Implement local LLM inference support for Ollama and LM Studio:
New Clients:
- OllamaClient: Interface to Ollama API (default: localhost:11434)
- LMStudioClient: Interface to LM Studio API (default: localhost:1234)
Factory Updates:
- Added OLLAMA and LMSTUDIO to LLMProvider enum
- Updated create_client() to instantiate local clients
- Updated list_available_providers() with is_local flag
Configuration:
- Added ollama_base_url and lmstudio_base_url settings
- Local providers return configured for API key check
Tests:
- Comprehensive test suite (250+ lines)
- Tests for client initialization and invocation
- Factory integration tests
Documentation:
- Added LLM Providers section to SKILL.md
- Documented setup for Ollama and LM Studio
- Added usage examples and configuration guide
Usage:
provider: ollama, model: llama3.2
provider: lmstudio, model: local-model
Update documentation to reflect new integration features:
README.md:
- Add 'Integrazione NotebookLM + RAG' section after Overview
- Update DocuMente component section with new endpoints
- Add notebooklm_sync.py and notebooklm_indexer.py to architecture
- Add integration API examples
- Add link to docs/integration.md
SKILL.md:
- Add RAG Integration to Capabilities table
- Update Autonomy Rules with new endpoints
- Add RAG Integration section to Quick Reference
- Add Sprint 2 changelog with integration features
- Update Skill Version to 1.2.0
docs/integration.md (NEW):
- Complete integration guide with architecture diagram
- API reference for all sync and query endpoints
- Usage examples and workflows
- Best practices and troubleshooting
- Performance considerations and limitations
- Roadmap for future features
All documentation now accurately reflects the unified
NotebookLM + RAG agent capabilities.
