- Fix unused imports in test_batch_mode.py
- Update Google GenAI API calls to use correct client.batches methods
- Add proper type annotations and error handling
- Ensure compatibility with google-generativeai SDK
Co-Authored-By: João <joao@crewai.com>
- Add google-generativeai dependency to pyproject.toml
- Extend LLM class with batch mode parameters (batch_mode, batch_size, batch_timeout)
- Implement batch request management methods for Gemini models
- Add batch-specific event types (BatchJobStartedEvent, BatchJobCompletedEvent, BatchJobFailedEvent)
- Create comprehensive test suite for batch mode functionality
- Add example demonstrating batch mode usage with cost savings
- Support inline batch requests for up to 50% cost reduction on Gemini models
Resolves issue #3116
Co-Authored-By: João <joao@crewai.com>
