frontend, session, cli, auth, knowledge-base, embedding, RBAC, OBS
Release history
WeKnora releases
LLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using RAG paradigm.
All releases
18 shown
- Prevent API key ciphertext (enc:v1:...) from leaking to the UI
- Add STORAGE_ALLOW_LIST env var to whitelist storage origins
- Tenant-wide IM channels overview under the user menu
- Expose API Key reset from the API Info page
Full changelog
What's Changed
- docs(readme): enhance layout for Agent Mode and Observability sections across multiple languages by @lyingbug in https://github.com/Tencent/WeKnora/pull/1047
- docs(readme): update tracing references from Jaeger to Langfuse across multiple languages by @lyingbug in https://github.com/Tencent/WeKnora/pull/1048
- feat(frontend): add LLM call timeout for agents by @lyingbug in https://github.com/Tencent/WeKnora/pull/1059
- fix(wiki): queue JSON handling and failed ingest operations by @lyingbug in https://github.com/Tencent/WeKnora/pull/1061
- feat(types): support legacy and current formats in tenant Scan by @lyingbug in https://github.com/Tencent/WeKnora/pull/1060
- chore(i18n): align en-US/ko-KR/ru-RU locales with zh-CN by @lyingbug in https://github.com/Tencent/WeKnora/pull/1062
- chore(i18n): align en-US/ko-KR/ru-RU locales with zh-CN by @lyingbug in https://github.com/Tencent/WeKnora/pull/1063
- fix(wiki): Lite ingest lock, failed-op requeue, sync task retry parity by @lyingbug in https://github.com/Tencent/WeKnora/pull/1064
- fix: LaTeX formulas flash and disappear during streaming (#1056) by @lyingbug in https://github.com/Tencent/WeKnora/pull/1065
- fix(container): aggregate registration errors in connector registry initialization by @Goodnight77 in https://github.com/Tencent/WeKnora/pull/1054
- fix(search): align rerank priority between Execute and rerankResults by @lyingbug in https://github.com/Tencent/WeKnora/pull/1067
- fix(im): isolate IM sessions per agent, recover from deleted sessions by @lyingbug in https://github.com/Tencent/WeKnora/pull/1069
- fix(im): remove pipeline-level timeout that kills multi-round agent reasoning by @lyingbug in https://github.com/Tencent/WeKnora/pull/1070
- fix(docreader): remove default 100-page limit for DOCX parsing by @lyingbug in https://github.com/Tencent/WeKnora/pull/1071
- fix: inject KB document listing on fallback for broad queries by @lyingbug in https://github.com/Tencent/WeKnora/pull/1072
- feat: data_analysis sql validation & type processing by @1141520944 in https://github.com/Tencent/WeKnora/pull/1053
- fix(docparser): preserve standalone image uploads from icon filter by @lyingbug in https://github.com/Tencent/WeKnora/pull/1076
- feat(miniprogram): add WeChat mini program plugin by @wolfkill in https://github.com/Tencent/WeKnora/pull/1055
- feat(knowledge-base): add document batch delete and list view by @voidkey in https://github.com/Tencent/WeKnora/pull/1075
- fix(knowledge-base): restore hover feedback on selected list rows by @voidkey in https://github.com/Tencent/WeKnora/pull/1078
- fix(frontend): 知识库文档区布局、批量条与列表/卡片体验 by @lyingbug in https://github.com/Tencent/WeKnora/pull/1080
- fix(chat): stop button behavior and input layout fixes by @lyingbug in https://github.com/Tencent/WeKnora/pull/1083
- fix: prevent API key ciphertext (enc:v1:...) from leaking to the UI by @lyingbug in https://github.com/Tencent/WeKnora/pull/1087
- 客户端添加切换租户 by @cn-kali-team in https://github.com/Tencent/WeKnora/pull/1085
- feat: add STORAGE_ALLOW_LIST env var by @Windfarer in https://github.com/Tencent/WeKnora/pull/1086
- feat(tenant): expose API Key reset from the API Info page by @lyingbug in https://github.com/Tencent/WeKnora/pull/1089
- fix(frontend): polish knowledge list sticky header and floating batch bar by @lyingbug in https://github.com/Tencent/WeKnora/pull/1088
- refactor(im): move adapter factories into per-platform subpackages by @lyingbug in https://github.com/Tencent/WeKnora/pull/1084
- fix:attachment_document_failed by @MaoMengww in https://github.com/Tencent/WeKnora/pull/1094
- refactor(frontend): unify Model/WebSearch/MCP settings pages with shared card + drawer by @lyingbug in https://github.com/Tencent/WeKnora/pull/1093
- fix(frontend): polish KB list sticky header, batch bar, and card checkbox by @lyingbug in https://github.com/Tencent/WeKnora/pull/1090
- fix(frontend): route chat drag-and-drop uploads correctly by @Aphroq in https://github.com/Tencent/WeKnora/pull/1095
- fix(im): rewrite private storage URLs to HTTP in IM channel replies by @lyingbug in https://github.com/Tencent/WeKnora/pull/1068
- fix(crypto): fail loudly when encrypted DB fields cannot be decrypted by @lyingbug in https://github.com/Tencent/WeKnora/pull/1100
- fix(web-search): normalize default tenant web search config at runtime by @sqkstwj in https://github.com/Tencent/WeKnora/pull/1097
- feat(im): tenant-wide IM channels overview under the user menu by @lyingbug in https://github.com/Tencent/WeKnora/pull/1102
- feat(sessions): add keyword search, user-scoped pinning, and IM source visibility by @lyingbug in https://github.com/Tencent/WeKnora/pull/1101
New Contributors
- @cn-kali-team made their first contribution in https://github.com/Tencent/WeKnora/pull/1085
- @Aphroq made their first contribution in https://github.com/Tencent/WeKnora/pull/1095
- @sqkstwj made their first contribution in https://github.com/Tencent/WeKnora/pull/1097
Full Changelog: https://github.com/Tencent/WeKnora/compare/v0.5.0...v0.5.1
- API key validation uses constant-time comparison to prevent timing attacks
- Knowledge-base Wiki system with configurable indexing strategy
- Langfuse observability integration for LLM token tracking and asynq pipeline tracing
- OpenMAIC interactive classroom skill with RAG-to-courseware generation
Full changelog
What's Changed
- feat(repository): update keyword retrieval logic to use ParadeDB's matching operator by @lyingbug in https://github.com/Tencent/WeKnora/pull/977
- Fix system prompt not being used when flag is false by @utafrali in https://github.com/Tencent/WeKnora/pull/969
- fix: missing deep copy entity by @shanghai-Jerry in https://github.com/Tencent/WeKnora/pull/975
- fix: SQLite/Lite mode compatibility for FAQ import and chunk operations by @swim2sun in https://github.com/Tencent/WeKnora/pull/968
- docs: add wiki documentation with cross-referenced links by @Liwx1014 in https://github.com/Tencent/WeKnora/pull/978
- fix: use explicit localhost for docreader health probes by @sn1p4am in https://github.com/Tencent/WeKnora/pull/983
- feat(logger): implement LLM debug logging functionality by @lyingbug in https://github.com/Tencent/WeKnora/pull/984
- feat: add registry dual-map and engine factory for VectorStore by @ochanism in https://github.com/Tencent/WeKnora/pull/973
- refactor(postgres): optimize vector retrieval and HNSW settings by @lyingbug in https://github.com/Tencent/WeKnora/pull/986
- feat: search engine adds proxy addresses and adds SSRF verification. by @1141520944 in https://github.com/Tencent/WeKnora/pull/987
- feat: pass IndexConfig to repositories with scalability options by @ochanism in https://github.com/Tencent/WeKnora/pull/981
- feat: add VectorStore management UI settings page by @ochanism in https://github.com/Tencent/WeKnora/pull/982
- fix: use constant-time comparison for API key validation by @MaoMengww in https://github.com/Tencent/WeKnora/pull/992
- feat: add vector_store_id column to knowledge_bases for per-KB vector store binding by @ochanism in https://github.com/Tencent/WeKnora/pull/994
- feat: add OpenMAIC interactive classroom skill with RAG-to-courseware generation by @peterchan2020 in https://github.com/Tencent/WeKnora/pull/989
- fix(storage): auto-detect content-type to resolve image rendering issues by @jack-wang-176 in https://github.com/Tencent/WeKnora/pull/999
- fix: ReadEvent incompatible sse data format by @shanghai-Jerry in https://github.com/Tencent/WeKnora/pull/1002
- fix: remove limit/offset from required in list_knowledge_chunks JSON Schema by @draix in https://github.com/Tencent/WeKnora/pull/1012
- fix/air-toml-cgo-ldflags by @MaoMengww in https://github.com/Tencent/WeKnora/pull/1010
- fix(docker): 修复镜像构建兼容性问题 by @Liwx1014 in https://github.com/Tencent/WeKnora/pull/1005
- Fix/storage content type by @jack-wang-176 in https://github.com/Tencent/WeKnora/pull/1013
- fix:修复make dev-app里面脚本问题 by @tohelloworld in https://github.com/Tencent/WeKnora/pull/1016
- feat/yuque datasource connector by @voidkey in https://github.com/Tencent/WeKnora/pull/1011
- feat(wiki): introduce knowledge-base Wiki system and configurable indexing strategy by @lyingbug in https://github.com/Tencent/WeKnora/pull/1017
- chore: Update .dockerignore and GitHub Actions for improved caching by @lyingbug in https://github.com/Tencent/WeKnora/pull/1018
- chore: Update .dockerignore to clarify documentation exclusions and dependencies by @lyingbug in https://github.com/Tencent/WeKnora/pull/1019
- feat: Enhance agent tool compatibility and knowledge base filtering by @lyingbug in https://github.com/Tencent/WeKnora/pull/1021
- fix : mattermost handle io.ReadAll errors in client file by @Goodnight77 in https://github.com/Tencent/WeKnora/pull/1020
- refactor: Simplify WeKnoraCloud request customization and message conversion by @lyingbug in https://github.com/Tencent/WeKnora/pull/1022
- fix(frontend): bundle tdesign-icons sprite locally for offline deploys by @lyingbug in https://github.com/Tencent/WeKnora/pull/1024
- fix(agent): terminate ReAct loop on final_answer regardless of arg parse success by @lyingbug in https://github.com/Tencent/WeKnora/pull/1023
- feat(models): support custom HTTP headers across all remote model calls by @lyingbug in https://github.com/Tencent/WeKnora/pull/1025
- feat(frontend): add copy action for model cards in settings by @lyingbug in https://github.com/Tencent/WeKnora/pull/1026
- fix(agent-share): don't require rerank model for wiki-only agents by @lyingbug in https://github.com/Tencent/WeKnora/pull/1028
- feat(observability): integrate Langfuse for LLM token tracking and tracing by @lyingbug in https://github.com/Tencent/WeKnora/pull/1027
- feat(observability): extend Langfuse tracing across the asynq pipeline by @lyingbug in https://github.com/Tencent/WeKnora/pull/1029
- fix(agent): load all sheets from Excel files in data analysis (#1007) by @lyingbug in https://github.com/Tencent/WeKnora/pull/1035
- feat(observability): instrument agent ReAct loop and tool calls in Langfuse by @lyingbug in https://github.com/Tencent/WeKnora/pull/1034
- fix(agent): improve tenant context handling and error reporting by @Goodnight77 in https://github.com/Tencent/WeKnora/pull/1036
- Fix/docreader protoc offline whitelist by @jack-wang-176 in https://github.com/Tencent/WeKnora/pull/1033
- chore(release): v0.5.0 by @lyingbug in https://github.com/Tencent/WeKnora/pull/1042
- docs(readme): refresh title and overview to reflect RAG + Agent + Auto-Wiki by @lyingbug in https://github.com/Tencent/WeKnora/pull/1043
- feat: correct data analysis errors using fileService. by @1141520944 in https://github.com/Tencent/WeKnora/pull/1041
- Update v0.5.0 README by @lyingbug in https://github.com/Tencent/WeKnora/pull/1044
New Contributors
- @utafrali made their first contribution in https://github.com/Tencent/WeKnora/pull/969
- @shanghai-Jerry made their first contribution in https://github.com/Tencent/WeKnora/pull/975
- @swim2sun made their first contribution in https://github.com/Tencent/WeKnora/pull/968
- @sn1p4am made their first contribution in https://github.com/Tencent/WeKnora/pull/983
- @1141520944 made their first contribution in https://github.com/Tencent/WeKnora/pull/987
- @jack-wang-176 made their first contribution in https://github.com/Tencent/WeKnora/pull/999
- @draix made their first contribution in https://github.com/Tencent/WeKnora/pull/1012
- @tohelloworld made their first contribution in https://github.com/Tencent/WeKnora/pull/1016
- @Goodnight77 made their first contribution in https://github.com/Tencent/WeKnora/pull/1020
Full Changelog: https://github.com/Tencent/WeKnora/compare/v0.4.0...v0.5.0
- Video parser removed
- VectorStore CRUD API
- Notion connector
- WeChat integration
- OIDC authentication support
- Parallel tool calling
- Datasource management with Feishu sync
- Novita AI as LLM provider
- MCP tool result auto-description via VLM
- AES-256-GCM encryption for API keys at rest
- Built-in MCP service support
- Weaviate vectordb integration
- S3 storage adapter
- Parent-child chunking for hierarchical retrieval
- Knowledge base pinning
- Fallback response handling
- Async knowledge re-parse API
- Batch chat management
- Milvus vectordb support
Full changelog
What's Changed
- feat: Add async knowledge re-parse API and examples by @begoniezhao in https://github.com/Tencent/WeKnora/pull/679
- feat: add product roadmap documentation and links in README files by @lyingbug in https://github.com/Tencent/WeKnora/pull/685
- fix: handle thinking content in Ollama chat responses by @is-Xiaoen in https://github.com/Tencent/WeKnora/pull/689
- feat(chat): add batch management for conversations by @tsukiga-kirei in https://github.com/Tencent/WeKnora/pull/692
- feat: add volcengine tos support by @Dounx in https://github.com/Tencent/WeKnora/pull/691
- feat: implement preview of user level memory graph by @chengjoey in https://github.com/Tencent/WeKnora/pull/687
- fix: change helm frontend APP_HOST env default value to app by @ChenRussell in https://github.com/Tencent/WeKnora/pull/694
- fix(auth): update form validation check to handle non-boolean responses by @tsukiga-kirei in https://github.com/Tencent/WeKnora/pull/695
- feat: Add knowledge creation support from remote file URLs by @begoniezhao in https://github.com/Tencent/WeKnora/pull/696
- feat: support milvus vectordb for knowledge retrieve by @chengjoey in https://github.com/Tencent/WeKnora/pull/699
- fix(swagger): resolve interface documentation generation error and regenerate docs by @ChenRussell in https://github.com/Tencent/WeKnora/pull/698
- Korean update by @andy5090 in https://github.com/Tencent/WeKnora/pull/701
- fix: prevent modal dismiss on text selection & load all sessions in batch manage by @tsukiga-kirei in https://github.com/Tencent/WeKnora/pull/703
- feat: support mermaid display by @CodeMarker0 in https://github.com/Tencent/WeKnora/pull/702
- Storage & Doc Processor Refactor by @lyingbug in https://github.com/Tencent/WeKnora/pull/704
- feat(repository): add TagID and IsRecommended fields to vector embeddings by @lyingbug in https://github.com/Tencent/WeKnora/pull/705
- refactor: remove mineru_api_base_url from ParserEngineConfig and related components by @lyingbug in https://github.com/Tencent/WeKnora/pull/706
- refactor: simplify image handling in _resolve_images function by @lyingbug in https://github.com/Tencent/WeKnora/pull/709
- feat: enhance image handling and UI adjustments in document components by @lyingbug in https://github.com/Tencent/WeKnora/pull/711
- feat: release v0.3.2 with new features, improvements, and bug fixes by @lyingbug in https://github.com/Tencent/WeKnora/pull/712
New Contributors
- @is-Xiaoen made their first contribution in https://github.com/Tencent/WeKnora/pull/689
- @andy5090 made their first contribution in https://github.com/Tencent/WeKnora/pull/701
Full Changelog: https://github.com/Tencent/WeKnora/compare/v0.3.1...v0.3.2
- Support remote backend and HTTPS proxy
- Load knowledge files via presigned URLs
- Enhance resource management in UI components
- Bing search provider
- Redis ACL support
- Agent skills sandbox configuration
Full changelog
What's Changed
- fix: MCP Client connection state not marked as closed after connection loss in SSE transport type by @manx98 in https://github.com/Tencent/WeKnora/pull/607
- Update session.md | 停止会话 by @dragon8git in https://github.com/Tencent/WeKnora/pull/604
- feat(web_fetch): enhance web fetch tool with DNS pinning and validati… by @lyingbug in https://github.com/Tencent/WeKnora/pull/611
- refactor: Refactor rune handling for correct chunk merging by @begoniezhao in https://github.com/Tencent/WeKnora/pull/614
- feat: add bing search provider by @chengjoey in https://github.com/Tencent/WeKnora/pull/615
- fix: clear tag selection state when re-entering knowledge base by @ChenRussell in https://github.com/Tencent/WeKnora/pull/617
- feat: Use num_ctx instead of truncate for embedding truncation by @begoniezhao in https://github.com/Tencent/WeKnora/pull/623
- feat: Add configurable global log level via env by @begoniezhao in https://github.com/Tencent/WeKnora/pull/625
- docs: update Air installation command from cosmtrek/air to air-verse/air by @MEKXH in https://github.com/Tencent/WeKnora/pull/627
- fix(chat): strip thinking content from model output by @MEKXH in https://github.com/Tencent/WeKnora/pull/628
- feat(redis): add REDIS_USERNAME support for Redis ACL by @Dounx in https://github.com/Tencent/WeKnora/pull/626
- Feat/agent skills by @voidkey in https://github.com/Tencent/WeKnora/pull/621
- feat(redis): add REDIS_USERNAME environment variable for Redis ACL cnfiguration by @lyingbug in https://github.com/Tencent/WeKnora/pull/630
- feat: enhance agent skills sandbox configuration and availability by @lyingbug in https://github.com/Tencent/WeKnora/pull/631
- feat: update sandbox service configuration in Docker Compose files by @lyingbug in https://github.com/Tencent/WeKnora/pull/632
- docs: fix api link by @liweijie0812 in https://github.com/Tencent/WeKnora/pull/633
- Optimize Jaccard function for set comparisons by @CodeMarker0 in https://github.com/Tencent/WeKnora/pull/634
- chore: fix ChunkExtracter typo (ChunkExtractor) by @ChenRussell in https://github.com/Tencent/WeKnora/pull/660
- fix: typo missed in previous commit by @voidkey in https://github.com/Tencent/WeKnora/pull/663
- fix: replace standard log with structured logger in main and recovery middleware by @hobostay in https://github.com/Tencent/WeKnora/pull/662
- feat: enhance MCP tool name and description handling for security by @lyingbug in https://github.com/Tencent/WeKnora/pull/665
- feat(frontend): allow configurable backend host and port by @Dounx in https://github.com/Tencent/WeKnora/pull/666
- feat: add REDIS_USERNAME support for asynq client by @Dounx in https://github.com/Tencent/WeKnora/pull/667
- Shared Space & KB/Agent Sharing by @lyingbug in https://github.com/Tencent/WeKnora/pull/661
New Contributors
- @manx98 made their first contribution in https://github.com/Tencent/WeKnora/pull/607
- @dragon8git made their first contribution in https://github.com/Tencent/WeKnora/pull/604
- @Dounx made their first contribution in https://github.com/Tencent/WeKnora/pull/626
- @liweijie0812 made their first contribution in https://github.com/Tencent/WeKnora/pull/633
- @CodeMarker0 made their first contribution in https://github.com/Tencent/WeKnora/pull/634
- @hobostay made their first contribution in https://github.com/Tencent/WeKnora/pull/662
Full Changelog: https://github.com/Tencent/WeKnora/compare/v0.2.14...v0.3.0
Minor fixes and improvements.
Full changelog
What's Changed
- fix: prioritize env variable over git tag in version by @lyingbug in https://github.com/Tencent/WeKnora/pull/586
- style(ollama): optimize retest button icon alignment using #icon slot by @jlau-ice in https://github.com/Tencent/WeKnora/pull/587
- fix: correctly extract host from completion_url by handling both v1 and non-v1 endpoints by @jlau-ice in https://github.com/Tencent/WeKnora/pull/590
- fix(parser): resolve chunk index mismatch in logs by @ChenRussell in https://github.com/Tencent/WeKnora/pull/596
- feat(migrations): add pg_search extension update migration files by @lyingbug in https://github.com/Tencent/WeKnora/pull/603
New Contributors
- @ChenRussell made their first contribution in https://github.com/Tencent/WeKnora/pull/596
Full Changelog: https://github.com/Tencent/WeKnora/compare/v0.2.13...v0.2.14
Minor fixes and improvements.
Full changelog
What's Changed
- fix(zhipu): correct Embedding BaseURL to match API structure by @MEKXH in https://github.com/Tencent/WeKnora/pull/578
- feat: add retrieve KB only when mentioned option by @lyingbug in https://github.com/Tencent/WeKnora/pull/579
- fix: replace dots with underscores in MCP tool names (#528) by @lyingbug in https://github.com/Tencent/WeKnora/pull/580
- chore: Update PostgreSQL image version to v0.21.4-pg17 by @begoniezhao in https://github.com/Tencent/WeKnora/pull/582
- feat: add matched question field to FAQ search results by @lyingbug in https://github.com/Tencent/WeKnora/pull/581
- fix(frontend): hide upload mask when drag leaves window by @jlau-ice in https://github.com/Tencent/WeKnora/pull/583
New Contributors
- @MEKXH made their first contribution in https://github.com/Tencent/WeKnora/pull/578
- @jlau-ice made their first contribution in https://github.com/Tencent/WeKnora/pull/583
Full Changelog: https://github.com/Tencent/WeKnora/compare/v0.2.11...v0.2.12
- Fix SQL injection vulnerabilities
- Fix SSRF vulnerabilities
- Add thinking mode support for agents
- Centralize environment variables into config module
- Critical vulnerability V-001 fixed
- Google web search provider
- Knowledge categorization feature
Minor fixes and improvements.
Full changelog
What's Changed
- chore: update comments and documentation for SequentialThinkingTool by @begoniezhao in https://github.com/Tencent/WeKnora/pull/519
- feat: 改进未分类标签的处理逻辑 by @lyingbug in https://github.com/Tencent/WeKnora/pull/520
- refactor: 统一标签列表渲染逻辑,移除重复的未分类标签处理代码 by @lyingbug in https://github.com/Tencent/WeKnora/pull/522
- feat: add download_spatial target and DuckDB spatial extension handling by @begoniezhao in https://github.com/Tencent/WeKnora/pull/523
- Replace模式清理未使用标签 by @lyingbug in https://github.com/Tencent/WeKnora/pull/524
- feat: 支持复制知识库时指定任务ID by @lyingbug in https://github.com/Tencent/WeKnora/pull/525
Full Changelog: https://github.com/Tencent/WeKnora/compare/v0.2.8...v0.2.9