From 31bcf0c43520d39d3c71d3cbc242a5425a048281 Mon Sep 17 00:00:00 2001 From: Sun-ZhenXing <1006925066@qq.com> Date: Thu, 29 Jan 2026 17:37:44 +0800 Subject: [PATCH] chore: update mineru --- builds/mineru/.env.example | 2 +- builds/mineru/Dockerfile | 2 +- builds/mineru/README.md | 2 +- builds/mineru/README.zh.md | 2 +- builds/mineru/docker-compose.yaml | 80 +++++++------------------------ 5 files changed, 21 insertions(+), 67 deletions(-) diff --git a/builds/mineru/.env.example b/builds/mineru/.env.example index 7fdc794..4b2351e 100644 --- a/builds/mineru/.env.example +++ b/builds/mineru/.env.example @@ -1,5 +1,5 @@ # MinerU Docker image -MINERU_VERSION=2.7.2 +MINERU_VERSION=2.7.3 # Port configurations MINERU_PORT_OVERRIDE_VLLM=30000 diff --git a/builds/mineru/Dockerfile b/builds/mineru/Dockerfile index f87afe8..0b3ab4e 100644 --- a/builds/mineru/Dockerfile +++ b/builds/mineru/Dockerfile @@ -19,7 +19,7 @@ RUN apt-get update && \ rm -rf /var/lib/apt/lists/* # Install mineru latest -RUN python3 -m pip install -U 'mineru[core]>=2.7.2' --break-system-packages && \ +RUN python3 -m pip install -U 'mineru[core]>=2.7.3' --break-system-packages && \ python3 -m pip cache purge # Download models and update the configuration file diff --git a/builds/mineru/README.md b/builds/mineru/README.md index c0937d6..a6b0c3a 100644 --- a/builds/mineru/README.md +++ b/builds/mineru/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 `2.7.2`. +- `MINERU_VERSION`: The version for MinerU, default is `2.7.3`. - `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`. diff --git a/builds/mineru/README.zh.md b/builds/mineru/README.zh.md index 09c551b..3a54489 100644 --- a/builds/mineru/README.zh.md +++ b/builds/mineru/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 `2.7.2`。 +- `MINERU_VERSION`: MinerU 的 Docker 镜像版本，默认为 `2.7.3`。 - `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`。 diff --git a/builds/mineru/docker-compose.yaml b/builds/mineru/docker-compose.yaml index bd87251..7beee3c 100644 --- a/builds/mineru/docker-compose.yaml +++ b/builds/mineru/docker-compose.yaml @@ -8,7 +8,7 @@ x-defaults: &defaults x-mineru-vllm: &mineru-vllm <<: *defaults - image: ${GLOBAL_REGISTRY:-}alexsuntop/mineru:${MINERU_VERSION:-2.7.2} + image: ${GLOBAL_REGISTRY:-}alexsuntop/mineru:${MINERU_VERSION:-2.7.3} build: context: . dockerfile: Dockerfile @@ -45,29 +45,10 @@ services: - ${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 + --host 0.0.0.0 + --port 30000 + # --data-parallel-size 2 # If using multiple GPUs, increase throughput using vllm's multi-GPU parallel mode + # --gpu-memory-utilization 0.9 # 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. healthcheck: test: ["CMD-SHELL", "curl -f http://localhost:30000/health || exit 1"] interval: 30s @@ -82,21 +63,11 @@ services: - ${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 + --host 0.0.0.0 + --port 8000 + # parameters for vllm-engine + # --data-parallel-size 2 # If using multiple GPUs, increase throughput using vllm's multi-GPU parallel mode + # --gpu-memory-utilization 0.5 # 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. healthcheck: test: [ @@ -119,30 +90,13 @@ services: - ${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 + --server-name 0.0.0.0 + --server-port 7860 + # --enable-api false # If you want to disable the API, set this to false + # --max-convert-pages 20 # If you want to limit the number of pages for conversion, set this to a specific number + # parameters for vllm-engine + # --data-parallel-size 2 # If using multiple GPUs, increase throughput using vllm's multi-GPU parallel mode + # --gpu-memory-utilization 0.5 # 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. healthcheck: test: [