Commit Graph

706 Commits

Author SHA1 Message Date
wizardchen 2b495c8232 refactor: Update wiki ingest service to support aliases in slug mapping
- Modified the `extractEntitiesAndConcepts` method to return a map of slugs to extracted items, including aliases for improved wiki-link generation.
- Updated the `processOneDocument` method to handle slug items with aliases, enhancing the clarity of generated summaries.
- Adjusted the `injectCrossLinks` method to utilize match text for cross-linking, ensuring accurate references in content.

These changes improve the accuracy and usability of wiki links and summaries by incorporating alias management.
2026-04-22 21:17:30 +08:00
wizardchen f07561f6b6 fix: resolve failing test and build errors
Made-with: Cursor
2026-04-22 21:17:29 +08:00
wizardchen d9cf4b7aa9 feat: implement metadata-based alias management for wiki pages
Made-with: Cursor
2026-04-22 21:17:29 +08:00
wizardchen 233c398d7a feat: Enhance image preview functionality in WikiBrowser component
- Updated the `picture-preview.vue` component to conditionally render images based on the `reviewUrl` prop, improving performance and usability.
- Integrated image preview functionality into the `WikiBrowser` component, allowing users to view images in a modal when clicked.
- Added references for `drawerBodyRef` and `readerBodyRef` to facilitate image loading and hydration, ensuring images are displayed correctly.
- Enhanced the `prompts_wiki.go` file to include new image handling rules for summaries, ensuring images are contextually relevant in generated content.

These changes improve the user experience by providing a seamless image viewing option within the WikiBrowser interface.
2026-04-22 21:17:28 +08:00
wizardchen 98e2464831 refactor: Enhance wiki ingest service with knowledge service integration and content sorting
- Introduced a new `knowledgeSvc` interface to the `wikiIngestService`, allowing for improved document title retrieval based on knowledge ID.
- Updated the document processing logic to prioritize titles from the knowledge service, enhancing accuracy.
- Refactored content reconstruction to sort chunks by `StartAt` and `ChunkIndex`, improving the organization of the final output.
- Added functionality to append image information at the end of the content, ensuring a cleaner text flow.

These changes improve the efficiency and clarity of the wiki ingest process, enhancing overall content management.
2026-04-22 21:17:27 +08:00
wizardchen 5d5073c96b refactor: Update wiki link syntax and rendering in WikiBrowser component
- Enhanced the `renderMarkdown` function to support the new `[[slug|display name]]` format for wiki links, improving link clarity and usability.
- Adjusted CSS styles for wiki links to provide a more intuitive hover effect and visual distinction.
- Updated prompts in the `prompts_wiki.go` file to reflect the new wiki link syntax, ensuring consistency across the application.

These changes improve the overall user experience by making wiki links more informative and visually appealing.
2026-04-22 21:17:26 +08:00
wizardchen 7eea22d655 refactor: Enhance wiki link generation in summary processing
- Updated the WikiSummaryPrompt to clarify the wiki-link syntax, specifying the use of slugs for referenced names.
- Modified the extractEntitiesAndConcepts method to return a mapping of slugs to display names, improving the accuracy of wiki-link references in summaries.
- Adjusted the summary content generation to include display names alongside slugs, enhancing the readability and context of generated summaries.

These changes improve the clarity and usability of wiki summaries by ensuring accurate and consistent link references.
2026-04-22 21:17:25 +08:00
wizardchen ec8a5fc392 refactor: Enhance wiki page management and index rebuilding
- Introduced a new method to list all wiki pages without pagination, facilitating index rebuilding and cross-linking.
- Updated the wiki ingest and retract processes to include document summaries, improving clarity in log entries and index updates.
- Enhanced the cleanup process for deleted knowledge, ensuring accurate summary retention and index regeneration.
- Streamlined the handling of page updates and deletions, optimizing the overall wiki management workflow.

These changes improve the efficiency and reliability of wiki content management and indexing.
2026-04-22 21:17:24 +08:00
wizardchen f00b2a176b refactor: Update EnqueueWikiIngest to utilize Redis for pending document management
- Modified the EnqueueWikiIngest function to accept a Redis client, enabling the use of a Redis list for managing pending wiki ingest documents.
- Introduced a debouncing mechanism to optimize task processing, ensuring that multiple rapid uploads are handled efficiently without unnecessary locks.
- Enhanced the overall architecture for better performance and reliability in handling wiki ingest tasks.

These changes streamline the ingestion process and improve the handling of concurrent document uploads.
2026-04-22 21:17:24 +08:00
wizardchen 3edd7548f4 refactor: Update step numbering in wiki_ingest service process 2026-04-22 21:17:23 +08:00
wizardchen 5e113ddba3 refactor: Remove detectSynthesisOpportunities function from wiki_ingest service
- Eliminated the detectSynthesisOpportunities function, which was responsible for suggesting synthesis opportunities based on page counts and types. This function was deemed unnecessary as it relied on heuristic methods without LLM integration.
- The removal streamlines the codebase and focuses on essential functionalities within the wiki_ingest service.

This change simplifies the service and prepares it for future enhancements that may involve more sophisticated synthesis logic.
2026-04-22 21:17:23 +08:00
wizardchen 4dff109d1b fix: Update wiki index rebuilding and log entry formatting
- Modified the `rebuildWikiIndexSimple` function to include `knowledgeID` in the parameters, ensuring accurate logging of deleted pages.
- Enhanced the log entry format in `appendLogEntry` to include the action type and improved timestamp formatting, providing clearer context for actions taken on wiki pages.
- Adjusted the `ProcessWikiRetract` and `ProcessWikiIngest` methods to align with the new log entry structure, ensuring consistency across logging actions.

These changes improve the clarity and accuracy of wiki activity logs, facilitating better tracking of content changes.
2026-04-22 21:17:23 +08:00
wizardchen 9be4152449 feat: Enhance search functionality in WikiPage repository and WikiBrowser component
- Updated the search logic in the WikiPage repository to use ILIKE for case-insensitive matching on title, content, summary, and slug fields, improving search accuracy.
- Added a watcher in the WikiBrowser component to reload all pages when the search query is cleared, enhancing user experience by ensuring relevant content is displayed immediately.

These changes collectively improve the search capabilities and responsiveness of the wiki interface.
2026-04-22 21:17:22 +08:00
wizardchen 0e28b2448c feat: Add arrow toggle functionality in WikiBrowser component
Implemented new features in the WikiBrowser component to allow users to toggle the visibility of arrows on graph edges. This includes:

1. **Localization Updates**: Added translations for "Show arrows" and "Hide arrows" in English, Korean, Russian, and Chinese.
2. **Graph Rendering Enhancements**: Introduced logic to dynamically update SVG line attributes based on the toggle state, improving visual clarity in graph representations.
3. **State Management**: Added reactive state management for arrow visibility, ensuring seamless user interaction.

These changes enhance the user experience by providing more control over graph visualizations.
2026-04-22 21:17:22 +08:00
wizardchen d4d005422d feat: Implement wiki_config updates in knowledge base management
Added functionality to enable updates for the `wiki_config` field in the `KnowledgeBaseConfig` struct. This includes:

1. **Type Definition Update**: Added `WikiConfig` field to `KnowledgeBaseConfig` to allow JSON unmarshaling during update requests.
2. **Service Layer Enhancement**: Updated the `UpdateKnowledgeBase` method to persist changes to `wiki_config` when provided in the request.
3. **Frontend TypeScript Adjustments**: Enhanced type definitions in the frontend to support `wiki_config`, improving IDE autocomplete and type checking.

This fix addresses the critical issue where `wiki_config` was not being updated due to its absence in the `KnowledgeBaseConfig` struct, ensuring proper handling of wiki configurations during knowledge base updates.
2026-04-22 21:17:21 +08:00
wizardchen 33da010605 feat: Implement deadlock retry mechanism for chunk creation
Added a new utility function, WithDeadlockRetry, to handle MySQL deadlock errors during chunk creation. This function retries the operation up to three times with exponential backoff. Updated the CreateChunks method to utilize this new function, ensuring robust handling of concurrent write scenarios and preventing potential deadlocks. Additionally, improved documentation for CreateChunks to clarify the use of Omit for avoiding auto-increment column issues.
2026-04-22 21:17:21 +08:00
wizardchen 749e8a0a19 feat: Implement content filter handling in agent response analysis
Added logic to the analyzeResponse function to handle cases where the LLM response is blocked by the content filter. This includes emitting events for the final answer and stopping the agent loop to prevent infinite responses. The implementation ensures that users receive a clear message when content is filtered, enhancing the agent's response management.
2026-04-22 21:17:21 +08:00
wizardchen e15adca0a6 fix: Enable wiki_config updates in knowledge base configuration
Implemented three critical fixes to enable wiki_config persistence during
KB creation and updates:

1. Add WikiConfig field to KnowledgeBaseConfig struct
   - File: internal/types/knowledgebase.go
   - Enables JSON unmarshaling of wiki_config from update requests
   - Previously the field was silently dropped during deserialization

2. Update UpdateKnowledgeBase service to persist wiki_config
   - File: internal/application/service/knowledgebase.go
   - Added logic to apply wiki_config changes when config parameter is provided
   - Mirrors existing logic for FAQConfig persistence

3. Update frontend TypeScript types for IDE completion
   - File: frontend/src/api/knowledge-base/index.ts
   - Added WikiConfig type to createKnowledgeBase function signature
   - Added structured WikiConfig type to updateKnowledgeBase config parameter
   - Enables TypeScript IDE autocomplete and type checking

Flow:
- Frontend: updateKnowledgeBase({name, description, config: {wiki_config}})
- Handler: Parses into UpdateKnowledgeBaseRequest via KnowledgeBaseConfig
- Service: Applies wiki_config to KB entity via UpdateKnowledgeBase
- Database: Persists wiki_config JSONB field to postgres

Root cause analysis:
Previously, the KnowledgeBaseConfig struct was missing the WikiConfig field,
causing JSON unmarshaling to silently drop any wiki_config data sent in
PUT requests. KB creation worked because it used the full KnowledgeBase struct.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-22 21:17:20 +08:00
wizardchen 16a0bff7bd feat: Enhance wiki functionality with recent activity log
This commit introduces a new "Recent Activity" section in the WikiBrowser component, allowing users to view the latest changes made to the wiki. The implementation includes:

- Addition of a toggleable recent activity log displaying the last five entries.
- Backend support for fetching the activity log from the knowledge base.
- Updates to the wiki ingest process to ensure draft pages are published post-ingest.
- Improvements to the deduplication process for entities and concepts during wiki page creation.

These enhancements aim to improve user engagement and provide better insights into wiki updates.
2026-04-22 21:17:19 +08:00
wizardchen e147209e77 feat: Implement comprehensive wiki feature for knowledge bases
This commit introduces the complete wiki feature for WeKnora, enabling AI-powered wiki page generation and management. The implementation includes:

**Backend Changes:**
- Wiki data model: WikiPage type with support for multiple page types (Summary, Entity, Concept, Index, Log)
- Database schema: wiki_pages table with full migration support
- WikiPageService: CRUD operations and page management
- WikiPageRepository: GORM-based persistence layer
- Wiki ingest pipeline: Automated generation of wiki pages from knowledge documents
  * Summary page generation using LLM
  * Entity and concept extraction in a single LLM call
  * Synthesis opportunity detection
  * Index page rebuilding
  * Log page maintenance
- Wiki boost feature: Enhance chat retrieval with wiki context
- Wiki linting: Maintenance and validation utilities
- Agent wiki tools: Enable agents to query and interact with wiki pages
- Wiki prompts: Comprehensive LLM prompt templates for all wiki generation tasks
- Language support: Reuse existing middleware language infrastructure for LLM prompts

**Frontend Changes:**
- Wiki browser UI: View all wiki pages with filtering and search
- Wiki API client: Knowledge base wiki management endpoints
- Knowledge base editor: Configure wiki settings (language, auto-ingest, synthesis model)
- i18n updates: Support for English, Korean, Russian, and Chinese interfaces

**Configuration:**
- Container DI: Wire up all wiki services
- Router: Register wiki API endpoints
- Task handling: Support async wiki ingest tasks

**Testing:**
- Unit tests for wiki page types
- Service layer tests
- Endpoint tests for wiki operations
- Integration tests with LLM mocking

**Documentation:**
- Language refactoring analysis and guides
- Implementation completion reports
- Quick reference guides for developers

**Key Features:**
✅ LLM-powered wiki page generation from documents
✅ Multi-language support (9+ languages)
✅ Automatic extraction of entities and concepts
✅ Synthesis opportunity detection
✅ Index and log page maintenance
✅ Progressive wiki building across multiple documents
✅ Agent-based wiki interaction
✅ Chat retrieval enhancement with wiki context
✅ Full frontend UI for wiki browsing

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-22 21:17:18 +08:00
wizardchen 095ccaed10 refactor: Replace hardcoded language logic with middleware infrastructure
- Refactor wiki_ingest.go to use types.LanguageLocaleName() instead of hardcoded if-else
- Supports 9+ languages (Chinese, English, Korean, Japanese, Russian, French, German, Spanish, Portuguese)
- Reduces 7 lines to 4 lines (43% reduction in code)
- Eliminates code duplication by reusing existing middleware infrastructure
- Consistent naming with middleware layer ("Chinese (Simplified)" format)
- Add comprehensive unit tests for LanguageLocaleName() (30 test cases)
- Add implementation guide, analysis, and completion documentation

Benefits:
- Single source of truth for language mappings (types.LanguageLocaleName)
- Better code maintainability and consistency
- No breaking changes or schema modifications required
- Performance: ~4.3ns per call, no measurable impact
- All tests passing, build successful

Files modified:
- internal/application/service/wiki_ingest.go: Refactored language determination (line 139)
- internal/types/context_helpers_test.go: Added 30 unit test cases (NEW)
- Documentation: Added LANGUAGE_MIDDLEWARE_ANALYSIS.md, LANGUAGE_REFACTORING_COMPLETED.md, IMPLEMENTATION_GUIDE.md, REFACTORING_SUMMARY.txt

Refs: LANGUAGE_MIDDLEWARE_ANALYSIS.md

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-22 21:17:17 +08:00
nullkey 4939011b0d fix(feishu): truncate sanitized filenames at UTF-8 rune boundary
Raw byte truncation at 200 bytes splits multi-byte codepoints (Chinese
characters are 3 bytes), producing invalid UTF-8 that downstream filename
validation (utf8.ValidString) rejects with "文件名包含非法字符". Peel
trailing bytes via DecodeLastRuneInString until the last rune is complete.

Same latent bug and fix as the Yuque connector's sanitizeFileName.
2026-04-22 16:39:55 +08:00
nullkey 656b07027a feat(datasource): add Yuque (语雀) connector
Syncs personal and team Yuque knowledge bases into WeKnora as Markdown,
with full and incremental sync + deletion detection. Mirrors the Feishu
connector pattern; fetches V2Doc.body directly (no async export step).

Config: api_token (required) + base_url (optional, defaults to public cloud).
401/403 wraps ErrInvalidCredentials; 429 honors Retry-After; filters to
status=1 Doc-type at list stage to conserve API quota. Body is trusted as
Markdown for format=markdown|lake — empirically verified against the v2
API: Lake XML lives separately in body_lake, body itself is the Markdown
view. Other formats (e.g. html) are skipped with a placeholder item so
they surface in sync logs instead of silently feeding HTML to the parser.

v2Doc.status accepts both int and string shapes — Yuque's OpenAPI spec
declares string but the live API returns int. sanitizeFileName truncates
at a UTF-8 rune boundary so multi-byte titles don't emit invalid UTF-8
that downstream filename validation rejects.

Also adds logger.SetOutput test hook, used by the token-redaction test.
2026-04-22 16:39:55 +08:00
draix 5591c84e7f fix: remove limit/offset from required in list_knowledge_chunks JSON Schema
limit and offset are optional parameters with default values (limit=20,
offset=0). Marking them as required in the JSON Schema forces LLM clients
to always supply them, breaking calls that rely on the defaults.

Fixes #1003
2026-04-21 23:27:14 +08:00
moineye 4ca0c7a644 fix: ReadEvent incompatible sse data format 2026-04-20 22:29:38 +08:00
jw_mac 09e1642335 fix(storage): auto-detect content-type to resolve image rendering issues
Fixes #995. Added mime type detection in SaveBytes for MinIO, OSS, S3, and TOS to prevent images from being incorrectly saved as text/csv.
2026-04-20 21:59:54 +08:00
ochan.kwon 127654ee78 feat: add vector_store_id column to knowledge_bases for per-KB vector store binding 2026-04-20 19:53:44 +08:00
Mao Meng e3b493e316 fix: use constant-time comparison for API key validation 2026-04-19 21:41:22 +08:00
ochan.kwon 8fd1d61333 feat: add VectorStore management UI settings page 2026-04-17 21:51:25 +08:00
ochan.kwon 927d3debff feat: pass IndexConfig to repositories with scalability options 2026-04-17 16:52:24 +08:00
hjz 7bd36bf954 feat: search engine adds proxy addresses and adds SSRF verification. 2026-04-17 16:38:02 +08:00
wizardchen 092044b68f refactor(postgres): optimize vector retrieval and HNSW settings
- Adjusted the expanded TopK limit to a maximum of 200 candidates to enhance HNSW efficiency.
- Updated the vector retrieval query to ensure the ORDER BY expression matches the indexed expression, improving index usage.
- Implemented local settings for HNSW's ef_search and iterative_scan within a transaction to optimize candidate retrieval.
- Added fallback logic to handle unsupported GUCs gracefully, ensuring query execution continues even with older pgvector versions.

These changes improve the performance and reliability of vector retrieval in the PostgreSQL implementation.
2026-04-17 12:11:03 +08:00
wizardchen d546406a15 feat(output): enhance output formatting to XML for various tools
- Updated the formatKnowledgeBaseList function to return knowledge base information as XML, improving data structure for integration.
- Modified the formatOutput function in GrepChunksTool to format search results as XML, enhancing readability and consistency.
- Adjusted the formatOutput method in KnowledgeSearchTool to output search results in XML format, providing a structured response.
- Refactored the buildOutput function in ListKnowledgeChunksTool to generate XML output, improving the clarity of chunk information.

These changes standardize output formats across multiple tools, facilitating better data handling and integration.
2026-04-17 12:11:03 +08:00
ochan.kwon c5fc05f3d0 feat: add registry dual-map and engine factory for VectorStore
- Extend RetrieveEngineRegistry with byStoreID map for DB store engines
- Add StoreRegistry interface and EngineFactory function type
- Create engine factory with per-driver SDK client construction
- Load VectorStore records from DB into registry at startup
- Wire Create/Delete to dynamically register/unregister engines
- Add comprehensive unit tests for registry and service
2026-04-17 00:15:37 +08:00
wizardchen 4f55994266 feat(prompt): enhance question rewriting and intent classification in prompt templates
- Updated the prompt template to clarify the task of understanding and rewriting user questions, improving the instructions for coreference resolution and ellipsis completion.
- Renamed sections for better clarity, changing "Rewriting Goals" to "Query Understanding."
- Added critical notes for intent classification regarding image and document attachments, ensuring accurate processing based on the presence of attachments.
- Improved examples to reflect the updated intent classification logic, enhancing the overall user experience in query handling.
2026-04-16 23:15:02 +08:00
wizardchen 53e8e17df4 feat(logger): implement LLM debug logging functionality
- Added a new logger for LLM calls, enabling detailed logging of model interactions, including request and response data.
- Introduced configuration options for enabling and specifying the log directory for LLM debug logs.
- Implemented cleanup for old log files to manage disk space effectively.
- Wrapped existing chat implementations to log calls when debug logging is enabled, enhancing traceability for model interactions.
2026-04-16 23:15:02 +08:00
wizardchen 6235a82183 Fix logger format string errors in system handler 2026-04-16 18:39:30 +08:00
wizardchen dcb7fd05b1 Fix compile error in weaviate repository 2026-04-16 18:37:31 +08:00
wizardchen 92b6b7507d refactor(chunk): improve parent-child chunk relationship handling in SplitTextParentChild
- Updated the SplitTextParentChild function to maintain a newParents slice, ensuring accurate parent indexing when splitting text into child chunks.
- This change enhances the integrity of parent-child relationships by correctly associating child chunks with their respective parents, improving overall chunk processing.
2026-04-16 18:29:33 +08:00
wizardchen 491c324197 feat(system): remove MinIO list buckets API and UI dependencies 2026-04-16 18:13:21 +08:00
wizardchen a560497ee8 feat(tenant): add storage bucket uniqueness validation for tenant creation and updates
- Implemented a new method to validate the uniqueness of storage bucket names across tenants, ensuring no two tenants can use the same bucket name.
- Integrated this validation into the CreateTenant and UpdateTenant methods, enhancing data isolation and preventing potential conflicts.
- Improved error logging for better traceability when validation fails.

This update strengthens the integrity of tenant storage configurations.
2026-04-16 18:13:20 +08:00
wizardchen af58e9cff4 fix(repository): ensure expandedTopK is at least params.TopK in VectorRetrieve
- Added a check to set expandedTopK to params.TopK if it is lower, ensuring the subquery limit is not less than the final limit.
- Removed unnecessary type casting in the SQL query for embedding distance calculations, simplifying the query structure.

This update improves the accuracy of vector retrieval operations in the PostgreSQL repository.
2026-04-16 18:13:20 +08:00
wizardchen a1a07e6818 Refactor knowledge post-processing into orchestrator task
Introduce KnowledgePostProcess task to decouple image multimodal
processing from downstream operations like summary, question
generation, and knowledge graph extraction.

This allows unifying the processing logic across documents and
images and ensures all text content, including from images,
is properly extracted before post-processing.
2026-04-16 18:13:20 +08:00
wizardchen 7c40fb6ac9 feat: enhance URL validation and timeout handling in knowledge base components
- Added isValidURL function to validate URLs before rendering links in the document content component, preventing invalid links from being clickable.
- Refactored timeout handling in KnowledgeBase.vue to use setTimeout instead of setInterval, improving performance and resource management.
- Ensured that timeouts are cleared appropriately to avoid memory leaks and unnecessary polling.

This update improves the robustness of URL handling and optimizes the component's performance.
2026-04-16 18:13:19 +08:00
wizardchen a78182cfc7 feat(handler): validate bucket name format and improve MinIO error handling
- Added validation for bucket name format to ensure it meets specified criteria, returning an error message for invalid formats.
- Simplified error messages for MinIO client creation and bucket auto-creation failures, enhancing clarity for users.
- Updated success messages to reflect the correct status of bucket creation without public-read policy settings.

This update improves the robustness of the MinIO integration and enhances user feedback during storage checks.
2026-04-16 18:13:19 +08:00
swim2sun d2c6814f22 fix: SQLite/Lite mode compatibility for FAQ import and chunk operations
Multiple fixes for WeKnora Lite mode (SQLite, no Redis):

1. Redis nil pointer panic on FAQ import (knowledge.go)
   - Add in-memory fallback (sync.Map) for FAQ import progress tracking
   - Add nil guards for running task locks and progress queries

2. seq_id not auto-incrementing in SQLite (chunk.go, tag.go)
   - GORM autoIncrement on non-PK columns doesn't work in SQLite
   - Add AssignChunkSeqIDs() to pre-assign seq_ids before batch insert
   - Add BeforeCreate hook for KnowledgeTag
   - Use Unscoped() to include soft-deleted records in MAX(seq_id) query

3. NOW() function not available in SQLite (chunk.go)
   - Replace raw SQL NOW() with time.Now() or datetime('now')
   - Use dialector check for raw SQL that must differ between PG and SQLite

4. FAQ KB should reject file uploads (knowledge.go)
   - Add kb.Type == "faq" check in CreateKnowledgeFromFile

5. Linux/macOS build compatibility (Makefile)
   - Conditionally apply macOS-only linker flag based on uname

6. Add SQLite integration tests (chunk_sqlite_test.go)
   - TestCreateChunks_SQLite_SeqIDAutoAssigned
   - TestCreateChunks_SQLite_SeqIDContinuesFromExisting
   - TestCreateChunks_SQLite_SeqIDUniqueAcrossKBs
   - TestCreateChunks_SQLite_SeqIDAfterSoftDelete
   - TestKnowledgeTag_SQLite_SeqIDAutoAssigned
   - TestUpdateChunk_SQLite_NoNOWError

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-15 20:37:10 +08:00
moineye 5000e6e665 fix: missing deep copy entity 2026-04-15 20:35:48 +08:00
ugurtafrali 38077d6ccd Fix system prompt not being used when flag is false 2026-04-15 20:21:12 +08:00
wizardchen 9bb4a12562 feat(repository): update keyword retrieval logic to use ParadeDB's matching operator
- Modified the SQL clause in the KeywordsRetrieve function to utilize ParadeDB's ||| operator for improved token matching.
- Enhanced the handling of retrieval results in the fuseOrDeduplicate function to maintain original scores for keyword-only results, ensuring better performance in FAQ scenarios.

This update optimizes the keyword retrieval process and improves the accuracy of search results.
2026-04-15 20:16:02 +08:00
wizardchen 9ba8582f70 feat(weknoracloud): implement WeKnoraCloud VLM integration
- Added WeKnoraCloudVLM struct to handle interactions with the WeKnoraCloud API, including image and text processing capabilities.
- Enhanced model configuration to include AppID and AppSecret for secure API access.
- Updated modelService to resolve WeKnoraCloud credentials and pass them to the VLM configuration.
- Implemented Predict method for sending requests to the WeKnoraCloud API and processing responses.

This update introduces a new integration with WeKnoraCloud, expanding the application's capabilities in handling multimedia content.
2026-04-15 15:43:08 +08:00