可能是个错误：mineru正常启动了，显存都占用了，但是网页端还提示没有mineru不可用。试了重启容器也不管用

[simple123456T]

docker logs -f mineru

(base) root@ubuntu:~# docker logs -f mineru
INFO 11-06 17:33:22 [__init__.py:241] Automatically detected platform cuda.
2025-11-06 17:33:29.875 | INFO     | mineru.backend.vlm.utils:enable_custom_logits_processors:43 - compute_capability: 8.9 >= 8.0 and vllm version: 0.10.1.1 >= 0.10.1, enable custom_logits_processors
start vllm server: ['/usr/local/bin/mineru-vllm-server', 'serve', '/root/.cache/modelscope/hub/models/OpenDataLab/MinerU2___5-2509-1___2B', '--host', '0.0.0.0', '--port', '30000', '--gpu-memory-utilization', '0.5', '--logits-processors', 'mineru_vl_utils:MinerULogitsProcessor']
(APIServer pid=1) INFO 11-06 17:33:30 [api_server.py:1805] vLLM API server version 0.10.1.1
(APIServer pid=1) INFO 11-06 17:33:30 [utils.py:326] non-default args: {'model_tag': '/root/.cache/modelscope/hub/models/OpenDataLab/MinerU2___5-2509-1___2B', 'host': '0.0.0.0', 'port': 30000, 'model': '/root/.cache/modelscope/hub/models/OpenDataLab/MinerU2___5-2509-1___2B', 'logits_processors': ['mineru_vl_utils:MinerULogitsProcessor'], 'gpu_memory_utilization': 0.5}
(APIServer pid=1) INFO 11-06 17:33:34 [__init__.py:711] Resolved architecture: Qwen2VLForConditionalGeneration
(APIServer pid=1) INFO 11-06 17:33:34 [__init__.py:1750] Using max model len 16384
(APIServer pid=1) INFO 11-06 17:33:34 [scheduler.py:222] Chunked prefill is enabled with max_num_batched_tokens=2048.
INFO 11-06 17:33:37 [__init__.py:241] Automatically detected platform cuda.
(EngineCore_0 pid=135) INFO 11-06 17:33:38 [core.py:636] Waiting for init message from front-end.
(EngineCore_0 pid=135) INFO 11-06 17:33:38 [core.py:74] Initializing a V1 LLM engine (v0.10.1.1) with config: model='/root/.cache/modelscope/hub/models/OpenDataLab/MinerU2___5-2509-1___2B', speculative_config=None, tokenizer='/root/.cache/modelscope/hub/models/OpenDataLab/MinerU2___5-2509-1___2B', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, override_neuron_config={}, tokenizer_revision=None, trust_remote_code=False, dtype=torch.bfloat16, max_seq_len=16384, download_dir=None, load_format=auto, tensor_parallel_size=1, pipeline_parallel_size=1, disable_custom_all_reduce=False, quantization=None, enforce_eager=False, kv_cache_dtype=auto, device_config=cuda, decoding_config=DecodingConfig(backend='auto', disable_fallback=False, disable_any_whitespace=False, disable_additional_properties=False, reasoning_backend=''), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None), seed=0, served_model_name=/root/.cache/modelscope/hub/models/OpenDataLab/MinerU2___5-2509-1___2B, enable_prefix_caching=True, chunked_prefill_enabled=True, use_async_output_proc=True, pooler_config=None, compilation_config={"level":3,"debug_dump_path":"","cache_dir":"","backend":"","custom_ops":[],"splitting_ops":["vllm.unified_attention","vllm.unified_attention_with_output","vllm.mamba_mixer2"],"use_inductor":true,"compile_sizes":[],"inductor_compile_config":{"enable_auto_functionalized_v2":false},"inductor_passes":{},"cudagraph_mode":1,"use_cudagraph":true,"cudagraph_num_of_warmups":1,"cudagraph_capture_sizes":[512,504,496,488,480,472,464,456,448,440,432,424,416,408,400,392,384,376,368,360,352,344,336,328,320,312,304,296,288,280,272,264,256,248,240,232,224,216,208,200,192,184,176,168,160,152,144,136,128,120,112,104,96,88,80,72,64,56,48,40,32,24,16,8,4,2,1],"cudagraph_copy_inputs":false,"full_cuda_graph":false,"pass_config":{},"max_capture_size":512,"local_cache_dir":null}
(EngineCore_0 pid=135) INFO 11-06 17:33:40 [parallel_state.py:1134] rank 0 in world size 1 is assigned as DP rank 0, PP rank 0, TP rank 0, EP rank 0
(EngineCore_0 pid=135) INFO 11-06 17:33:40 [topk_topp_sampler.py:50] Using FlashInfer for top-p & top-k sampling.
(EngineCore_0 pid=135) INFO 11-06 17:33:42 [gpu_model_runner.py:1953] Starting to load model /root/.cache/modelscope/hub/models/OpenDataLab/MinerU2___5-2509-1___2B...
(EngineCore_0 pid=135) INFO 11-06 17:33:42 [gpu_model_runner.py:1985] Loading model from scratch...
(EngineCore_0 pid=135) WARNING 11-06 17:33:42 [cuda.py:211] Current `vllm-flash-attn` has a bug inside vision module, so we use xformers backend instead. You can run `pip install flash-attn` to use flash-attention backend.
(EngineCore_0 pid=135) INFO 11-06 17:33:42 [cuda.py:328] Using Flash Attention backend on V1 engine.
2025-11-06 17:33:42.305904169 [W:onnxruntime:Default, device_discovery.cc:164 DiscoverDevicesForPlatform] GPU device discovery failed: device_discovery.cc:89 ReadFileContents Failed to open file: "/sys/class/drm/card0/device/vendor"
Loading safetensors checkpoint shards:   0% Completed | 0/1 [00:00<?, ?it/s]
Loading safetensors checkpoint shards: 100% Completed | 1/1 [00:00<00:00,  3.60it/s]
Loading safetensors checkpoint shards: 100% Completed | 1/1 [00:00<00:00,  3.59it/s]
(EngineCore_0 pid=135) 
(EngineCore_0 pid=135) INFO 11-06 17:33:42 [default_loader.py:262] Loading weights took 0.31 seconds
(EngineCore_0 pid=135) INFO 11-06 17:33:43 [gpu_model_runner.py:2007] Model loading took 2.1641 GiB and 0.606546 seconds
(EngineCore_0 pid=135) INFO 11-06 17:33:43 [gpu_model_runner.py:2591] Encoder cache will be initialized with a budget of 14175 tokens, and profiled with 1 video items of the maximum feature size.
(EngineCore_0 pid=135) INFO 11-06 17:33:47 [backends.py:548] Using cache directory: /root/.cache/vllm/torch_compile_cache/2d5451fb12/rank_0_0/backbone for vLLM's torch.compile
(EngineCore_0 pid=135) INFO 11-06 17:33:47 [backends.py:559] Dynamo bytecode transform time: 1.96 s
(EngineCore_0 pid=135) INFO 11-06 17:33:49 [backends.py:194] Cache the graph for dynamic shape for later use
(EngineCore_0 pid=135) [rank0]:W1106 17:33:50.191000 135 torch/_inductor/utils.py:1250] [0/0] Not enough SMs to use max_autotune_gemm mode
(EngineCore_0 pid=135) INFO 11-06 17:33:58 [backends.py:215] Compiling a graph for dynamic shape takes 10.67 s
(EngineCore_0 pid=135) INFO 11-06 17:34:06 [monitor.py:34] torch.compile takes 12.63 s in total
(EngineCore_0 pid=135) /usr/local/lib/python3.12/dist-packages/torch/utils/cpp_extension.py:2356: UserWarning: TORCH_CUDA_ARCH_LIST is not set, all archs for visible cards are included for compilation. 
(EngineCore_0 pid=135) If this is not desired, please set os.environ['TORCH_CUDA_ARCH_LIST'].
(EngineCore_0 pid=135)   warnings.warn(

前端界面

操作步骤

(base) root@ubuntu:/Targetarget/Yuxi-Know-0.3.0# MINERU_VL_SERVER=http://localhost:30000
(base) root@ubuntu:/Targetarget/Yuxi-Know-0.3.0# MINERU_API_URI=http://localhost:30001
(base) root@ubuntu:/Targetarget/Yuxi-Know-0.3.0# docker compose up -d api
[+] Running 4/4
 ✔ Container milvus-etcd-dev  Running                                                                                                0.0s 
 ✔ Container milvus-minio     Healthy                                                                                                0.5s 
 ✔ Container milvus           Healthy                                                                                                0.5s 
 ✔ Container api-dev          Running                                                                                                0.0s 
(base) root@ubuntu:/Targetarget/Yuxi-Know-0.3.0# docker compose up -d mineru-vllm-server mineru-api
[+] Running 2/2
 ✔ Container mineru      Started                                                                                                    17.3s 
 ✔ Container mineru-api  Started                                                                                                    17.5s 
(base) root@ubuntu:/Targetarget/Yuxi-Know-0.3.0# docker ps -a 
CONTAINER ID   IMAGE                                      COMMAND                  CREATED         STATUS                   PORTS                                                                                                NAMES
1243a9db2b4f   mineru-vllm:latest                         "mineru-api --host 0…"   4 minutes ago   Up 3 minutes             0.0.0.0:30001->30001/tcp, [::]:30001->30001/tcp                                                      mineru-api
b727e34a4b71   mineru-vllm:latest                         "mineru-vllm-server …"   4 minutes ago   Up 3 minutes (healthy)   0.0.0.0:30000->30000/tcp, [::]:30000->30000/tcp                                                      mineru
b909f5695821   yuxi-web:0.3.dev                           "docker-entrypoint.s…"   2 hours ago     Up 2 hours               0.0.0.0:5173->5173/tcp, [::]:5173->5173/tcp                                                          web-dev
97337eb8d28a   yuxi-api:0.3.dev                           "uv run --no-dev uvi…"   2 hours ago     Up 2 hours (healthy)     0.0.0.0:5050->5050/tcp, [::]:5050->5050/tcp                                                          api-dev
5d264a72fba6   milvusdb/milvus:v2.5.6                     "/tini -- milvus run…"   2 hours ago     Up 2 hours (healthy)     0.0.0.0:9091->9091/tcp, [::]:9091->9091/tcp, 0.0.0.0:19530->19530/tcp, [::]:19530->19530/tcp         milvus
ac415dc5ab23   neo4j:5.26                                 "tini -g -- /startup…"   2 hours ago     Up 2 hours (unhealthy)   0.0.0.0:7474->7474/tcp, [::]:7474->7474/tcp, 7473/tcp, 0.0.0.0:7687->7687/tcp, [::]:7687->7687/tcp   graph
7bf4a64e6a0f   minio/minio:RELEASE.2023-03-20T20-16-18Z   "/usr/bin/docker-ent…"   2 hours ago     Up 2 hours (healthy)     0.0.0.0:9000-9001->9000-9001/tcp, [::]:9000-9001->9000-9001/tcp                                      milvus-minio
573d39fa2dd4   quay.io/coreos/etcd:v3.5.5                 "etcd -advertise-cli…"   2 hours ago     Up 2 hours (healthy)     2379-2380/tcp                                                                                        milvus-etcd-dev
(base) root@ubuntu:/Targetarget/Yuxi-Know-0.3.0# docker ps 
CONTAINER ID   IMAGE                                      COMMAND                  CREATED         STATUS                   PORTS                                                                                                NAMES
1243a9db2b4f   mineru-vllm:latest                         "mineru-api --host 0…"   4 minutes ago   Up 4 minutes             0.0.0.0:30001->30001/tcp, [::]:30001->30001/tcp                                                      mineru-api
b727e34a4b71   mineru-vllm:latest                         "mineru-vllm-server …"   4 minutes ago   Up 4 minutes (healthy)   0.0.0.0:30000->30000/tcp, [::]:30000->30000/tcp                                                      mineru
b909f5695821   yuxi-web:0.3.dev                           "docker-entrypoint.s…"   2 hours ago     Up 2 hours               0.0.0.0:5173->5173/tcp, [::]:5173->5173/tcp                                                          web-dev
97337eb8d28a   yuxi-api:0.3.dev                           "uv run --no-dev uvi…"   2 hours ago     Up 2 hours (healthy)     0.0.0.0:5050->5050/tcp, [::]:5050->5050/tcp                                                          api-dev
5d264a72fba6   milvusdb/milvus:v2.5.6                     "/tini -- milvus run…"   2 hours ago     Up 2 hours (healthy)     0.0.0.0:9091->9091/tcp, [::]:9091->9091/tcp, 0.0.0.0:19530->19530/tcp, [::]:19530->19530/tcp         milvus
ac415dc5ab23   neo4j:5.26                                 "tini -g -- /startup…"   2 hours ago     Up 2 hours (unhealthy)   0.0.0.0:7474->7474/tcp, [::]:7474->7474/tcp, 7473/tcp, 0.0.0.0:7687->7687/tcp, [::]:7687->7687/tcp   graph
7bf4a64e6a0f   minio/minio:RELEASE.2023-03-20T20-16-18Z   "/usr/bin/docker-ent…"   2 hours ago     Up 2 hours (healthy)     0.0.0.0:9000-9001->9000-9001/tcp, [::]:9000-9001->9000-9001/tcp                                      milvus-minio
573d39fa2dd4   quay.io/coreos/etcd:v3.5.5                 "etcd -advertise-cli…"   2 hours ago     Up 2 hours (healthy)     2379-2380/tcp                                                                                        milvus-etcd-dev
(base) root@ubuntu:/Targetarget/Yuxi-Know-0.3.0

[simple123456T]

(base) root@ubuntu:/Targetarget/Yuxi-Know-0.3.0# curl http://localhost:30001/health
{"detail":"Not Found"}

下面是mineru-api 容器的日志：
The API documentation can be accessed at the following address:
- Swagger UI: http://0.0.0.0:30001/docs
- ReDoc: http://0.0.0.0:30001/redoc
INFO:     172.19.0.1:47164 - "GET /health HTTP/1.1" 404 Not Found

[xerrors]

@simple123456T 如果是在同一台机器上，尝试将环境变量修改为：

MINERU_VL_SERVER=http://host.docker.internal:30000
MINERU_API_URI=http://host.docker.internal:30001

这是由于 docker 内部无法访问宿主机的 localhost

[simple123456T]

还是不行，是不是你的代码写错：

root@ubuntu:/Targetarget/Yuxi-Know-0.3.0# export MINERU_VL_SERVER=http://host.docker.internal:30000
root@ubuntu:/Targetarget/Yuxi-Know-0.3.0# export MINERU_API_URI=http://host.docker.internal:30001
root@ubuntu:/Targetarget/Yuxi-Know-0.3.0# docker compose up -d mineru-vllm-server mineru-api
[+] Running 3/3
 ✔ Network yuxi-know-030_default  Created                                               0.1s 
 ✔ Container mineru-api           Started                                               0.8s 
 ✔ Container mineru               Started                                               0.8s 
root@ubuntu:/Targetarget/Yuxi-Know-0.3.0# docker compose up -d api
[+] Running 4/4
 ✔ Container milvus-minio     Healthy                                                   0.5s 
 ✔ Container milvus-etcd-dev  Running                                                   0.0s 
 ✔ Container milvus           Healthy                                                   0.5s 
 ✔ Container api-dev          Running                                                   0.0s 
root@ubuntu:/Targetarget/Yuxi-Know-0.3.0# docker ps 
CONTAINER ID   IMAGE                                      COMMAND                  CREATED          STATUS                      PORTS                                                                                                NAMES
9b3e0640f2e8   mineru-vllm:latest                         "mineru-api --host 0…"   2 minutes ago    Up 2 minutes                0.0.0.0:30001->30001/tcp, [::]:30001->30001/tcp                                                      mineru-api
61855191cd98   mineru-vllm:latest                         "mineru-vllm-server …"   2 minutes ago    Up 2 minutes (healthy)      0.0.0.0:30000->30000/tcp, [::]:30000->30000/tcp                                                      mineru
5618f2a4baa9   paddlex:latest                             "/opt/nvidia/nvidia_…"   10 minutes ago   Up 10 minutes (unhealthy)   22/tcp, 0.0.0.0:8080->8080/tcp, [::]:8080->8080/tcp                                                  paddlex-ocr
c086539a3c37   yuxi-web:0.3.dev                           "docker-entrypoint.s…"   11 minutes ago   Up 11 minutes               0.0.0.0:5173->5173/tcp, [::]:5173->5173/tcp                                                          web-dev
5a023fa90eb1   yuxi-api:0.3.dev                           "uv run --no-dev uvi…"   11 minutes ago   Up 11 minutes (healthy)     0.0.0.0:5050->5050/tcp, [::]:5050->5050/tcp                                                          api-dev
9401ed8712cf   milvusdb/milvus:v2.5.6                     "/tini -- milvus run…"   11 minutes ago   Up 11 minutes (healthy)     0.0.0.0:9091->9091/tcp, [::]:9091->9091/tcp, 0.0.0.0:19530->19530/tcp, [::]:19530->19530/tcp         milvus
1e5f9da104b1   minio/minio:RELEASE.2023-03-20T20-16-18Z   "/usr/bin/docker-ent…"   11 minutes ago   Up 11 minutes (healthy)     0.0.0.0:9000-9001->9000-9001/tcp, [::]:9000-9001->9000-9001/tcp                                      milvus-minio
b59a9719053e   neo4j:5.26                                 "tini -g -- /startup…"   11 minutes ago   Up 11 minutes (unhealthy)   0.0.0.0:7474->7474/tcp, [::]:7474->7474/tcp, 7473/tcp, 0.0.0.0:7687->7687/tcp, [::]:7687->7687/tcp   graph
96883d90fcc5   quay.io/coreos/etcd:v3.5.5                 "etcd -advertise-cli…"   11 minutes ago   Up 11 minutes (healthy)     2379-2380/tcp                                                                                        milvus-etcd-dev

我在 api-dev 日志中发现你的log显示的 mineru_ocr，这个是不是和容器名不一样

f667d505d99d/query-params HTTP/1.1" 200
11-07 12:09:40 INFO: 127.0.0.1:55248 - "GET /api/system/health HTTP/1.1" 200
11-07 12:09:42 DEBUG document_processor_factory.py:58: 创建文档处理器: onnx_rapid_ocr
11-07 12:09:42 DEBUG document_processor_factory.py:58: 创建文档处理器: mineru_ocr
11-07 12:09:42 DEBUG document_processor_factory.py:58: 创建文档处理器: paddlex_ocr
11-07 12:09:42 INFO: 172.18.0.7:34118 - "GET /api/system/ocr/health HTTP/1.1" 200
11-07 12:09:58 INFO: 172.18.0.7:40464 - "GET /api/system/ocr/health HTTP/1.1" 200
11-07 12:10:10 INFO: 127.0.0.1:33854 - "GET /api/system/health HTTP/1.1" 200
11-07 12:10:32 INFO: 172.18.0.7:54474 - "GET /api/system/ocr/health HTTP/1.1" 200
11-07 12:10:40 INFO: 127.0.0.1:49702 - "GET /api/system/health HTTP/1.1" 200

[simple123456T]

[simple123456T]

我用了官方的mineru镜像在docker中启动了一遍，暴露的api端口也设置成了30001，但是看到你的前端调用的是30001的根目录，而根目录下也没有路由，所以是不是你的mineru的url路径写错了。不是根目录，而是有其他的路由路径

[xerrors]

按照你图里的情况，你的环境变量就没设置成功啊，还是 localhost

[simple123456T]

之前设置了的，这个是没贴出来的log。

[Dawei-Simayi]

之前设置了的，这个是没贴出来的log。

run一个新的实例就好了