GV

GeezerVison

The World Wide Web, restored to 800 pixels of glory.

Home|About|Gaming cabinet|Archives|How it works|Starter sites

On this site

  • Sign in
  • ActionsCI/CD and automation
  • CodespacesCloud development environments
  • All Features
  • Documentation
  • Training
  • Certifications
  • Build with Copilot
  • Customize Copilot
  • Integrations
  • Trending repos
  • GitHub Sponsors
  • Developer articles
  • Enterprises

This view

  • Original page
  • New address

GeezerVison is showing github.com — Support on-premise deployment and connect to self-hosted AI model · Issue #94 · sqlchat/sqlchat

Support on-premise deployment and connect to self-hosted AI model #94

New issue
Copy link
New issue
Copy link
Open
Open
Support on-premise deployment and connect to self-hosted AI model#94
Copy link
Labels
enhancementNew feature or requestNew feature or request

Description

@xisungod
xisungod
opened on May 18, 2023
Issue body actions

我想部署在离线内网服务器上,所以能支持其他离线ai模型吗?GPT需要联网,支持自定义AI模型吗

Reacted by Zhang Wenbin and Markus Skyttner

Activity

  1. tianzhou
    changed the title [-]我想部署在离线内网服务器上,所以能支持其他离线ai模型吗?GPT需要联网,支持自定义AI模型吗[/-] [+]Support on-premise deployment and connect to self-hosted AI model[/+] on May 18, 2023
  2. tianzhou
    added
    enhancementNew feature or requestNew feature or request
    on Jun 17, 2023
  3. 502647092 commented on Jul 4, 2024

    @502647092
    502647092
    on Jul 4, 2024
    More actions

    可以自己本地部署 Ollama
    通过 ollama cp 模型名称 gpt-4 复制一个模型

  4. 502647092 commented on Jul 17, 2024

    @502647092
    502647092
    on Jul 17, 2024
    More actions

    可以自己本地部署Ollama 通过 ollama cp 模型名称 gpt-4 复制一个模型

    有具体文档可以参考吗

    直接 docker compose 起一个 ollama

    version: "3.3"
    services:
      ollama:
        deploy:
          resources:
            reservations:
              devices:
                - driver: nvidia
                  count: all
                  capabilities:
                    - gpu
        image: ollama/ollama
        volumes:
          - ./ollama:/root/.ollama
        environment:
          - OLLAMA_ORIGINS=*
          - OLLAMA_MAX_QUEUE=256
          - OLLAMA_KEEP_ALIVE=-1
          - OLLAMA_NUM_PARALLEL=16
          - OLLAMA_MAX_LOADED_MODELS=4
        restart: always
        container_name: ollama
        ports:
          - 11434:11434
    networks: {}
    

    然后 docker exec -it ollama bash 终端
    拉取 glm4 或者 qwen2 模型

    ollama pull glm4
    

    然后复制模型到 gpt4

    ollama cp glm4 gpt4
    

    之后就可以用了

  5. unstoppbale9527 commented on Aug 21, 2025

    @unstoppbale9527
    unstoppbale9527
    on Aug 21, 2025
    More actions

    可以自己本地部署 Ollama 通过 ollama cp 模型名称 gpt-4 复制一个模型

    ollama启动模型成功后需要 sqlcaht怎么连接ollama
    docker run --name sqlchat --platform linux/amd64 --env NEXTAUTH_SECRET="$(openssl rand -hex 5)" -p 3000:3000 --hostname 0.0.0.0 sqlchat/sqlchat:latest

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    enhancementNew feature or requestNew feature or request

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions

      You are visitor 01402503 — GeezerVison does not store the pages you look up.
      Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required.