feat: 更新 Docker 配置和服务说明，优化环境变量和服务命名

- 修改 docker-compose.yml，更新 PADDLEX_URI 环境变量，调整为 http://paddlex-ocr:8080。 - 更新 api.Dockerfile，优化代理环境变量的设置逻辑。 - 修改 paddlex.Dockerfile，更新工作目录和服务启动命令，确保使用新的配置文件。 - 新增 PP-StructureV3.yaml 配置文件，定义新的服务管道。 - 在 README.md 中添加服务说明，列出各服务及其端口信息，提升文档可读性。
2025-06-25 14:16:34 +08:00 · 2025-06-25 14:16:34 +08:00 · bb4ce9e5c2
commit bb4ce9e5c2
parent 4afbb42f96
6 changed files with 264 additions and 13 deletions
--- a/README.md
+++ b/README.md
@ -141,7 +141,22 @@ ark:
    - deepseek-r1-250120
 ```

-本地模型部署参考 [how-to.md](./docs/how-to.md)
+### 服务说明
+
+项目中会启动多个服务，包括但不限于下面
+
+|端口|服务|说明|
+|--|--|--|
+|5173|web|前端服务|
+|5050|api|后端服务|
+|7474, 7687|neo4j|图数据库接口|
+|9000, 9001|minio|文件数据库|
+|19530, 9091|mivlus|向量数据库|
+|30000|mineru|PDF解析（默认不启用）|
+|8080|paddlex|PP-Structure-V3 服务（默认不启用）|
+|8081|vllm|模型本地推理服务（默认不启用）|
+
+

 ### 2. 向量模型和重排序模型

--- a/docker-compose.yml
+++ b/docker-compose.yml
@ -4,8 +4,8 @@ services:
      context: .
      dockerfile: docker/api.Dockerfile
      args:
-        http_proxy: ${HTTP_PROXY:-""}
-        https_proxy: ${HTTPS_PROXY:-""}
+        http_proxy: ${HTTP_PROXY:-}
+        https_proxy: ${HTTPS_PROXY:-}
    image: yuxi-api:0.1.0
    container_name: api-dev
    working_dir: /app
@ -33,7 +33,7 @@ services:
      - NEO4J_PASSWORD=${NEO4J_PASSWORD:-0123456789}
      - MILVUS_URI=${MILVUS_URI:-http://milvus:19530}
      - MINERU_OCR_URI=${MINERU_OCR_URI:-http://mineru:30000}
-      - PADDLEX_URI=${PADDLEX_URI:-http://paddlex:8080}
+      - PADDLEX_URI=${PADDLEX_URI:-http://paddlex-ocr:8080}
      - MINIO_URI=${MINIO_URI:-http://milvus-minio:9000}
      - MODEL_DIR=/models
      - RUNNING_IN_DOCKER=true
@ -202,7 +202,7 @@ services:
      context: .
      dockerfile: docker/paddlex.Dockerfile
    image: paddlex:latest
-    container_name: paddlex
+    container_name: paddlex-ocr
    profiles:
      - all
    volumes:
--- a/docker/PP-StructureV3.yaml
+++ b/docker/PP-StructureV3.yaml
@ -0,0 +1,230 @@
+pipeline_name: PP-StructureV3
+
+batch_size: 8
+
+use_doc_preprocessor: True
+use_seal_recognition: True
+use_table_recognition: True
+use_formula_recognition: True
+use_chart_recognition: True
+use_region_detection: True
+
+
+SubModules:
+  LayoutDetection:
+    module_name: layout_detection
+    model_name: PP-DocLayout_plus-L
+    model_dir: null
+    batch_size: 8
+    threshold:
+      0: 0.3  # paragraph_title
+      1: 0.5  # image
+      2: 0.4  # text
+      3: 0.5  # number
+      4: 0.5  # abstract
+      5: 0.5  # content
+      6: 0.5  # figure_table_chart_title
+      7: 0.3  # formula
+      8: 0.5  # table
+      9: 0.5  # reference
+      10: 0.5 # doc_title
+      11: 0.5 # footnote
+      12: 0.5 # header
+      13: 0.5 # algorithm
+      14: 0.5 # footer
+      15: 0.45 # seal
+      16: 0.5 # chart
+      17: 0.5 # formula_number
+      18: 0.5 # aside_text
+      19: 0.5 # reference_content
+    layout_nms: True
+    layout_unclip_ratio: [1.0, 1.0]
+    layout_merge_bboxes_mode:
+      0: "large"  # paragraph_title
+      1: "large"  # image
+      2: "union"  # text
+      3: "union"  # number
+      4: "union"  # abstract
+      5: "union"  # content
+      6: "union"  # figure_table_chart_title
+      7: "large"  # formula
+      8: "union"  # table
+      9: "union"  # reference
+      10: "union" # doc_title
+      11: "union" # footnote
+      12: "union" # header
+      13: "union" # algorithm
+      14: "union" # footer
+      15: "union" # seal
+      16: "large" # chart
+      17: "union" # formula_number
+      18: "union" # aside_text
+      19: "union" # reference_content
+  ChartRecognition:
+    module_name: chart_recognition
+    model_name: PP-Chart2Table
+    model_dir: null
+    batch_size: 1
+  RegionDetection:
+    module_name: layout_detection
+    model_name: PP-DocBlockLayout
+    model_dir: null
+    layout_nms: True
+    layout_merge_bboxes_mode: "small"
+
+SubPipelines:
+  DocPreprocessor:
+    pipeline_name: doc_preprocessor
+    batch_size: 8
+    use_doc_orientation_classify: True
+    use_doc_unwarping: True
+    SubModules:
+      DocOrientationClassify:
+        module_name: doc_text_orientation
+        model_name: PP-LCNet_x1_0_doc_ori
+        model_dir: null
+        batch_size: 8
+      DocUnwarping:
+        module_name: image_unwarping
+        model_name: UVDoc
+        model_dir: null
+
+  GeneralOCR:
+    pipeline_name: OCR
+    batch_size: 8
+    text_type: general
+    use_doc_preprocessor: False
+    use_textline_orientation: True
+    SubModules:
+      TextDetection:
+        module_name: text_detection
+        model_name: PP-OCRv5_server_det
+        model_dir: null
+        limit_side_len: 736
+        limit_type: min
+        max_side_limit: 4000
+        thresh: 0.3
+        box_thresh: 0.6
+        unclip_ratio: 1.5
+      TextLineOrientation:
+        module_name: textline_orientation
+        model_name: PP-LCNet_x1_0_textline_ori
+        model_dir: null
+        batch_size: 8
+      TextRecognition:
+        module_name: text_recognition
+        model_name: PP-OCRv5_server_rec
+        model_dir: null
+        batch_size: 8
+        score_thresh: 0.0
+
+
+  TableRecognition:
+    pipeline_name: table_recognition_v2
+    use_layout_detection: False
+    use_doc_preprocessor: False
+    use_ocr_model: False
+    SubModules:
+      TableClassification:
+        module_name: table_classification
+        model_name: PP-LCNet_x1_0_table_cls
+        model_dir: null
+
+      WiredTableStructureRecognition:
+        module_name: table_structure_recognition
+        model_name: SLANeXt_wired
+        model_dir: null
+
+      WirelessTableStructureRecognition:
+        module_name: table_structure_recognition
+        model_name: SLANet_plus
+        model_dir: null
+
+      WiredTableCellsDetection:
+        module_name: table_cells_detection
+        model_name: RT-DETR-L_wired_table_cell_det
+        model_dir: null
+
+      WirelessTableCellsDetection:
+        module_name: table_cells_detection
+        model_name: RT-DETR-L_wireless_table_cell_det
+        model_dir: null
+
+      TableOrientationClassify:
+        module_name: doc_text_orientation
+        model_name: PP-LCNet_x1_0_doc_ori
+        model_dir: null
+    SubPipelines:
+      GeneralOCR:
+        pipeline_name: OCR
+        text_type: general
+        use_doc_preprocessor: False
+        use_textline_orientation: True
+        SubModules:
+          TextDetection:
+            module_name: text_detection
+            model_name: PP-OCRv5_server_det
+            model_dir: null
+            limit_side_len: 736
+            limit_type: min
+            max_side_limit: 4000
+            thresh: 0.3
+            box_thresh: 0.4
+            unclip_ratio: 1.5
+          TextLineOrientation:
+            module_name: textline_orientation
+            model_name: PP-LCNet_x1_0_textline_ori
+            model_dir: null
+            batch_size: 8
+          TextRecognition:
+            module_name: text_recognition
+            model_name: PP-OCRv5_server_rec
+            model_dir: null
+            batch_size: 8
+        score_thresh: 0.0
+
+  SealRecognition:
+    pipeline_name: seal_recognition
+    batch_size: 8
+    use_layout_detection: False
+    use_doc_preprocessor: False
+    SubPipelines:
+      SealOCR:
+        pipeline_name: OCR
+        batch_size: 8
+        text_type: seal
+        use_doc_preprocessor: False
+        use_textline_orientation: False
+        SubModules:
+          TextDetection:
+            module_name: seal_text_detection
+            model_name: PP-OCRv4_server_seal_det
+            model_dir: null
+            limit_side_len: 736
+            limit_type: min
+            max_side_limit: 4000
+            thresh: 0.2
+            box_thresh: 0.6
+            unclip_ratio: 0.5
+          TextRecognition:
+            module_name: text_recognition
+            model_name: PP-OCRv5_server_rec
+            model_dir: null
+            batch_size: 8
+            score_thresh: 0
+
+  FormulaRecognition:
+    pipeline_name: formula_recognition
+    batch_size: 8
+    use_layout_detection: False
+    use_doc_preprocessor: False
+    SubModules:
+      FormulaRecognition:
+        module_name: formula_recognition
+        model_name: PP-FormulaNet_plus-L
+        model_dir: null
+        batch_size: 8
+
+Serving:
+  extra:
+    max_num_input_imgs: null
--- a/docker/api.Dockerfile
+++ b/docker/api.Dockerfile
@ -8,11 +8,13 @@ WORKDIR /app
 # 环境变量设置
 ARG http_proxy
 ARG https_proxy
-ENV http_proxy=$http_proxy \
-    https_proxy=$https_proxy \
-    TZ=Asia/Shanghai \
+ENV TZ=Asia/Shanghai \
    UV_LINK_MODE=copy

+# 只有当代理变量不为空时才设置代理
+RUN if [ -n "$http_proxy" ]; then echo "export http_proxy=$http_proxy" >> /etc/environment; fi
+RUN if [ -n "$https_proxy" ]; then echo "export https_proxy=$https_proxy" >> /etc/environment; fi
+
 RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone

 # 安装系统依赖
@ -34,9 +36,6 @@ RUN --mount=type=cache,target=/root/.cache/uv \
 COPY ../src /app/src
 COPY ../server /app/server

-# 关闭代理设置
-RUN unset http_proxy https_proxy
-
 # 同步项目
 RUN --mount=type=cache,target=/root/.cache/uv \
    uv sync
--- a/docker/paddlex.Dockerfile
+++ b/docker/paddlex.Dockerfile
@ -1,12 +1,15 @@
 FROM ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/paddlex:paddlex3.0.1-paddlepaddle3.0.0-gpu-cuda11.8-cudnn8.9-trt8.6

-WORKDIR /paddle
+WORKDIR /root/PaddleX/paddlex

 # 安装 hpi-cpu，如您所指示
 RUN paddlex --install hpi-cpu
+RUN paddlex --install serving
+
+COPY docker/PP-StructureV3.yaml /root/PaddleX/paddlex/PP-StructureV3.yaml

 # 暴露 PaddleX 服务端口
 EXPOSE 8080

 # 运行 PaddleX PP-StructureV3 流水线服务
-CMD ["paddlex", "--serve", "--pipeline", "PP-StructureV3", "--host", "0.0.0.0", "--port", "8080"]
+CMD ["paddlex", "--serve", "--pipeline", "PP-StructureV3.yaml", "--host", "0.0.0.0", "--port", "8080"]
--- a/pyproject.toml
+++ b/pyproject.toml
@ -55,3 +55,7 @@ lint.ignore = ["F401"]  # 忽略的规则
 dev = [
    "vllm>=0.8.5.post1",
 ]
+
+# uv 配置 - 使用阿里云镜像源
+[tool.uv]
+index-url = "https://mirrors.aliyun.com/pypi/simple/"