ntohidi
3bc56dd028
fix: allow custom LLM providers for adaptive crawler embedding config. ref: #1291
- Change embedding_llm_config from Dict to Union[LLMConfig, Dict] for type safety
- Add backward-compatible conversion property _embedding_llm_config_dict
- Replace all hardcoded OpenAI embedding configs with configurable options
- Fix LLMConfig object attribute access in query expansion logic
- Add comprehensive example demonstrating multiple provider configurations
- Update documentation with both LLMConfig object and dictionary usage patterns
Users can now specify any LLM provider for query expansion in embedding strategy:
- New: embedding_llm_config=LLMConfig(provider='anthropic/claude-3', api_token='key')
- Old: embedding_llm_config={'provider': 'openai/gpt-4', 'api_token': 'key'} (still works)
2025-09-09 12:49:55 +08:00
..
2025-06-10 18:08:27 +08:00
2025-02-21 19:55:02 +08:00
2025-08-17 19:45:23 +08:00
2025-04-29 23:04:32 +08:00
2024-12-31 19:45:02 +08:00
2025-09-09 12:49:55 +08:00
2025-09-09 12:49:55 +08:00
2025-07-17 11:35:16 +02:00
2025-03-07 23:14:11 +08:00
2025-04-10 23:22:38 +08:00