chore: update mineru & remove outdated version

2025-12-01 09:23:43 +08:00
parent 1c42cb2800
commit 861bb6bb40
14 changed files with 142 additions and 1447 deletions
--- a/builds/mineru-vllm/docker-compose.yaml
+++ b/builds/mineru-vllm/docker-compose.yaml
@@ -1,109 +0,0 @@
-x-defaults: &defaults
-  restart: unless-stopped
-  logging:
-    driver: json-file
-    options:
-      max-size: 100m
-      max-file: "3"
-
-x-mineru-vllm: &mineru-vllm
-  <<: *defaults
-  image: ${GLOBAL_REGISTRY:-}alexsuntop/mineru:${MINERU_VERSION:-2.6.4}
-  build:
-    context: .
-    dockerfile: Dockerfile
-  environment:
-    TZ: ${TZ:-UTC}
-    MINERU_MODEL_SOURCE: local
-  ulimits:
-    memlock: -1
-    stack: 67108864
-  ipc: host
-  deploy:
-    resources:
-      limits:
-        cpus: '16.0'
-        memory: 32G
-      reservations:
-        cpus: '8.0'
-        memory: 16G
-        devices:
-          - driver: nvidia
-            device_ids: [ '0' ]
-            capabilities: [ gpu ]
-
-services:
-  mineru-vllm-server:
-    <<: *mineru-vllm
-    profiles: ["vllm-server"]
-    ports:
-      - ${MINERU_PORT_OVERRIDE_VLLM:-30000}:30000
-    entrypoint: mineru-vllm-server
-    command:
-      - --host 0.0.0.0
-      - --port 30000
-
-      # If using multiple GPUs, increase throughput using vllm's multi-GPU parallel mode.
-      # - --data-parallel-size 2
-      # If running on a single GPU and encountering VRAM shortage, reduce the KV cache size by this parameter,
-      # if VRAM issues persist, try lowering it further to `0.4` or below.
-      # - --gpu-memory-utilization 0.5
-
-    healthcheck:
-      test: ["CMD-SHELL", "curl -f http://localhost:30000/health || exit 1"]
-      interval: 30s
-      timeout: 10s
-      retries: 3
-      start_period: 60s
-
-
-  mineru-api:
-    <<: *mineru-vllm
-    profiles: ["api"]
-    ports:
-      - ${MINERU_PORT_OVERRIDE_API:-8000}:8000
-    entrypoint: mineru-api
-    command:
-      - --host 0.0.0.0
-      - --port 8000
-
-      # If using multiple GPUs, increase throughput using vllm's multi-GPU parallel mode.
-      # - --data-parallel-size 2
-      # If running on a single GPU and encountering VRAM shortage, reduce the KV cache size by this parameter,
-      # if VRAM issues persist, try lowering it further to `0.4` or below.
-      # - --gpu-memory-utilization 0.5
-    healthcheck:
-      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:8000/health"]
-      interval: 30s
-      timeout: 10s
-      retries: 3
-      start_period: 60s
-
-  mineru-gradio:
-    <<: *mineru-vllm
-    profiles: ["gradio"]
-    ports:
-      - ${MINERU_PORT_OVERRIDE_GRADIO:-7860}:7860
-    entrypoint: mineru-gradio
-    command:
-      - --server-name 0.0.0.0
-      - --server-port 7860
-
-      # Enable the vllm engine for Gradio
-      - --enable-vllm-engine true
-      # If you want to disable the API, set this to false
-      # - --enable-api false
-      # If you want to limit the number of pages for conversion, set this to a specific number
-      # - --max-convert-pages 20
-
-      # If using multiple GPUs, increase throughput using vllm's multi-GPU parallel mode.
-      # - --data-parallel-size 2
-      # If running on a single GPU and encountering VRAM shortage, reduce the KV cache size by this parameter,
-      # if VRAM issues persist, try lowering it further to `0.4` or below.
-      # - --gpu-memory-utilization 0.5
-    healthcheck:
-      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:7860/"]
-      interval: 30s
-      timeout: 10s
-      retries: 3
-      start_period: 60s
--- a/builds/mineru-vllm/.env.example
+++ b/builds/mineru-vllm/.env.example
@@ -1,5 +1,5 @@
 # MinerU Docker image
-MINERU_DOCKER_IMAGE=alexsuntop/mineru:2.5.4
+MINERU_DOCKER_IMAGE=alexsuntop/mineru:2.6.5

 # Port configurations
 MINERU_PORT_OVERRIDE_VLLM=30000
--- a/builds/mineru-vllm/Dockerfile
+++ b/builds/mineru-vllm/Dockerfile
--- a/builds/mineru-vllm/README.md
+++ b/builds/mineru-vllm/README.md
@@ -39,7 +39,7 @@ mineru -p demo.pdf -o ./output -b vlm-http-client -u http://localhost:30000

 ## Configuration

- `MINERU_VERSION`: The version for MinerU, default is `2.6.4`.
+- `MINERU_VERSION`: The version for MinerU, default is `2.6.5`.
 - `MINERU_PORT_OVERRIDE_VLLM`: The host port for the VLLM server, default is `30000`.
 - `MINERU_PORT_OVERRIDE_API`: The host port for the API service, default is `8000`.
 - `MINERU_PORT_OVERRIDE_GRADIO`: The host port for the Gradio WebUI, default is `7860`.
--- a/builds/mineru-vllm/README.zh.md
+++ b/builds/mineru-vllm/README.zh.md
@@ -39,7 +39,7 @@ mineru -p demo.pdf -o ./output -b vlm-http-client -u http://localhost:30000

 ## 配置

- `MINERU_VERSION`: MinerU 的 Docker 镜像版本，默认为 `2.6.4`。
+- `MINERU_VERSION`: MinerU 的 Docker 镜像版本，默认为 `2.6.5`。
 - `MINERU_PORT_OVERRIDE_VLLM`: VLLM 服务器的主机端口，默认为 `30000`。
 - `MINERU_PORT_OVERRIDE_API`: API 服务的主机端口，默认为 `8000`。
 - `MINERU_PORT_OVERRIDE_GRADIO`: Gradio WebUI 的主机端口，默认为 `7860`。
--- a/builds/mineru/docker-compose.yaml
+++ b/builds/mineru/docker-compose.yaml
@@ -0,0 +1,139 @@
+x-defaults: &defaults
+  restart: unless-stopped
+  logging:
+    driver: json-file
+    options:
+      max-size: 100m
+      max-file: "3"
+
+x-mineru-vllm: &mineru-vllm
+  <<: *defaults
+  image: ${GLOBAL_REGISTRY:-}alexsuntop/mineru:${MINERU_VERSION:-2.6.5}
+  build:
+    context: .
+    dockerfile: Dockerfile
+  environment:
+    TZ: ${TZ:-UTC}
+    MINERU_MODEL_SOURCE: local
+  ulimits:
+    memlock: -1
+    stack: 67108864
+  ipc: host
+  deploy:
+    resources:
+      limits:
+        cpus: '16.0'
+        memory: 32G
+      reservations:
+        cpus: '8.0'
+        memory: 16G
+        devices:
+          - driver: nvidia
+            device_ids: [ '0' ]
+            capabilities: [ gpu ]
+
+services:
+  mineru-openai-server:
+    <<: *mineru-vllm
+    profiles: ["openai-server"]
+    ports:
+      - ${MINERU_PORT_OVERRIDE_VLLM:-30000}:30000
+    entrypoint: mineru-openai-server
+    command:
+      # ==================== Engine Selection ====================
+      # WARNING: Only ONE engine can be enabled at a time!
+      # Choose 'vllm' OR 'lmdeploy' (uncomment one line below)
+      - --engine vllm
+      # --engine lmdeploy
+
+      # ==================== vLLM Engine Parameters ====================
+      # Uncomment if using --engine vllm
+      - --host 0.0.0.0
+      - --port 30000
+      # Multi-GPU configuration (increase throughput)
+      # --data-parallel-size 2
+      # Single GPU memory optimization (reduce if VRAM insufficient)
+      # --gpu-memory-utilization 0.5  # Try 0.4 or lower if issues persist
+
+      # ==================== LMDeploy Engine Parameters ====================
+      # Uncomment if using --engine lmdeploy
+      # --server-name 0.0.0.0
+      # --server-port 30000
+      # Multi-GPU configuration (increase throughput)
+      # --dp 2
+      # Single GPU memory optimization (reduce if VRAM insufficient)
+      # --cache-max-entry-count 0.5  # Try 0.4 or lower if issues persist
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://localhost:30000/health || exit 1"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 60s
+
+
+  mineru-api:
+    <<: *mineru-vllm
+    profiles: ["api"]
+    ports:
+      - ${MINERU_PORT_OVERRIDE_API:-8000}:8000
+    entrypoint: mineru-api
+    command:
+      # ==================== Server Configuration ====================
+      - --host 0.0.0.0
+      - --port 8000
+
+      # ==================== vLLM Engine Parameters ====================
+      # Multi-GPU configuration
+      # --data-parallel-size 2
+      # Single GPU memory optimization
+      # --gpu-memory-utilization 0.5  # Try 0.4 or lower if VRAM insufficient
+
+      # ==================== LMDeploy Engine Parameters ====================
+      # Multi-GPU configuration
+      # --dp 2
+      # Single GPU memory optimization
+      # --cache-max-entry-count 0.5  # Try 0.4 or lower if VRAM insufficient
+    healthcheck:
+      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:8000/health"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 60s
+
+  mineru-gradio:
+    <<: *mineru-vllm
+    profiles: ["gradio"]
+    ports:
+      - ${MINERU_PORT_OVERRIDE_GRADIO:-7860}:7860
+    entrypoint: mineru-gradio
+    command:
+      # ==================== Gradio Server Configuration ====================
+      - --server-name 0.0.0.0
+      - --server-port 7860
+
+      # ==================== Gradio Feature Settings ====================
+      # --enable-api false  # Disable API endpoint
+      # --max-convert-pages 20  # Limit conversion page count
+
+      # ==================== Engine Selection ====================
+      # WARNING: Only ONE engine can be enabled at a time!
+
+      # Option 1: vLLM Engine (recommended for most users)
+      - --enable-vllm-engine true
+      # Multi-GPU configuration
+      # --data-parallel-size 2
+      # Single GPU memory optimization
+      # --gpu-memory-utilization 0.5  # Try 0.4 or lower if VRAM insufficient
+
+      # Option 2: LMDeploy Engine
+      # --enable-lmdeploy-engine true
+      # Multi-GPU configuration
+      # --dp 2
+      # Single GPU memory optimization
+      # --cache-max-entry-count 0.5  # Try 0.4 or lower if VRAM insufficient
+    healthcheck:
+      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:7860/"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 60s