cache to more complex entity filters (home-assistant#118344)
  Reduce the intent response data sent to LLMs (home-assistant#118346)
  Small speed up to connecting dispatchers (home-assistant#118342)
  Tweak Assist LLM API prompt (home-assistant#118343)
  Add Conversation command to timers (home-assistant#118325)
  LLM Assist API to ignore intents if not needed for exposed entities or calling device (home-assistant#118283)
  Replace pop calls with del where the result is discarded in entity (home-assistant#118340)
  Replace pop calls with del where the result is discarded in mqtt (home-assistant#118338)
  Use del instead of pop in the entity platform remove (home-assistant#118337)
  Update the recommended model for Google Gen AI (home-assistant#118323)
  Fix source_change not triggering an update (home-assistant#118312)
  Several fixes for the Matter climate platform (home-assistant#118322)
  Use None default for traccar server battery level sensor (home-assistant#118324)
  [esphome] 100% voice assistant test coverage (home-assistant#118334)
  Mark sonos group update a background task (home-assistant#118333)
  Filter timers more when pausing/unpausing (home-assistant#118331)
  ...
raman325 added a commit to raman325/home-assistant that referenced this pull request May 29, 2024
* dev: (8244 commits)
  Update zwave_js WS APIs for provisioning (home-assistant#117400)
  Add OSO Energy binary sensors (home-assistant#117174)
  Add august open action (home-assistant#113795)
  Add smoke detector temperature to Yale Smart Alarm (home-assistant#116306)
  Don't report entities with invalid unique id when loading the entity registry (home-assistant#118290)
  Fix epic_games_store mystery game URL (home-assistant#118314)
  Use runtime_data in ping (home-assistant#118332)
  Fix last_reported_timestamp not being updated when last_reported is changed (home-assistant#118341)
  Replace pop calls with del where the result is discarded in restore_state (home-assistant#118339)
  Improve websocket message coalescing to handle thundering herds better (home-assistant#118268)
  Add cache to more complex entity filters (home-assistant#118344)
  Reduce the intent response data sent to LLMs (home-assistant#118346)
  Small speed up to connecting dispatchers (home-assistant#118342)
  Tweak Assist LLM API prompt (home-assistant#118343)
  Add Conversation command to timers (home-assistant#118325)
  LLM Assist API to ignore intents if not needed for exposed entities or calling device (home-assistant#118283)
  Replace pop calls with del where the result is discarded in entity (home-assistant#118340)
  Replace pop calls with del where the result is discarded in mqtt (home-assistant#118338)
  Use del instead of pop in the entity platform remove (home-assistant#118337)
  Update the recommended model for Google Gen AI (home-assistant#118323)
  ...
raman325 added a commit to raman325/home-assistant that referenced this pull request May 29, 2024
* dev: (1785 commits)
  Update zwave_js WS APIs for provisioning (home-assistant#117400)
  Add OSO Energy binary sensors (home-assistant#117174)
  Add august open action (home-assistant#113795)
  Add smoke detector temperature to Yale Smart Alarm (home-assistant#116306)
  Don't report entities with invalid unique id when loading the entity registry (home-assistant#118290)
  Fix epic_games_store mystery game URL (home-assistant#118314)
  Use runtime_data in ping (home-assistant#118332)
  Fix last_reported_timestamp not being updated when last_reported is changed (home-assistant#118341)
  Replace pop calls with del where the result is discarded in restore_state (home-assistant#118339)
  Improve websocket message coalescing to handle thundering herds better (home-assistant#118268)
  Add cache to more complex entity filters (home-assistant#118344)
  Reduce the intent response data sent to LLMs (home-assistant#118346)
  Small speed up to connecting dispatchers (home-assistant#118342)
  Tweak Assist LLM API prompt (home-assistant#118343)
  Add Conversation command to timers (home-assistant#118325)
  LLM Assist API to ignore intents if not needed for exposed entities or calling device (home-assistant#118283)
  Replace pop calls with del where the result is discarded in entity (home-assistant#118340)
  Replace pop calls with del where the result is discarded in mqtt (home-assistant#118338)
  Use del instead of pop in the entity platform remove (home-assistant#118337)
  Update the recommended model for Google Gen AI (home-assistant#118323)
  ...
@github-actions github-actions bot locked and limited conversation to collaborators May 30, 2024
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants