3 Commits

Author	SHA1	Message	Date
Paul Bailey	b48e53ce63	Fix Ollama model name to use llama3:latest instead of llama3:8b ... - Changed model from 'llama3:8b' to 'llama3:latest' to match available models - Verified Ollama integration is working correctly - AI detection now successfully identifies speakers in unmarked text	2025-12-09 10:54:05 +00:00
Paul Bailey	73dc5695ca	Improve Ollama speaker detection with multi-sample strategy ... - Sample up to 4 chunks of 5000 characters from different text positions - Distribute samples evenly across beginning, middle, and end of text - Deduplicate speakers across all samples for comprehensive detection - Log individual sample results for debugging - Handle short texts efficiently (single sample) - Updated tests to verify multi-sample behavior This ensures speakers introduced anywhere in long texts are detected, not just those appearing in the first 2000 characters.	2025-12-09 10:40:59 +00:00
Paul Bailey	a8802fd765	Implement Ollama integration service for AI-based speaker detection ... - Created OllamaService class with httpx for API communication - Implemented detect_speakers() method with structured prompts - Added JSON response parser supporting multiple formats - Implemented is_available() health check method - Added 30-second timeout handling - Configured OLLAMA_BASE_URL environment variable - Added comprehensive unit tests with 100% coverage - Updated requirements.txt with httpx dependency Requirements: 14.1, 14.2, 14.3, 14.6	2025-12-09 10:35:30 +00:00