[Feat] Update for paddleocr 3.5

.gitignore

@@ -12,6 +12,7 @@ inference_results/
 output/
 train_data/
 log/
+
 *.DS_Store
 *.vs
 *.user
@@ -26,9 +27,14 @@ log/
 build/
 dist/
 *.egg-info/
+
 /deploy/android_demo/app/OpenCV/
 /deploy/android_demo/app/PaddleLite/
 /deploy/android_demo/app/.cxx/
 /deploy/android_demo/app/cache/
+
 test_tipc/web/models/
 test_tipc/web/node_modules/
+
+.venv/
+.worktrees/

deploy/paddleocr_vl_docker/build_pipeline.sh

@@ -2,6 +2,9 @@
 
 set -euo pipefail
 
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+source "${SCRIPT_DIR}/pip_version_arg.sh"
+
 device_type='nvidia-gpu'
 build_for_offline='false'
 paddleocr_version='3.4.0'
@@ -18,8 +21,8 @@ Usage: $(basename "$0") [OPTIONS]
 Options:
   --device-type <type>      Device type (nvidia-gpu|nvidia-gpu-sm120|hygon-dcu|kunlunxin-xpu|metax-gpu|iluvatar-gpu|huawei-npu|intel-gpu|amd-gpu) [default: ${device_type}]
   --offline                 Build offline version
-  --ppocr-version <ver>     PaddleOCR version [default: ${paddleocr_version}]
-  --pdx-version <ver>       PaddleX version [default: ${paddlex_version}]
+  --ppocr-version <spec>    PaddleOCR version or URL [default: ${paddleocr_version}]
+  --pdx-version <spec>      PaddleX version or URL [default: ${paddlex_version}]
   --platform <platform>     Build platform [default: ${platform}]
   --action <action>         Post-build action: load|push|tar|none [default: ${action}]
                             load: Load to local Docker
@@ -34,6 +37,7 @@ Examples:
   $0 --device-type nvidia-gpu --action push
   $0 --device-type nvidia-gpu --platform linux/amd64,linux/arm64 --action push
   $0 --device-type nvidia-gpu --action tar --platform linux/amd64
+  $0 --pdx-version git+https://github.com/PaddlePaddle/PaddleX.git@main
 EOF
 }
 
@@ -133,6 +137,9 @@ while [[ $# -gt 0 ]]; do
     esac
 done
 
+paddleocr_pip_suffix="$(pip_build_arg_suffix "${paddleocr_version}")"
+paddlex_pip_suffix="$(pip_build_arg_suffix "${paddlex_version}")"
+
 # Validate platform compatibility for load action
 if [[ "${action}" == 'load' ]] && [[ "${platform}" == *','* ]]; then
     echo "Error: Cannot use --action load with multiple platforms" >&2
@@ -155,15 +162,15 @@ if [ ! -f "${dockerfile}" ]; then
 fi
 
 revision="$(git rev-parse --short HEAD)"
-image_version="${revision}-ppocr${paddleocr_version}-pdx${paddlex_version}"
+image_version="${revision}-ppocr$(version_tag_label "${paddleocr_version}")-pdx$(version_tag_label "${paddlex_version}")"
 
 # Image name
 base_image_name='paddleocr-vl'
 
 # Main tags
 main_tag="${registry}/${base_image_name}:${tag_suffix}"
 version_tag="${registry}/${base_image_name}:${tag_suffix/latest/${image_version}}"
-paddleocr_version_tag="${registry}/${base_image_name}:${tag_suffix/latest/paddleocr${paddleocr_version%.*}}"
+paddleocr_version_tag="${registry}/${base_image_name}:${tag_suffix/latest/paddleocr$(version_tag_label "${paddleocr_version}")}"
 
 # Build arguments array
 build_args=(
@@ -173,8 +180,8 @@ build_args=(
     '-t' "${version_tag}"
     '-t' "${paddleocr_version_tag}"
     '--build-arg' "BUILD_FOR_OFFLINE=${build_for_offline}"
-    '--build-arg' "PADDLEOCR_VERSION===${paddleocr_version}"
-    '--build-arg' "PADDLEX_VERSION===${paddlex_version}"
+    '--build-arg' "PADDLEOCR_VERSION=${paddleocr_pip_suffix}"
+    '--build-arg' "PADDLEX_VERSION=${paddlex_pip_suffix}"
     '--build-arg' "http_proxy=${http_proxy:-}"
     '--build-arg' "https_proxy=${https_proxy:-}"
     '--build-arg' "no_proxy=${no_proxy:-}"

deploy/paddleocr_vl_docker/build_vlm.sh

@@ -2,6 +2,9 @@
 
 set -euo pipefail
 
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+source "${SCRIPT_DIR}/pip_version_arg.sh"
+
 device_type='nvidia-gpu'
 backend='vllm'
 build_for_offline='false'
@@ -20,8 +23,8 @@ Options:
   --device-type <type>      Device type (nvidia-gpu|nvidia-gpu-sm120|hygon-dcu|kunlunxin-xpu|metax-gpu|iluvatar-gpu|huawei-npu|intel-gpu|amd-gpu) [default: ${device_type}]
   --backend <backend>       Backend type (vllm|fastdeploy) [default: ${backend}]
   --offline                 Build offline version
-  --ppocr-version <ver>     PaddleOCR version [default: ${paddleocr_version}]
-  --pdx-version <ver>       PaddleX version [default: ${paddlex_version}]
+  --ppocr-version <spec>    PaddleOCR version or URL [default: ${paddleocr_version}]
+  --pdx-version <spec>      PaddleX version or URL [default: ${paddlex_version}]
   --platform <platform>     Build platform [default: ${platform}]
   --action <action>         Post-build action: load|push|tar|none [default: ${action}]
                             load: Load to local Docker
@@ -36,6 +39,7 @@ Examples:
   $0 --device-type nvidia-gpu --backend vllm --action push
   $0 --platform linux/amd64,linux/arm64 --action push
   $0 --action tar --platform linux/amd64
+  $0 --ppocr-version https://github.com/PaddlePaddle/PaddleOCR/archive/main.zip
 EOF
 }
 
@@ -151,6 +155,9 @@ while [[ $# -gt 0 ]]; do
     esac
 done
 
+paddleocr_pip_suffix="$(pip_build_arg_suffix "${paddleocr_version}")"
+paddlex_pip_suffix="$(pip_build_arg_suffix "${paddlex_version}")"
+
 # Validate platform compatibility for load action
 if [[ "${action}" == 'load' ]] && [[ "${platform}" == *','* ]]; then
     echo "Error: Cannot use --action load with multiple platforms" >&2
@@ -173,15 +180,15 @@ if [ ! -f "${dockerfile}" ]; then
 fi
 
 revision="$(git rev-parse --short HEAD)"
-image_version="${revision}-ppocr${paddleocr_version}-pdx${paddlex_version}"
+image_version="${revision}-ppocr$(version_tag_label "${paddleocr_version}")-pdx$(version_tag_label "${paddlex_version}")"
 
 # Image name
 base_image_name="paddleocr-genai-${backend}-server"
 
 # Main tags
 main_tag="${registry}/${base_image_name}:${tag_suffix}"
 version_tag="${registry}/${base_image_name}:${tag_suffix/latest/${image_version}}"
-paddleocr_version_tag="${registry}/${base_image_name}:${tag_suffix/latest/paddleocr${paddleocr_version%.*}}"
+paddleocr_version_tag="${registry}/${base_image_name}:${tag_suffix/latest/paddleocr$(version_tag_label "${paddleocr_version}")}"
 
 # Build arguments array
 build_args=(
@@ -191,8 +198,8 @@ build_args=(
     '-t' "${version_tag}"
     '-t' "${paddleocr_version_tag}"
     '--build-arg' "BUILD_FOR_OFFLINE=${build_for_offline}"
-    '--build-arg' "PADDLEOCR_VERSION===${paddleocr_version}"
-    '--build-arg' "PADDLEX_VERSION===${paddlex_version}"
+    '--build-arg' "PADDLEOCR_VERSION=${paddleocr_pip_suffix}"
+    '--build-arg' "PADDLEX_VERSION=${paddlex_pip_suffix}"
     '--build-arg' "BACKEND=${backend}"
     '--build-arg' "http_proxy=${http_proxy:-}"
     '--build-arg' "https_proxy=${https_proxy:-}"

deploy/paddleocr_vl_docker/pip_version_arg.sh

@@ -0,0 +1,47 @@
+#!/usr/bin/env bash
+
+pip_build_arg_suffix() {
+    local v="$1"
+    [[ -z "$v" ]] && {
+        echo ""
+        return
+    }
+    if [[ "$v" == '=='* ]]; then
+        echo "$v"
+        return
+    fi
+    if [[ "$v" == '>='* ]] || [[ "$v" == '<='* ]] || [[ "$v" == '~='* ]] || [[ "$v" == '!='* ]]; then
+        echo "$v"
+        return
+    fi
+    if [[ "$v" == '<'* ]] || [[ "$v" == '>'* ]]; then
+        echo "$v"
+        return
+    fi
+    if [[ "$v" =~ ^(https?://|git\+|file://) ]]; then
+        echo " @${v}"
+        return
+    fi
+    if [[ "$v" == @* ]]; then
+        echo " @${v#@}"
+        return
+    fi
+    echo "==${v}"
+}
+
+version_tag_label() {
+    local v="$1"
+    if [[ "$v" =~ ^(https?://|git\+|file://) ]] || [[ "$v" == @* ]]; then
+        if command -v shasum >/dev/null 2>&1; then
+            printf 'u%s' "$(printf '%s' "$v" | shasum -a 256 | cut -c1-8)"
+        elif command -v sha256sum >/dev/null 2>&1; then
+            printf 'u%s' "$(printf '%s' "$v" | sha256sum | cut -c1-8)"
+        else
+            printf 'u%s' "$(printf '%s' "$v" | cksum | cut -c1-8)"
+        fi
+    else
+        local s="$v"
+        [[ "$s" == '=='* ]] && s="${s#==}"
+        echo "${s%.*}"
+    fi
+}

docs/version3.x/deployment/high_performance_inference.en.md

@@ -16,6 +16,8 @@ This document primarily introduces the installation and usage methods for high-p
 
 ### 1.1 Install High-Performance Inference Dependencies
 
+The high-performance inference functionality depends on the PaddlePaddle framework, so before proceeding to the subsequent steps, you need to ensure that PaddlePaddle is installed in your environment.
+
 Install the dependencies required for high-performance inference using the PaddleOCR CLI:
 
 ```bash

docs/version3.x/deployment/high_performance_inference.md

@@ -16,6 +16,8 @@ comments: true
 
 ## 1.1 安装高性能推理依赖
 
+高性能推理功能依赖于飞桨框架，因此，在进行后续步骤前，您需要确保环境中安装有飞桨框架。
+
 通过 PaddleOCR CLI 安装高性能推理所需依赖：
 
 ```bash