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
..
2025-09-09 12:49:55 +08:00
2025-04-14 23:00:47 +08:00
2025-08-06 15:03:30 +08:00
2025-07-23 09:47:18 +02:00
2025-01-07 20:49:50 +08:00
2025-04-14 12:16:31 +02:00
2025-08-04 19:02:01 +08:00
2025-08-06 15:19:37 +08:00
2025-08-28 17:48:12 +08:00
2025-08-26 16:44:07 +08:00
2025-08-06 15:03:30 +08:00
2025-05-25 10:02:13 +08:00
2025-07-17 16:59:10 +08:00
2025-08-05 23:29:19 +05:30
2025-06-08 18:34:05 +08:00
2025-07-08 11:46:24 +02:00
2025-07-08 12:24:33 +02:00
2025-06-29 20:41:37 +08:00
2025-08-21 19:11:31 +05:30
2025-06-08 11:33:28 +08:00
2025-08-14 18:21:24 +08:00
2025-08-13 18:16:46 +05:30