* Initial plan
* Add backend support for external knowledge bases
Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com>
* Add frontend support for external knowledge bases with tabs UI
Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com>
* Add i18n translations for all languages (Traditional Chinese and Japanese)
Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com>
* Update knowledge base tab list styling to match plugins page
Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com>
* perf: margin-top for kb page
* refactor: switch RetrievalResultEntry to langbot_plugin pkg ones
* feat: knowledge retriever listing and creating
* stash
* refactor: unify sync mechanism for polymorphic components
* feat: use unified retireval result struct in retrieval test page
* chore: remove unused methods
* feat: retriever icon displaying
* feat: localagent retrieval with external kbs
* chore: bump version of langbot-plugin to 0.2.0b1
* fix: i18n
---------
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com>
Co-authored-by: Junyan Qin <rockchinq@gmail.com>
* Initial plan
* feat: Add hover card with model details to embedding model selector in KB form
- Updated KBForm.tsx to fetch full EmbeddingModel objects instead of simplified entities
- Added HoverCard component to show model details (icon, description, base URL, extra args) when hovering over embedding model options
- Removed unused IEmbeddingModelEntity import and embeddingModelNameList state
- Made the embedding model selector consistent with LLM model selector behavior
Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com>
---------
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com>
* feat: add ZIP file upload support for knowledge base
- Add _parse_zip method to FileParser class using zipfile library
- Support extraction and processing of TXT, PDF, DOCX, MD, HTML files from ZIP
- Update FileUploadZone to accept .zip files
- Add ZIP format to supported formats in internationalization files
- Implement error handling for invalid ZIP files and unsupported content
- Follow existing async parsing patterns and error handling conventions
Co-Authored-By: Rock <rockchinq@gmail.com>
* refactor: modify ZIP processing to store each document as separate file
- Remove _parse_zip method from FileParser as ZIP handling now occurs at knowledge base level
- Add _store_zip_file method to RuntimeKnowledgeBase to extract and store each document separately
- Each document in ZIP is now stored as individual file entry in knowledge base
- Process ZIP files in memory using io.BytesIO to avoid filesystem writes
- Generate unique file names for extracted documents to prevent conflicts
Co-Authored-By: Rock <rockchinq@gmail.com>
* perf: delete temp files
---------
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Rock <rockchinq@gmail.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Junyan Qin <Chin>, u79E6u9A8Fu8A00 in Chinese, you can call me my english name Rock Chin. <rockchinq@gmail.com>
