WeKnora/internal/tracing/langfuse
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
..
asynq.go feat(tracing): migrate langfuse client to OTLP/OTel wire protocol 2026-07-17 16:30:45 +08:00
asynq_test.go feat(tracing): migrate langfuse client to OTLP/OTel wire protocol 2026-07-17 16:30:45 +08:00
config.go feat(tracing): migrate langfuse client to OTLP/OTel wire protocol 2026-07-17 16:30:45 +08:00
config_test.go feat(observability): integrate Langfuse for LLM token tracking and tracing 2026-04-24 10:29:19 +08:00
context.go fix(observability): nest follow-up completions under the chat trace 2026-08-31 19:42:32 +08:00
events.go feat(llm): add prompt-cache observability and wiki cache-friendly prompts 2026-07-23 19:17:30 +08:00
exporter.go feat(tracing): migrate langfuse client to OTLP/OTel wire protocol 2026-07-17 16:30:45 +08:00
manager.go fix(tracing): merge Langfuse finish metadata and export auto root spans 2026-07-17 16:58:40 +08:00
manager_test.go feat(tracing): migrate langfuse client to OTLP/OTel wire protocol 2026-07-17 16:30:45 +08:00
memory_obs.go feat(memory): add cross-session long-term memory 2026-08-13 18:00:02 +08:00
memory_obs_test.go feat(memory): add cross-session long-term memory 2026-08-13 18:00:02 +08:00
middleware.go feat(tracing): migrate langfuse client to OTLP/OTel wire protocol 2026-07-17 16:30:45 +08:00
retrieval_obs.go fix(models): align configuration and multimodal embedding workflows (#4080) 2026-10-10 11:06:00 +08:00
retrieval_obs_test.go fix(models): align configuration and multimodal embedding workflows (#4080) 2026-10-10 11:06:00 +08:00
tracer.go fix(tracing): keep sandbox RPC spans under their owning operations 2026-09-12 10:15:54 +08:00
tracer_test.go fix(tracing): keep sandbox RPC spans under their owning operations 2026-09-12 10:15:54 +08:00