Commit Graph

6 Commits

Author SHA1 Message Date
Yeuoly f902504af0 feat: support multimodal embeddings (#237)
* Inline multimodal entities into existing models

* apply ruff

* bump to 0.7.0b1

* fix: remove tenant_id from invoke_multimodal_embedding

* tests: add rerank

* apply ruff

* fix

* fix: typing
2025-12-08 19:40:56 +08:00
Joe f1d201d9a8 fix: update request timeout to use environment configuration (#245) 2025-11-24 15:10:16 +08:00
Yeuoly ffbd309137 fix: add more test cases for model factory (#236) 2025-11-14 13:48:28 +08:00
Maries 569e68ac62 refactor: update model provider to use ModelFactory for instance mana… (#223)
* refactor: update model provider to use ModelFactory for instance management

* refactor: integrate ModelFactory for model instance mapping in tests

* refactor: remove unused imports and clean up test files
2025-10-20 14:27:20 +08:00
immortal-wm 2fc9753673 fix: corrected latency accuracy (#189)
* fix latency calc

* feat: add timing context management to AIModel for latency tracking

- Introduced a new TimingContextRaceConditionError to handle race conditions in multi-threaded environments.
- Implemented a timing_context method in AIModel to track request timing and prevent concurrent usage.
- Updated various model classes (LargeLanguageModel, ModerationModel, RerankModel, Speech2TextModel, TextEmbeddingModel, TTSModel) to utilize the new timing context for latency calculations.
- Added tests to validate timing context behavior under concurrent and sequential usage scenarios.

* feat: implement ModelFactory for dynamic model instance creation

- Added ModelFactory class to generate stateless model instances based on provider configurations and model classes.
- Updated PluginRegistration to utilize ModelFactory for managing model instances, enhancing code organization and maintainability.

* feat: add unit tests for model registry and mock model provider

- Introduced a new test file for validating model registry functionality.
- Implemented mock classes for model provider and LLM to facilitate testing.
- Added tests to ensure correct model instance retrieval from the registry.

* apply ruff

---------

Co-authored-by: Yeuoly <admin@srmxy.cn>
2025-09-16 16:15:20 +08:00
Vitor a39ec2c948 fix: incorrectly uses new_tool_call.function.name while getting existing tool calls (#104) 2025-04-25 14:00:23 +08:00