WeKnora/website-docs/03-features
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
..
01-tenant-auth.md feat(auth): 新增仅限邀请注册档位 (#3900) 2026-09-30 13:32:55 +08:00
02-knowledge-base.md feat: index and recall images with multimodal embedding models (#3683) 2026-10-08 18:19:53 +08:00
03-document-parsing.md fix(docparser): 云解析超时改为跟随既有配置,不再硬编码 (#3891) 2026-10-08 14:02:42 +08:00
04-chunking.md docs: sync website-docs, homepage and changelog for v0.8.2 (#3632) 2026-09-24 11:26:34 +08:00
05-retrieval-engines.md fix(retrieval): fix recall correctness, score scales, cost and agent tools (#3687) 2026-09-25 10:48:18 +08:00
06-models.md fix(models): align configuration and multimodal embedding workflows (#4080) 2026-10-10 11:06:00 +08:00
07-agent.md fix(data-analysis): skip style-only worksheets before DuckDB loading (#3660) 2026-10-08 13:04:29 +08:00
08-mcp.md fix(mcp): report advertised directory failures in connection tests (#3905) 2026-10-09 12:01:27 +08:00
09-knowledge-graph.md docs: sync website-docs, homepage and changelog for v0.8.2 (#3632) 2026-09-24 11:26:34 +08:00
10-datasource.md feat(datasource/dingtalk): 摄取钉钉"上传文件"(docx/pptx/xlsx/pdf) (#3786) 2026-10-09 10:56:04 +08:00
11-web-search.md fix(agent): align web_search count limit with the configured maximum (#4011) 2026-10-10 10:27:52 +08:00
12-im-integration.md revert: take the plugin system back out of main 2026-09-26 14:58:18 +08:00
13-embed-channel.md docs: sync website-docs, homepage and changelog for v0.8.2 (#3632) 2026-09-24 11:26:34 +08:00
14-wiki.md docs: sync website-docs, homepage and changelog for v0.8.2 (#3632) 2026-09-24 11:26:34 +08:00
15-evaluation.md docs: sync website-docs, homepage and changelog for v0.8.2 (#3632) 2026-09-24 11:26:34 +08:00
16-observability.md docs: sync website-docs, homepage and changelog for v0.8.2 (#3632) 2026-09-24 11:26:34 +08:00
17-faq.md fix(retrieval): fix recall correctness, score scales, cost and agent tools (#3687) 2026-09-25 10:48:18 +08:00
18-chat-experience.md feat(chat): open cited documents at the cited passage (#3700) 2026-09-25 13:26:16 +08:00
19-storage-backends.md docs: sync website-docs, homepage and changelog for v0.8.2 (#3632) 2026-09-24 11:26:34 +08:00
20-platform-admin.md feat(models): add system admin model catalog console (#3662) 2026-09-24 16:31:45 +08:00
21-file-access.md docs: sync website-docs, homepage and changelog for v0.8.2 (#3632) 2026-09-24 11:26:34 +08:00
22-skills-sandbox.md feat(ui): add search to Skills and MCP toolbox lists (#3731) 2026-10-08 01:27:51 +08:00
23-memory.md docs: sync website-docs, homepage and changelog for v0.8.2 (#3632) 2026-09-24 11:26:34 +08:00
24-feishu-drive.md docs: 迁移有效文档至 website-docs 并清理旧文档 (#3580) 2026-09-22 23:25:40 +08:00
25-seafile.md feat(datasource): add Seafile data source connector (#3616) 2026-10-08 16:18:09 +08:00