Skip to main content

Add your description here

Project description

项目说明

财蕴天下服务端项目目录

创建项目

# 项目初始化 [默认当前文件夹] 
uv init [project_name] 
# 创建虚拟环境 
uv venv
# 添加依赖(会更新 pyproject.toml) 
uv add "mcp[cli]"
uv add dotenv
uv add flask
uv add gunicorn
uv add websockets
uv add dashscope
uv add requests
uv add deepmerge
uv add alibabacloud-bailian20231229
uv add fastapi
# 同步项目依赖 
uv sync

# 把依赖关系写入文件
uv pip freeze > requirements.txt

# 安装依赖
uv pip install -r requirements.txt

Debug run 本地mcp测试验证

# 先启动mcp sse服务
uv run cytx_mcp_server.py
# 再启动调试工具
uv run mcp dev cytx_mcp_server.py

# fastapi启动
uvicorn main:app --host 0.0.0.0 --port 8001 --reload --debug --log-level debug

# 新的mcp server 启动 -- 报告解读
uv run cytx_report_mcp_server.py

生产 run

# 生产安装python
CPPFLAGS="$(pkg-config --cflags openssl11)" \
LDFLAGS="$(pkg-config --libs openssl11)" \
pyenv install -v 3.12.0

#生产启动mcp server
nohup uv run cytx_mcp_server.py --host 0.0.0.0 --port=8000 > mcp.log 2>&1 &
# 生成启动 报告mcp server
nohup uv run cytx_report_mcp_server.py --host 0.0.0.0 --port=8002 > report.log 2>&1 &

# fastapi启动
uvicorn main:app --host 0.0.0.0 --port 8001 --reload

# fastapi 生产启动
uvicorn -D main:app --host 0.0.0.0 --port 8001 --workers 4

## fastapi 日志输出到文件
nohup uv run uvicorn main:app --host 0.0.0.0 --port 8001 --workers 4 > api.log 2>&1 &

### 生成 stop
~~~  shell
# 查看进程
ps -ef | grep cytx_mcp_server.py
# 停止mcp server
pkill -f cytx_mcp_server.py

#停止gunicorn
pkill -f gunicorn

生产配合nginx使用

     location /cytxapi/ {
          proxy_pass http://127.0.0.1:8001/cytxapi/;

          proxy_set_header Host $host;
          proxy_set_header X-Real-IP $remote_addr;
          #proxy_set_header X-Forwarded-For $proxy_add_xforwarded_for;
          proxy_set_header X-Forwarded-Proto $scheme;

          proxy_connect_timeout 60s;
          proxy_read_timeout 120s;
        }

        location /chatws {
          proxy_pass http://127.0.0.1:8001/chatws;
          proxy_http_version 1.1;
          proxy_set_header Upgrade $http_upgrade;
          proxy_set_header Connection "upgrade";
          proxy_read_timeout 86400s;
          #proxy_write_timeout 86400s;
        }
        
        location /fileUploads/ {
                alias /opt/server/ai-cytx-fastapi/uploads/;
        }

百炼平台mcp server配置

开发环境:
{
    "mcpServers":{
        "CytxApp":{
            "url":"http://123.56.40.34:8000/sse"
        }
    }
}

{
    "mcpServers":{
        "CytxApp":{
            "url":"http://123.56.40.34:8002/sse"
        }
    }
}


{
    "mcpServers": {
        "CytxApp": {
            "command": "uv",
            "args": [
                "run",
                "--with",
                "mcp",
                "--with",
                "websockets",
                "mcp",
                "run",
                "cytx_mcp_server.py"
            ]
        }
    }
}

{
    "mcpServers": {
        "CytxApp": {
            "command": "uvx",
            "args": [
                --from”,
                "ai-cytx-fastapi",
                "run-mcp-server"
            ]
        }
    }
}


测试环境:
{
    "mcpServers":{
        "CytxApp":{
            "url":"http://101.201.61.165:8000/sse"
        }
    }
}

大模型文档说明

提示词说明文档

doc/project/cytx/prompt/prompt-omini.md
doc/project/cytx/prompt/prompt-core.md

知识库相关文档

doc/project/cytx/kb/

接口相关文档

doc/project/cytx/api/

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ai_cytx_fastapi-0.5.0.tar.gz (34.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

ai_cytx_fastapi-0.5.0-py3-none-any.whl (42.3 kB view details)

Uploaded Python 3

File details

Details for the file ai_cytx_fastapi-0.5.0.tar.gz.

File metadata

  • Download URL: ai_cytx_fastapi-0.5.0.tar.gz
  • Upload date:
  • Size: 34.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.6.16

File hashes

Hashes for ai_cytx_fastapi-0.5.0.tar.gz
Algorithm Hash digest
SHA256 128b30bcb67446cb127185caf8e0d9ba1d7530af804c45046673c2a6786c8ff2
MD5 8667f91ba0668b5cb61a5c103e74c127
BLAKE2b-256 fe0e2402c2bcfc617594b6b22aa7589252cdc632baaf2055ae087b8d6408509b

See more details on using hashes here.

File details

Details for the file ai_cytx_fastapi-0.5.0-py3-none-any.whl.

File metadata

File hashes

Hashes for ai_cytx_fastapi-0.5.0-py3-none-any.whl
Algorithm Hash digest
SHA256 ac62c1bce395b0f44e4d952c86cd4e49089f1749c42619f287e4d44beb4ed10a
MD5 da5d98b718fe17411655af73124b8fcf
BLAKE2b-256 b547fc5789f7929e263bbd61a870a5a40d889ed8c82a845a2a08609acd12d846

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page