panda/agent_jrxml
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
13 Commits 2 Branches 0 Tags
da79640259de4514ffb183acaec2a3129a70d59a
Commit Graph

4 Commits

Author SHA1 Message Date
panda c9f003e1b7 feat: 新增 OCR 单据字段精确提取模块 
- 新增 backend/ocr_extractor.py: 两阶段提取流水线 (文档分析 + 字段提取)
- 四种提取策略: 精确KV匹配/模糊KV匹配/正则模式/表格结构匹配
- agent/state.py: 新增 ocr_extraction_result 和 uploaded_file_path 字段
- agent/nodes.py: process_input() 中自动触发 OCR 提取钩子
- app.py: 文件上传时保留图片路径, 总结卡片中展示提取结果
- .env.example: 新增 OCR_USE_GPU / OCR_CONFIDENCE_THRESHOLD 配置项
- tests/test_ocr_extraction.py: 48 个单元测试全部通过
 2026-05-20 08:06:55 +08:00
panda 6467fd4ae5 feat: v3 robustness upgrade — EasyOCR, failure recovery, minimum content check 
- OCR: EasyOCR (primary, ch_sim+en) with PaddleOCR fallback for Windows compatibility
- Validation: _check_minimum_content() rejects empty-shell JRXML (no band/textField)
- Retry: MAX_RETRY 3→5, exhaustion records pending_failure_context for next-turn auto-injection
- Finalize: only saves jrxml_versions on pass, preserves last good final_jrxml on fail
- Extract JRXML: improved empty markdown block handling and XML fragment fallback
- UI: real-time node progress via placeholder updates, initial "analyzing" feedback
- UI: use agent_state (full) instead of node_state (partial) for summary card routing
- UI: unknown template_type now gives LLM meaningful image context instead of metadata
- Docs: updated CLAUDE.md and CODE_GUIDE.md to reflect all v3 changes

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
 2026-05-19 19:15:30 +08:00
panda 70614dff5e feat: comprehensive v2 upgrade — streaming, error KB, file upload, layout analysis 
Major changes:
- Streaming: LLM统一 _BaseLLM 接口 (invoke + stream), generate/modify/correct
  节点使用 get_stream_writer() 实现逐字输出, UI 节点平铺展开自动折叠
- Prompt外部化: 7个prompt拆分到 prompts/*.md, loader.py 支持热重载
- 错误自增长: backend/error_kb.py — 指纹去重 + ChromaDB持久化,
  correct_jrxml→validate 通过时自动入库, retrieve同时搜索错误KB
- 文件上传: backend/file_parser.py — PDF/DOCX/图片/文本解析,
  侧边栏多文件上传, 文本自动注入下一条消息
- A4模板识别: backend/layout_analyzer.py — 三种模式(完整A4/行片段修改/行片段新建),
  PaddleOCR元素提取 + 行分组 + JRXML section匹配
- 会话历史下载: jrxml_versions版本追踪 + 侧边栏历史版本下载按钮
- 预览修复: route_after_save跳过预览/导出意图的验证循环
- Ctrl+C修复: JS注入拦截Streamlit裸c键清缓存

Docs: CLAUDE.md (完整项目文档), ROADMAP.md (改进路线图)

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
 2026-05-19 15:02:53 +08:00
panda 4b43c5d3e4 feat: LangGraph工作流核心 — Agent状态/节点/图 + 验证服务 + 知识库 
agent/
  state.py: AgentState TypedDict（20字段含意图/压缩/会话/撤销）
  nodes.py: 17个节点函数（生成/修改/验证/纠错/意图分类/压缩/撤销/重置）
  graph.py: 17节点状态图，8意图路由分发

验证服务 validation_service/
  main.py: FastAPI服务，lxml XSD验证 + 结构化检查（字段引用/SQL/尺寸）

数据 data/
  sample_templates/: 4个JRXML示例模板
  corrections/: 3个错误修正案例

脚本 scripts/
  init_kb.py: Chroma知识库初始化
 2026-05-14 23:21:10 +08:00