WeKnora/internal/models/providers
lyingbug c3f077ed18
fix(models): align configuration and multimodal embedding workflows (#4080)
* fix(models): align configuration defaults and multimodal workflows

* feat(image): enhance image retrieval diagnostics and filtering

- Implemented `retrieveObservedImagePool` to observe engine calls and record image recall decisions without altering results.
- Added detailed diagnostics in `summarizeImagePool` and `summarizeImageCandidateCut` to track image filtering decisions and scores.
- Introduced tests for image pool diagnostics to ensure accurate filtering and decision recording.
- Updated existing functions to utilize new retrieval and summarization methods for improved observability and accuracy in image handling.

* feat(embeddings): enhance image handling with new formats and message support

- Introduced `EmbeddingImageFormat` to manage image input formats, allowing for both object and messages formats.
- Updated `EmbeddingsSettings` to include new fields for `ImageFormat`, `ImagePrompt`, and `TextAsMessages` to support multimodal embedding workflows.
- Enhanced `Client` methods to build request bodies for images in both formats, ensuring compatibility with vLLM's requirements.
- Added tests to validate the new image message handling and ensure correct request formatting for different scenarios.
- Updated documentation to reflect changes in image input handling and configuration options.

* feat(similarity): add embedding similarity mode for enhanced document scoring

- Introduced a new `similarity` option in `ModelDebugOptions` to score documents and an optional image against a query.
- Updated `ModelDebugDrawer.vue` to support a new input mode for similarity, allowing users to select similarity as an input type.
- Enhanced the UI to display similarity results, including ranked candidates based on cosine similarity.
- Added tests to validate the functionality of the new similarity mode in embedding models.
- Updated localization files to include new strings related to similarity mode in multiple languages.

* feat(embeddings): add Qwen3-VL-Embedding support for multimodal input

- Introduced Qwen3-VL-Embedding model with support for both text and image inputs.
- Updated model configuration files to include compatibility settings for the new embedding type.
- Enhanced tests to validate the functionality of Qwen3-VL-Embedding, ensuring correct handling of inputs and outputs.
- Updated documentation to reflect the new model's capabilities and usage instructions.

* test(models): wrap embedding assertions to satisfy lint

* test(opensearch): isolate HTTP transports between parallel tests
2026-10-10 11:06:00 +08:00
..
assets feat(rerank): support Pinecone Inference protocol (#3957) 2026-10-08 17:54:15 +08:00
aliyun.go fix(models): serve qwen3-rerank on the native DashScope rerank protocol 2026-09-24 14:18:55 +08:00
anthropic.go refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00
azure_openai.go refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00
builtin.go feat(rerank): support Pinecone Inference protocol (#3957) 2026-10-08 17:54:15 +08:00
compat.go refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00
deepseek.go refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00
definition.go refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00
gemini.go refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00
generic.go fix(models): align configuration and multimodal embedding workflows (#4080) 2026-10-10 11:06:00 +08:00
gpustack.go refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00
huggingface_tei.go feat(rerank): support Hugging Face TEI protocol (#3956) 2026-10-08 14:02:49 +08:00
hunyuan.go refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00
jina.go feat: judge image hits by their image in rerank and show them to vision models (#4013) 2026-10-09 13:01:48 +08:00
litellm.go refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00
lkeap.go refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00
longcat.go refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00
mimo.go refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00
minimax.go fix(models): align configuration and multimodal embedding workflows (#4080) 2026-10-10 11:06:00 +08:00
modelscope.go refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00
moonshot.go refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00
novita.go refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00
nvidia.go feat: judge image hits by their image in rerank and show them to vision models (#4013) 2026-10-09 13:01:48 +08:00
openai.go refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00
openrouter.go refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00
pinecone.go feat(rerank): support Pinecone Inference protocol (#3957) 2026-10-08 17:54:15 +08:00
providers_test.go fix(models): align configuration and multimodal embedding workflows (#4080) 2026-10-10 11:06:00 +08:00
qianfan.go refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00
qiniu.go refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00
requesty.go refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00
siliconflow.go refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00
volcengine.go refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00
weknoracloud.go refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00
zhipu.go refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00