diff --git a/CHANGELOG.md b/CHANGELOG.md index 75e45754..8c6e505b 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -2,6 +2,55 @@ All notable changes to this project will be documented in this file. +## [0.6.2] - 2026-06-10 + +### New Features + +- **NEW**: **Per-Upload Process Configuration & Upload Confirm Dialog** — the headline of this release. Every file / URL / folder upload can now carry a `process_config` (`KnowledgeProcessOverrides`) that overrides KB defaults for that batch only: parser engine rules, chunking, multimodal (VLM / ASR), question generation, graph extraction, and related flags. The Web UI adds an upload-confirm step so operators can review and tweak settings before enqueueing; the Go client and `weknora doc upload` accept the same JSON payload. +- **NEW**: **Document Reparse with Process Config** — `POST /knowledge/:id/reparse` accepts an optional `process_config` body to re-run parsing with new settings while preserving the knowledge record; overrides are persisted on the knowledge metadata and merged with KB defaults via `ResolveProcessConfig`. +- **NEW**: **`weknora` CLI v0.9** (BREAKING) — auth/profile model harmonization, resource-command cleanup, and bundled Agent Skills: + - **Bundled skills**: `weknora-rag-search` and `weknora-shared` skills ship in-tree with drift-guard parity tests. + - **`session stop`**: abort an in-flight agent run from the terminal. + - **`--kb` resolver**: accepts KB name or id on `doc delete --all` and `search chunks` / `search docs` (required; no silent project-link fallback). + - **Auth/profile**: `auth login` authenticates the active profile (use `profile add --use` first); `auth logout` / `auth refresh` drop `--name` — target another profile with global `--profile`. + - **MCP rename**: `agent_invoke` → `session_ask`; `agent create --kb` → `--attach-kb`. +- **NEW**: **Knowledge-base marquee selection** — drag-to-select multiple documents in the KB list for batch operations. +- **NEW**: **HNSW index for 1024-dim embeddings** — migration `000059_embeddings_hnsw_1024` adds an HNSW index tuned for `bge-m3`-class 1024-dimensional vectors on PostgreSQL pgvector. +- **NEW**: **Frontend build commit ID** — Vite injects the git commit hash into the UI for version tracking (Settings → System Info). + +### Improvements + +- **IMPROVED**: **Chat resources store** — centralized Pinia store for KB / agent selection across chat, editor, and command palette; hardened cache invalidation and deduplication when switching tenants or reloading lists. +- **IMPROVED**: **Dark-mode code preview** — syntax highlighting in document / manual-knowledge code blocks respects the active theme. +- **IMPROVED**: **Agent `get_document_info` tool** — schema and input parameters refined for clearer LLM tool calls. +- **IMPROVED**: **Chat provider** — provider-native tool-call metadata preserved end-to-end in streaming responses. +- **IMPROVED**: **Process config model** — removed standalone `enable_multimodal` KB flag in favor of unified `process_config`; parent-child chunking settings aligned; `graph_enabled` correctly gated on extract config. +- **IMPROVED**: **Tracing** — Jaeger integration removed; Langfuse remains the sole observability backend (simpler startup, fewer env knobs). +- **IMPROVED**: **Model sanitization** — chat model name and path validation hardened against malformed provider configs. + +### Bug Fixes + +- **FIXED**: Langfuse initialization failure on certain startup orderings. +- **FIXED**: Share-link endpoints allow anonymous read access again (#1617). +- **FIXED**: Wiki document status not refreshing after polling completes. +- **FIXED**: KB list deduplication — multiple knowledge bases no longer render as an empty list. +- **FIXED**: Custom jieba user-dictionary directory respected when configured. +- **FIXED**: DuckDB spatial extension no longer attempts network install during startup. +- **FIXED**: Document scroll container layout during loading state. +- **FIXED**: `graph_enabled` logic in process configuration merge path. + +### Infrastructure & Build + +- **BUILD**: Migration `000059_embeddings_hnsw_1024`. +- **BUILD**: Frontend `chatResources` / `uploadConfirm` / `editorResources` stores; `useMarqueeSelect` composable. +- **BUILD**: CLI v0.9 contract tests, skill parity guards, and `session stop` command. + +### Documentation + +- **DOC**: `docs/api/knowledge.md` documents `process_config` on upload and reparse. +- **DOC**: `docs/QA.md` extended for upload process config and CLI v0.9 breaking changes. +- **DOC**: Architecture diagram updated for per-upload config, bundled CLI skills, and HNSW. + ## [0.6.1] - 2026-06-05 ### New Features diff --git a/README.md b/README.md index 4d0dbccb..3c707336 100644 --- a/README.md +++ b/README.md @@ -28,7 +28,7 @@ License - Version + Version

@@ -57,6 +57,7 @@ The framework supports auto-syncing knowledge from Feishu, Notion, and Yuque (mo ## ✨ Latest Updates +- **v0.6.2** — Per-upload process configuration with upload-confirm dialog; document reparse with `process_config`; `weknora` CLI v0.9 (bundled Agent Skills, `session stop`, auth/profile harmonization); KB marquee multi-select; HNSW index for 1024-dim pgvector embeddings; chat resources store refactor; Langfuse-only tracing (Jaeger removed). See [`CHANGELOG.md`](./CHANGELOG.md). - **v0.6.1** — Document parsing trace timeline (Langfuse-style span tree with stage-by-stage progress + stop-parse); OpenSearch vector store driver; declarative built-in models via YAML; system admin & consolidated platform settings + audit log; new-user onboarding guide; settings UI redesign; `weknora` CLI v0.7 / v0.8 (agent-first wire contract, NDJSON, `--dry-run`); OpenDataLoader + PaddleOCR-VL parsers; MCP server multi-transport (stdio / SSE / HTTP); per-model thinking-mode config; Tencent LKEAP rerank + native Gemini embeddings + MiniMax-M3. See [`CHANGELOG.md`](./CHANGELOG.md). - **v0.6.0** — Tenant RBAC (4-tier role matrix `Owner` / `Admin` / `Contributor` / `Viewer` + per-KB ownership + per-tenant audit log), tenant member management & multi-workspace UX, self-service workspaces; `weknora` CLI v0.4 GA with `mcp serve`; KB retrieval fan-out across vector stores; AES-256-GCM credential encryption + docreader gRPC TLS + Token; Zhipu embedder + Huawei OBS; server-side user preferences; Go 1.26.0. See [`docs/RBAC说明.md`](./docs/RBAC说明.md) and [`CHANGELOG.md`](./CHANGELOG.md). - **v0.5.2** — Wiki ingest scales to 40k-document KBs (task queue + DLQ); MCP human-in-the-loop tool approval; Anthropic / Apache Doris / Tencent VectorDB / KS3 / SearXNG backends; adaptive 3-tier chunking with live preview; global ⌘K command palette; Yuque connector + WeChat Mini Program; `weknora` CLI preview. @@ -115,9 +116,11 @@ Fully modular pipeline from document parsing, vectorization, and retrieval to LL | Capability | Details | |------------|---------| | Knowledge Base Types | FAQ / Document / Wiki with folder import, URL import, tag management, and online entry | +| Per-Upload Process Config | Override parser, chunking, multimodal (VLM / ASR), graph extraction, and question generation per upload batch via upload-confirm dialog or `process_config` API; reparse with new settings | | Data Source Import | Auto-sync from Feishu / Notion / Yuque (more data sources coming soon); incremental and full sync | | Document Formats | PDF / Word / Txt / Markdown / HTML / Images / CSV / Excel / PPT / JSON | -| Retrieval Strategies | BM25 sparse / Dense retrieval / GraphRAG / parent-child chunking / multi-dimensional indexing | +| Retrieval Strategies | BM25 sparse / Dense retrieval / GraphRAG / parent-child chunking / HNSW-accelerated pgvector (1024-dim) / multi-dimensional indexing | +| Batch Selection | Marquee drag-select multiple documents in the KB list for batch operations | | E2E Testing | Full-pipeline visualization with recall hit rate, BLEU / ROUGE metric evaluation | **Integrations & Extensions** @@ -139,7 +142,7 @@ Fully modular pipeline from document parsing, vectorization, and retrieval to LL | UI | Web UI / RESTful API / CLI (`weknora`) / Chrome Extension / WeChat Mini Program | | Access Control | Tenant RBAC with 4-tier role matrix (Owner / Admin / Contributor / Viewer), per-KB resource ownership, per-tenant audit log, invite-only workspaces, self-service tenant creation, cross-tenant superuser | | Security | AES-256-GCM at-rest encryption for API keys and MCP / data-source credentials with graceful key rotation; gRPC TLS + Token between app and docreader; SSRF-safe HTTP client; sandbox isolation for agent skills | -| Observability | Integrated Langfuse for ReAct loops, token tracking, tool calls, and pipeline tracing; built-in Langfuse-style document parsing trace timeline with stage-by-stage progress | +| Observability | Integrated Langfuse (sole tracing backend) for ReAct loops, token tracking, tool calls, and pipeline tracing; built-in Langfuse-style document parsing trace timeline with stage-by-stage progress | | Task Management | MQ async tasks, automatic database migration on version upgrade | | Model Management | Centralized config, declarative built-in models via YAML, per-knowledge-base model selection, per-model thinking-mode config, multi-tenant built-in model sharing, WeKnora Cloud hosted models and parsing | @@ -166,6 +169,8 @@ The [WeKnora Mini Program](./miniprogram/README.md) provides a lightweight mobil `weknora` is the official CLI for driving the API from a terminal or AI agent. The command surface mirrors `gh` CLI's ` ` convention; output is human-readable by default and switches to a stable JSON envelope with `--json`. +v0.9 ships bundled Agent Skills (`weknora-rag-search`, `weknora-shared`), adds +`session stop`, and harmonizes auth/profile workflows (see [`cli/CHANGELOG.md`](./cli/CHANGELOG.md)). ```bash weknora auth login --host https://kb.example.com diff --git a/README_CN.md b/README_CN.md index 368e279f..55194dbb 100644 --- a/README_CN.md +++ b/README_CN.md @@ -28,7 +28,7 @@ License - 版本 + 版本

@@ -56,6 +56,7 @@ ## ✨ 最新更新 +- **v0.6.2** —— 按批次解析配置(`process_config`)+ 上传确认对话框;文档重新解析(reparse)支持覆盖配置;`weknora` CLI v0.9(内置 Agent Skills、`session stop`、auth/profile 统一);知识库框选多选;pgvector 1024 维 HNSW 索引;对话资源 Store 重构;仅保留 Langfuse 追踪(移除 Jaeger)。详见 [`CHANGELOG.md`](./CHANGELOG.md)。 - **v0.6.1** —— 文档解析追踪时间线(Langfuse 风格 Span 树,逐阶段进度展示 + 解析中止);OpenSearch 向量库驱动;YAML 声明式内置模型配置;系统管理员与统一平台设置 + 审计日志;新用户引导;设置页 UI 重构;`weknora` CLI v0.7 / v0.8(Agent 优先线协议、NDJSON、`--dry-run`);OpenDataLoader 与 PaddleOCR-VL 解析引擎;MCP Server 多传输(stdio / SSE / HTTP);按模型的思考模式配置;腾讯云 LKEAP 重排 + 原生 Gemini Embedding + MiniMax-M3。详见 [`CHANGELOG.md`](./CHANGELOG.md)。 - **v0.6.0** —— 租户 RBAC(四级角色矩阵 `Owner` / `Admin` / `Contributor` / `Viewer` + 按 KB 归属 + 每租户审计日志)、租户成员管理与多工作区 UX、自助创建工作区;`weknora` CLI v0.4 正式版 + `mcp serve`;KB 检索跨向量库扇出;MCP / 数据源凭据 AES-256-GCM 加密 + docreader gRPC TLS + Token;新增智谱 Embedding 与华为云 OBS;服务端用户偏好;Go 1.26.0。详见 [`docs/RBAC说明.md`](./docs/RBAC说明.md) 与 [`CHANGELOG.md`](./CHANGELOG.md)。 - **v0.5.2** —— Wiki 入库支撑万级文档知识库(任务队列 + 死信队列);MCP 工具人机审批;Anthropic / Apache Doris / 腾讯云 VectorDB / 金山云 KS3 / SearXNG 后端;自适应三层分块 + 实时调试面板;全局 ⌘K 命令面板;语雀连接器 + 微信小程序;`weknora` CLI 早期版本。 @@ -114,9 +115,11 @@ | 能力 | 详情 | |------|------| | 知识库类型 | FAQ / 文档 / Wiki,支持文件夹导入、URL 导入、标签管理、在线录入 | +| 按批次解析配置 | 上传确认对话框或 `process_config` API 覆盖解析引擎、分块、多模态(VLM / ASR)、图谱抽取与问题生成;支持 reparse 时调整配置 | | 数据源导入 | 飞书 / Notion / 语雀 知识库自动同步(更多数据源开发中),支持增量与全量同步 | | 文档格式 | PDF / Word / Txt / Markdown / HTML / 图片 / CSV / Excel / PPT / JSON | -| 检索策略 | BM25 稀疏召回 / Dense 稠密召回 / GraphRAG 图谱增强 / 父子分块 / 多维度索引 | +| 检索策略 | BM25 稀疏召回 / Dense 稠密召回 / GraphRAG 图谱增强 / 父子分块 / pgvector HNSW 加速(1024 维)/ 多维度索引 | +| 批量选择 | 知识库文档列表支持框选(marquee)多选,便于批量操作 | | 端到端测试 | 检索+生成全链路可视化,评估召回命中率、BLEU / ROUGE 等指标 | **集成与扩展** @@ -139,7 +142,7 @@ | 界面 | Web UI / RESTful API / 命令行(`weknora`)/ Chrome Extension / 微信小程序 | | 权限控制 | 租户 RBAC 四级角色矩阵(Owner / Admin / Contributor / Viewer),按知识库的资源归属,每租户审计日志,invite-only 准入,自助创建工作区,跨租户超级管理员 | | 安全 | API Key 与 MCP / 数据源凭据 AES-256-GCM 静态加密、支持平滑密钥轮换;app ↔ docreader gRPC TLS + Token;防 SSRF HTTP 客户端;Agent 技能沙箱隔离 | -| 可观测性 | 集成 Langfuse 以追踪 ReAct 循环、Token 消耗、工具调用和任务流水线;内置 Langfuse 风格的文档解析追踪时间线,逐阶段展示解析进度 | +| 可观测性 | 集成 Langfuse(唯一追踪后端)以追踪 ReAct 循环、Token 消耗、工具调用和任务流水线;内置 Langfuse 风格的文档解析追踪时间线,逐阶段展示解析进度 | | 任务管理 | MQ 异步任务,版本升级自动数据库迁移 | | 模型管理 | 集中配置,YAML 声明式内置模型配置,知识库级别模型选择,按模型思考模式配置,多租户共享内置模型,WeKnora Cloud 托管模型与文档解析 | diff --git a/README_JA.md b/README_JA.md index dc5d5d01..6c88d48f 100644 --- a/README_JA.md +++ b/README_JA.md @@ -28,7 +28,7 @@ License - バージョン + バージョン

@@ -56,6 +56,7 @@ Feishu、Notion、Yuqueなどの外部プラットフォームからのナレッ ## ✨ 最新アップデート +- **v0.6.2** — アップロード単位の解析設定(`process_config`)+ アップロード確認ダイアログ;reparse 時の設定上書き;`weknora` CLI v0.9(同梱 Agent Skills、`session stop`、auth/profile 統合);KB マーキー複数選択;pgvector 1024 次元 HNSW インデックス;チャットリソース Store 刷新;Langfuse のみのトレーシング(Jaeger 削除)。詳細は [`CHANGELOG.md`](./CHANGELOG.md)。 - **v0.6.1** — ドキュメント解析トレースタイムライン(Langfuse 風の Span ツリー、ステージごとの進捗表示 + 解析中止);OpenSearch ベクター DB ドライバー;YAML 宣言型ビルトインモデル設定;システム管理者と統合プラットフォーム設定 + 監査ログ;新規ユーザーオンボーディングガイド;設定 UI 刷新;`weknora` CLI v0.7 / v0.8(Agent ファースト ワイヤープロトコル、NDJSON、`--dry-run`);OpenDataLoader と PaddleOCR-VL 解析エンジン;MCP サーバーのマルチトランスポート(stdio / SSE / HTTP);モデル単位の思考モード設定;Tencent LKEAP リランク + ネイティブ Gemini Embedding + MiniMax-M3。詳細は [`CHANGELOG.md`](./CHANGELOG.md) を参照。 - **v0.6.0** — テナント RBAC(4 階層ロールマトリクス `Owner` / `Admin` / `Contributor` / `Viewer` + KB 単位の所有 + テナントごとの監査ログ)、テナントメンバー管理とマルチワークスペース UX、セルフサービスでのワークスペース作成;`weknora` CLI v0.4 GA + `mcp serve`;KB 検索の複数ベクター DB ファンアウト;MCP / データソース資格情報の AES-256-GCM 暗号化 + docreader gRPC TLS + Token;Zhipu Embedder と華為雲 OBS の追加;サーバーサイドユーザー設定;Go 1.26.0。詳細は [`docs/RBAC说明.md`](./docs/RBAC说明.md) と [`CHANGELOG.md`](./CHANGELOG.md) を参照。 - **v0.5.2** — Wiki インジェストが万件規模 KB に対応(タスクキュー + DLQ);MCP 工具人機審批;Anthropic / Apache Doris / Tencent VectorDB / 金山雲 KS3 / SearXNG バックエンド;適応型 3 段階チャンキング + ライブプレビュー;グローバル ⌘K コマンドパレット;Yuque コネクタ + WeChat ミニプログラム;`weknora` CLI プレビュー版。 @@ -115,9 +116,11 @@ Feishu、Notion、Yuqueなどの外部プラットフォームからのナレッ | 機能 | 詳細 | |------|------| | ナレッジベースタイプ | FAQ / ドキュメント / Wiki、フォルダーインポート・URL インポート・タグ管理・オンライン入力 | +| アップロード単位の解析設定 | アップロード確認ダイアログまたは `process_config` API でパーサー・チャンキング・マルチモーダル(VLM / ASR)・グラフ抽出・質問生成をバッチ単位で上書き;reparse 時も設定変更可能 | | データソースインポート | Feishu / Notion / Yuque ナレッジベースの自動同期(他のデータソースも開発中)、増分・全量同期対応 | | 文書フォーマット | PDF / Word / Txt / Markdown / HTML / 画像 / CSV / Excel / PPT / JSON | -| 検索戦略 | BM25 疎検索 / Dense 密検索 / GraphRAG グラフ強化 / 親子チャンキング / 多次元インデックス | +| 検索戦略 | BM25 疎検索 / Dense 密検索 / GraphRAG グラフ強化 / 親子チャンキング / pgvector HNSW 加速(1024 次元)/ 多次元インデックス | +| 一括選択 | KB リストでマーキー(ドラッグ)複数選択によるバッチ操作 | | E2E テスト | 検索+生成の全パイプライン可視化、リコール的中率・BLEU / ROUGE 指標評価 | **連携と拡張** @@ -137,7 +140,7 @@ Feishu、Notion、Yuqueなどの外部プラットフォームからのナレッ |------|------| | デプロイ | ローカル / Docker / Kubernetes (Helm)、プライベート化・オフラインデプロイ対応 | | UI | Web UI / RESTful API / CLI (`weknora`) / Chrome Extension / WeChat ミニプログラム | -| 可観測性 | ReActループ、トークン消費、ツール呼び出し、パイプライン追跡のためのLangfuse統合;Langfuse 風のドキュメント解析トレースタイムラインを内蔵し、ステージごとの進捗を表示 | +| 可観測性 | Langfuse(唯一のトレーシングバックエンド)で ReAct ループ・トークン消費・ツール呼び出し・パイプライン追跡;Langfuse 風のドキュメント解析トレースタイムラインを内蔵し、ステージごとの進捗を表示 | | タスク管理 | MQ 非同期タスク、バージョンアップ時の DB 自動マイグレーション | | モデル管理 | 集中設定、YAML 宣言型ビルトインモデル設定、ナレッジベース単位のモデル選択、モデル単位の思考モード設定、マルチテナント組み込みモデル共有、WeKnora Cloud ホスティングモデルとドキュメント解析 | diff --git a/README_KO.md b/README_KO.md index 69da28d2..6247f6b2 100644 --- a/README_KO.md +++ b/README_KO.md @@ -28,7 +28,7 @@ License - 버전 + 버전

@@ -56,6 +56,7 @@ Feishu, Notion, Yuque 등 외부 플랫폼에서 지식 자동 동기화를 지 ## ✨ 최신 업데이트 +- **v0.6.2** — 업로드 단위 파싱 설정(`process_config`) + 업로드 확인 대화상자; reparse 시 설정 덮어쓰기; `weknora` CLI v0.9(번들 Agent Skills, `session stop`, auth/profile 통합); KB 마키 선택 다중 선택; pgvector 1024차원 HNSW 인덱스; 채팅 리소스 Store 리팩터; Langfuse 단일 추적(Jaeger 제거). 자세한 내용은 [`CHANGELOG.md`](./CHANGELOG.md). - **v0.6.1** — 문서 파싱 추적 타임라인(Langfuse 스타일 Span 트리, 단계별 진행 표시 + 파싱 중단); OpenSearch 벡터 저장소 드라이버; YAML 선언형 내장 모델 구성; 시스템 관리자와 통합 플랫폼 설정 + 감사 로그; 신규 사용자 온보딩 가이드; 설정 UI 리디자인; `weknora` CLI v0.7 / v0.8(Agent 우선 와이어 프로토콜, NDJSON, `--dry-run`); OpenDataLoader 및 PaddleOCR-VL 파싱 엔진; MCP 서버 멀티 트랜스포트(stdio / SSE / HTTP); 모델별 사고 모드 설정; Tencent LKEAP 리랭크 + 네이티브 Gemini 임베딩 + MiniMax-M3. 자세한 내용은 [`CHANGELOG.md`](./CHANGELOG.md) 참고. - **v0.6.0** — 테넌트 RBAC(4단계 역할 매트릭스 `Owner` / `Admin` / `Contributor` / `Viewer` + KB 단위 소유 + 테넌트별 감사 로그), 테넌트 멤버 관리와 멀티 워크스페이스 UX, 셀프 서비스 워크스페이스 생성; `weknora` CLI v0.4 GA + `mcp serve`; 여러 벡터 저장소에 걸친 KB 검색 팬아웃; MCP / 데이터 소스 자격 증명 AES-256-GCM 암호화 + docreader gRPC TLS + Token; Zhipu 임베더와 화웨이 클라우드 OBS 추가; 서버 사이드 사용자 환경설정; Go 1.26.0. 자세한 내용은 [`docs/RBAC说明.md`](./docs/RBAC说明.md)과 [`CHANGELOG.md`](./CHANGELOG.md) 참고. - **v0.5.2** — Wiki 인제스트가 만 건 규모 KB 지원(작업 큐 + DLQ); MCP 휴먼인더루프 도구 승인; Anthropic / Apache Doris / Tencent VectorDB / Kingsoft Cloud KS3 / SearXNG 백엔드; 적응형 3단계 청킹 + 라이브 미리보기; 글로벌 ⌘K 명령 팔레트; Yuque 커넥터 + WeChat 미니프로그램; `weknora` CLI 프리뷰. @@ -124,9 +125,11 @@ Feishu, Notion, Yuque 등 외부 플랫폼에서 지식 자동 동기화를 지 | 기능 | 상세 | |------|------| | 지식베이스 타입 | FAQ / 문서 / Wiki, 폴더 임포트·URL 임포트·태그 관리·온라인 입력 | +| 업로드 단위 파싱 설정 | 업로드 확인 대화상자 또는 `process_config` API로 파서·청킹·멀티모달(VLM / ASR)·그래프 추출·질문 생성을 배치 단위로 덮어쓰기; reparse 시 설정 변경 지원 | | 데이터 소스 임포트 | Feishu / Notion / Yuque 지식베이스 자동 동기화(추가 데이터 소스 개발 중), 증분·전체 동기화 지원 | | 문서 포맷 | PDF / Word / Txt / Markdown / HTML / 이미지 / CSV / Excel / PPT / JSON | -| 검색 전략 | BM25 희소 / Dense 밀집 / GraphRAG 그래프 강화 / 부모-자식 청킹 / 다차원 인덱싱 | +| 검색 전략 | BM25 희소 / Dense 밀집 / GraphRAG 그래프 강화 / 부모-자식 청킹 / pgvector HNSW 가속(1024차원) / 다차원 인덱싱 | +| 일괄 선택 | KB 목록에서 마키(드래그) 다중 선택으로 일괄 작업 | | E2E 테스트 | 전체 파이프라인 시각화, 리콜 적중률·BLEU / ROUGE 지표 평가 | **연동 및 확장** @@ -146,7 +149,7 @@ Feishu, Notion, Yuque 등 외부 플랫폼에서 지식 자동 동기화를 지 |------|------| | 배포 | 로컬 / Docker / Kubernetes (Helm), 프라이빗/오프라인 배포 지원 | | UI | Web UI / RESTful API / CLI (`weknora`) / Chrome Extension / WeChat 미니 프로그램 | -| 관측 가능성 | ReAct 루프, 토큰 소비, 도구 호출, 파이프라인 추적을 위한 Langfuse 통합; Langfuse 스타일의 문서 파싱 추적 타임라인 내장으로 단계별 진행 표시 | +| 관측 가능성 | Langfuse(단일 추적 백엔드)로 ReAct 루프·토큰 소비·도구 호출·파이프라인 추적; Langfuse 스타일의 문서 파싱 추적 타임라인 내장으로 단계별 진행 표시 | | 작업 관리 | MQ 비동기 작업, 버전 업그레이드 시 자동 DB 마이그레이션 | | 모델 관리 | 중앙 설정, YAML 선언형 내장 모델 구성, 지식베이스별 모델 선택, 모델별 사고 모드 설정, 멀티테넌트 내장 모델 공유, WeKnora Cloud 호스팅 모델 및 문서 파싱 | diff --git a/VERSION b/VERSION index ee6cdce3..b6160487 100644 --- a/VERSION +++ b/VERSION @@ -1 +1 @@ -0.6.1 +0.6.2 diff --git a/cli/CHANGELOG.md b/cli/CHANGELOG.md index b6a82d5f..4a71f9cf 100644 --- a/cli/CHANGELOG.md +++ b/cli/CHANGELOG.md @@ -10,7 +10,7 @@ of the WeKnora server / frontend release cadence. CLI history before v0.3 is recorded in the project root [CHANGELOG.md](../CHANGELOG.md) under the release that introduced the CLI. -## [Unreleased] +## [0.9.0] - 2026-06-10 ### v0.9 — auth/profile model harmonization + flag cleanup diff --git a/docs/QA.md b/docs/QA.md index b817bb5c..16ac9eb2 100644 --- a/docs/QA.md +++ b/docs/QA.md @@ -260,5 +260,29 @@ Wiki 模式允许 Agent 根据原始文档自动生成并维护一套结构化 0.6.1 引入了系统管理员与统一平台设置面板(含平台审计日志),与租户内 RBAC 区分:系统管理员管理的是「平台级」配置,而非单个租户内的资源。首次启用需通过系统管理员 bootstrap 流程晋升首个管理员;撤销管理员权限有安全防护(避免误撤导致无人可管)。相关迁移为 `000053_system_admin_and_settings`。 +## 18. 上传时如何自定义解析配置(process_config)? + +0.6.2 起,文件 / URL / 文件夹上传可携带 `process_config`(`KnowledgeProcessOverrides`),在**本次批次**内覆盖知识库默认的解析引擎、分块、多模态(VLM / ASR)、问题生成、图谱抽取等设置,而不会改动 KB 全局配置。Web UI 在上传前会弹出确认对话框供调整;API 与 `weknora doc upload` 传同名 JSON 即可。 + +- **与 KB 默认配置的关系**:未传的字段沿用 KB 默认值;`graph_enabled` 仅在 `extract_config.enabled` 为 true 时生效。 +- **重新解析**:`POST /knowledge/:id/reparse` 可在 body 中传 `process_config` 以新配置重跑解析,覆盖项会写入 `knowledge.metadata.process_overrides`。 +- **图片 / 音频校验**:批次含图片时需 KB 已配置 VLM;含音频时需已配置 ASR,否则上传会被拒绝。 +- 详见 [`docs/api/knowledge.md`](./api/knowledge.md)。 + +## 19. 升级到 0.6.2 后 `weknora` CLI 登录或 MCP 工具报错? + +0.6.2 随附 **CLI v0.9**(破坏性变更),常见迁移: + +- **`auth login` 不再创建 profile**:先 `weknora profile add --host --use`,再 `weknora auth login`;切换 profile 用全局 `--profile `。 +- **`auth logout` / `auth refresh` 去掉 `--name`**:作用于当前 active profile。 +- **MCP 工具 `agent_invoke` 已更名为 `session_ask`**:外部 MCP 客户端需刷新工具 schema。 +- **`agent create --kb` 改为 `--attach-kb`**;`doc delete --all` 与 `search chunks` / `search docs` 的 `--kb` 必填且支持名称或 ID。 +- 新增 `weknora session stop ` 可中止进行中的 Agent 运行;仓库内附带 `weknora-rag-search` / `weknora-shared` 内置 Skills。 +- 详见 [`cli/CHANGELOG.md`](../cli/CHANGELOG.md)。 + +## 20. pgvector 检索变慢或刚升级后需要做什么? + +0.6.2 新增迁移 `000059_embeddings_hnsw_1024`,为 **1024 维** embedding(如 bge-m3)在 PostgreSQL pgvector 上创建 HNSW 索引。服务启动会自动执行迁移;若你使用其他维度,该索引可能不适用,需按自身 embedding 维度另行调优。升级后首次大批量入库期间索引构建可能占用额外 I/O,属正常现象。 + ## P.S. 如果以上方式未解决问题,请在issue中描述您的问题,并提供必要的日志信息辅助我们进行问题排查 diff --git a/docs/docs.go b/docs/docs.go index 4b0634c8..5058b0c6 100644 --- a/docs/docs.go +++ b/docs/docs.go @@ -6282,6 +6282,14 @@ const docTemplate = `{ "name": "id", "in": "path", "required": true + }, + { + "description": "可选的处理配置覆盖:{\\", + "name": "body", + "in": "body", + "schema": { + "type": "object" + } } ], "responses": { @@ -13198,10 +13206,6 @@ const docTemplate = `{ "description": "Chunk size", "type": "integer" }, - "enable_multimodal": { - "description": "EnableMultimodal (deprecated, kept for backward compatibility with old data)", - "type": "boolean" - }, "enable_parent_child": { "description": "EnableParentChild enables two-level parent-child chunking strategy.\nWhen enabled, large parent chunks provide context while small child chunks\nare used for vector matching. Retrieval matches on child but returns parent content.", "type": "boolean" @@ -14642,6 +14646,38 @@ const docTemplate = `{ } } }, + "github_com_Tencent_WeKnora_internal_types.KnowledgeProcessOverrides": { + "type": "object", + "properties": { + "asr_config": { + "$ref": "#/definitions/github_com_Tencent_WeKnora_internal_types.ASRConfig" + }, + "chunking_config": { + "$ref": "#/definitions/github_com_Tencent_WeKnora_internal_types.ChunkingConfig" + }, + "enable_multimodel": { + "type": "boolean" + }, + "extract_config": { + "$ref": "#/definitions/github_com_Tencent_WeKnora_internal_types.ExtractConfig" + }, + "graph_enabled": { + "type": "boolean" + }, + "parser_engine_rules": { + "type": "array", + "items": { + "$ref": "#/definitions/github_com_Tencent_WeKnora_internal_types.ParserEngineRule" + } + }, + "question_generation_config": { + "$ref": "#/definitions/github_com_Tencent_WeKnora_internal_types.QuestionGenerationConfig" + }, + "vlm_config": { + "$ref": "#/definitions/github_com_Tencent_WeKnora_internal_types.VLMConfig" + } + } + }, "github_com_Tencent_WeKnora_internal_types.ListMembersResponse": { "type": "object", "properties": { @@ -14910,6 +14946,9 @@ const docTemplate = `{ "content": { "type": "string" }, + "process_config": { + "$ref": "#/definitions/github_com_Tencent_WeKnora_internal_types.KnowledgeProcessOverrides" + }, "status": { "type": "string" }, @@ -16630,6 +16669,14 @@ const docTemplate = `{ "description": "Tool name", "type": "string" }, + "provider_metadata": { + "description": "Provider-specific tool-call state for replay", + "allOf": [ + { + "$ref": "#/definitions/github_com_Tencent_WeKnora_internal_types.ToolCallMetadata" + } + ] + }, "reflection": { "description": "Agent's reflection on this tool call result (if enabled)", "type": "string" @@ -16644,6 +16691,15 @@ const docTemplate = `{ } } }, + "github_com_Tencent_WeKnora_internal_types.ToolCallMetadata": { + "type": "object", + "additionalProperties": { + "type": "array", + "items": { + "type": "integer" + } + } + }, "github_com_Tencent_WeKnora_internal_types.ToolResult": { "type": "object", "properties": { diff --git a/docs/images/architecture.png b/docs/images/architecture.png index 92917119..eba16caf 100644 Binary files a/docs/images/architecture.png and b/docs/images/architecture.png differ diff --git a/docs/swagger.json b/docs/swagger.json index 52261834..a2f31186 100644 --- a/docs/swagger.json +++ b/docs/swagger.json @@ -6275,6 +6275,14 @@ "name": "id", "in": "path", "required": true + }, + { + "description": "可选的处理配置覆盖:{\\", + "name": "body", + "in": "body", + "schema": { + "type": "object" + } } ], "responses": { @@ -13191,10 +13199,6 @@ "description": "Chunk size", "type": "integer" }, - "enable_multimodal": { - "description": "EnableMultimodal (deprecated, kept for backward compatibility with old data)", - "type": "boolean" - }, "enable_parent_child": { "description": "EnableParentChild enables two-level parent-child chunking strategy.\nWhen enabled, large parent chunks provide context while small child chunks\nare used for vector matching. Retrieval matches on child but returns parent content.", "type": "boolean" @@ -14635,6 +14639,38 @@ } } }, + "github_com_Tencent_WeKnora_internal_types.KnowledgeProcessOverrides": { + "type": "object", + "properties": { + "asr_config": { + "$ref": "#/definitions/github_com_Tencent_WeKnora_internal_types.ASRConfig" + }, + "chunking_config": { + "$ref": "#/definitions/github_com_Tencent_WeKnora_internal_types.ChunkingConfig" + }, + "enable_multimodel": { + "type": "boolean" + }, + "extract_config": { + "$ref": "#/definitions/github_com_Tencent_WeKnora_internal_types.ExtractConfig" + }, + "graph_enabled": { + "type": "boolean" + }, + "parser_engine_rules": { + "type": "array", + "items": { + "$ref": "#/definitions/github_com_Tencent_WeKnora_internal_types.ParserEngineRule" + } + }, + "question_generation_config": { + "$ref": "#/definitions/github_com_Tencent_WeKnora_internal_types.QuestionGenerationConfig" + }, + "vlm_config": { + "$ref": "#/definitions/github_com_Tencent_WeKnora_internal_types.VLMConfig" + } + } + }, "github_com_Tencent_WeKnora_internal_types.ListMembersResponse": { "type": "object", "properties": { @@ -14903,6 +14939,9 @@ "content": { "type": "string" }, + "process_config": { + "$ref": "#/definitions/github_com_Tencent_WeKnora_internal_types.KnowledgeProcessOverrides" + }, "status": { "type": "string" }, @@ -16623,6 +16662,14 @@ "description": "Tool name", "type": "string" }, + "provider_metadata": { + "description": "Provider-specific tool-call state for replay", + "allOf": [ + { + "$ref": "#/definitions/github_com_Tencent_WeKnora_internal_types.ToolCallMetadata" + } + ] + }, "reflection": { "description": "Agent's reflection on this tool call result (if enabled)", "type": "string" @@ -16637,6 +16684,15 @@ } } }, + "github_com_Tencent_WeKnora_internal_types.ToolCallMetadata": { + "type": "object", + "additionalProperties": { + "type": "array", + "items": { + "type": "integer" + } + } + }, "github_com_Tencent_WeKnora_internal_types.ToolResult": { "type": "object", "properties": { diff --git a/docs/swagger.yaml b/docs/swagger.yaml index f7f7ab81..1f0ee667 100644 --- a/docs/swagger.yaml +++ b/docs/swagger.yaml @@ -372,10 +372,6 @@ definitions: chunk_size: description: Chunk size type: integer - enable_multimodal: - description: EnableMultimodal (deprecated, kept for backward compatibility - with old data) - type: boolean enable_parent_child: description: |- EnableParentChild enables two-level parent-child chunking strategy. @@ -1519,6 +1515,27 @@ definitions: description: 最后更新时间 type: integer type: object + github_com_Tencent_WeKnora_internal_types.KnowledgeProcessOverrides: + properties: + asr_config: + $ref: '#/definitions/github_com_Tencent_WeKnora_internal_types.ASRConfig' + chunking_config: + $ref: '#/definitions/github_com_Tencent_WeKnora_internal_types.ChunkingConfig' + enable_multimodel: + type: boolean + extract_config: + $ref: '#/definitions/github_com_Tencent_WeKnora_internal_types.ExtractConfig' + graph_enabled: + type: boolean + parser_engine_rules: + items: + $ref: '#/definitions/github_com_Tencent_WeKnora_internal_types.ParserEngineRule' + type: array + question_generation_config: + $ref: '#/definitions/github_com_Tencent_WeKnora_internal_types.QuestionGenerationConfig' + vlm_config: + $ref: '#/definitions/github_com_Tencent_WeKnora_internal_types.VLMConfig' + type: object github_com_Tencent_WeKnora_internal_types.ListMembersResponse: properties: members: @@ -1705,6 +1722,8 @@ definitions: type: string content: type: string + process_config: + $ref: '#/definitions/github_com_Tencent_WeKnora_internal_types.KnowledgeProcessOverrides' status: type: string tag_id: @@ -3005,6 +3024,10 @@ definitions: name: description: Tool name type: string + provider_metadata: + allOf: + - $ref: '#/definitions/github_com_Tencent_WeKnora_internal_types.ToolCallMetadata' + description: Provider-specific tool-call state for replay reflection: description: Agent's reflection on this tool call result (if enabled) type: string @@ -3013,6 +3036,12 @@ definitions: - $ref: '#/definitions/github_com_Tencent_WeKnora_internal_types.ToolResult' description: Execution result (contains Output) type: object + github_com_Tencent_WeKnora_internal_types.ToolCallMetadata: + additionalProperties: + items: + type: integer + type: array + type: object github_com_Tencent_WeKnora_internal_types.ToolResult: properties: data: @@ -8474,6 +8503,11 @@ paths: name: id required: true type: string + - description: 可选的处理配置覆盖:{\ + in: body + name: body + schema: + type: object produces: - application/json responses: diff --git a/frontend/package-lock.json b/frontend/package-lock.json index a5bbd71c..c07f00f2 100644 --- a/frontend/package-lock.json +++ b/frontend/package-lock.json @@ -1,12 +1,12 @@ { "name": "knowledage-base", - "version": "0.6.0", + "version": "0.6.2", "lockfileVersion": 3, "requires": true, "packages": { "": { "name": "knowledage-base", - "version": "0.6.0", + "version": "0.6.2", "dependencies": { "@microsoft/fetch-event-source": "^2.0.1", "@types/dompurify": "^3.2.0", diff --git a/frontend/package.json b/frontend/package.json index 5827ad80..cbeccfa4 100644 --- a/frontend/package.json +++ b/frontend/package.json @@ -1,6 +1,6 @@ { "name": "knowledage-base", - "version": "0.6.1", + "version": "0.6.2", "private": true, "type": "module", "scripts": { diff --git a/helm/Chart.yaml b/helm/Chart.yaml index 458508b9..d08ab39c 100644 --- a/helm/Chart.yaml +++ b/helm/Chart.yaml @@ -5,7 +5,7 @@ description: | with document parsing, vector search, and LLM integration. type: application version: 0.1.0 -appVersion: "v0.6.1" +appVersion: "v0.6.2" kubeVersion: ">=1.25.0-0" home: https://github.com/Tencent/WeKnora icon: https://raw.githubusercontent.com/Tencent/WeKnora/main/docs/images/logo.png