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
..
2025-08-21 19:11:31 +05:30
2025-08-28 17:48:12 +08:00
2025-06-10 18:08:27 +08:00
2025-04-23 19:02:39 +08:00
2025-06-18 19:05:44 +02:00
2025-01-22 20:51:46 +08:00
2025-08-17 19:45:23 +08:00
2025-09-09 12:49:55 +08:00
2025-07-09 09:41:03 +02:00
2025-05-17 19:03:51 +08:00
2025-08-14 18:21:24 +08:00
2025-05-16 21:44:56 +08:00
2025-05-17 19:03:51 +08:00
2025-07-08 15:48:40 +02:00