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

backend/requirements.txt

@@ -5,3 +5,4 @@ soundfile==0.12.1
 python-multipart==0.0.6
 pydantic==2.5.3
 numpy==1.26.3
+httpx==0.26.0