Fix #213: [FEATURE] Gemini and Perplexity summarization model#215
Open
VedantKh wants to merge 1 commit intoZackriya-Solutions:mainfrom
Open
Fix #213: [FEATURE] Gemini and Perplexity summarization model#215VedantKh wants to merge 1 commit intoZackriya-Solutions:mainfrom
VedantKh wants to merge 1 commit intoZackriya-Solutions:mainfrom
Conversation
…tion model This commit adds support for Google Gemini and Perplexity AI as alternative summarization models for meeting transcripts. Backend changes: - Updated database schema to add geminiApiKey and perplexityApiKey columns to settings table - Added migration logic to handle existing databases - Updated save_api_key() and get_api_key() functions to support gemini and perplexity providers - Implemented Gemini model integration using GeminiModel and GeminiProvider from pydantic-ai - Implemented Perplexity model integration using OpenAI-compatible API - Updated transcript_processor.py to handle both new providers - Updated main.py to validate API keys for gemini and perplexity providers Frontend changes: - Updated ModelConfig interface to include 'gemini' and 'perplexity' as valid provider types - Added Gemini model options: gemini-2.0-flash-exp, gemini-exp-1206, gemini-2.0-flash-thinking-exp-1219, gemini-1.5-pro, gemini-1.5-flash, gemini-1.5-flash-8b - Added Perplexity model options: llama-3.1-sonar-small-128k-online, llama-3.1-sonar-large-128k-online, llama-3.1-sonar-huge-128k-online - Updated requiresApiKey check to include both new providers - Added UI options for Google Gemini and Perplexity in provider selection dropdown Users can now configure and use Gemini or Perplexity models for AI-powered meeting summarization by selecting the provider and entering their API key in the model settings. Co-Authored-By: Vedant Khanna <vedantkhanna@gmail.com>
Collaborator
|
The PR edits based on the python backend |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Fixes #213
Summary
This PR adds support for Google Gemini and Perplexity AI as alternative summarization models for meeting transcripts, addressing the feature request in issue #213.
Changes Made
Backend Changes
Frontend Changes
Files Modified
Testing
Users can now:
Link to Devin run
https://app.devin.ai/sessions/a03c6bf039d7469b99f9f34bc29a198d
Requested by
Vedant Khanna (vedantkhanna@gmail.com) - @VedantKh