Documentation
User Guide
Docker Deployment

Docker Deployment

Pre-built Docker images are available on Alibaba Cloud Container Registry for quick containerized deployment.

Available Images

RegionImage
US Westmodelscope-registry.us-west-1.cr.aliyuncs.com/modelscope-repo/sirchmunk:ubuntu22.04-py312-0.0.4
China Beijingmodelscope-registry.cn-beijing.cr.aliyuncs.com/modelscope-repo/sirchmunk:ubuntu22.04-py312-0.0.4

Quick Start

# Pull the image
docker pull modelscope-registry.cn-beijing.cr.aliyuncs.com/modelscope-repo/sirchmunk:ubuntu22.04-py312-0.0.4

# Start the service
docker run -d \
  --name sirchmunk \
  -p 8584:8584 \
  -e LLM_API_KEY="your-api-key-here" \
  -e LLM_BASE_URL="https://api.openai.com/v1" \
  -e LLM_MODEL_NAME="gpt-5.2" \
  -e LLM_TIMEOUT=60.0 \
  -e UI_THEME=light \
  -e UI_LANGUAGE=en \
  -e SIRCHMUNK_VERBOSE=false \
  -v /path/to/your_work_path:/data/sirchmunk \
  -v /path/to/your/docs:/mnt/docs:ro \
  modelscope-registry.cn-beijing.cr.aliyuncs.com/modelscope-repo/sirchmunk:ubuntu22.04-py312-0.0.4

Open http://localhost:8584 to access the WebUI, or call the API directly:

import requests

response = requests.post(
    "http://localhost:8584/api/v1/search",
    json={
        "query": "your search question here",
        "paths": ["/mnt/docs"],
    },
)
print(response.json())

Volume Mounts

MountPurpose
-v /path/to/your_work_path:/data/sirchmunkPersistent storage for knowledge clusters and chat history
-v /path/to/your/docs:/mnt/docs:roMount your document directory (read-only)

Environment Variables

VariableDescriptionDefault
LLM_API_KEYYour LLM API keyrequired
LLM_BASE_URLOpenAI-compatible API base URLhttps://api.openai.com/v1
LLM_MODEL_NAMEModel namegpt-5.2
LLM_TIMEOUTLLM request timeout (seconds)60.0
UI_THEMEWeb UI theme (light or dark)light
UI_LANGUAGEUI language (en or zh)en
SIRCHMUNK_VERBOSEEnable verbose loggingfalse
Tip

For full Docker parameters and advanced usage, see the docker/README.md in the Sirchmunk repository.

docs