OneAPI接入本地大模型+FastGPT调用本地大模型

将Ollama下载的本地大模型配置到OneAPI中,并通过FastGPT调用本地大模型完成对话。

OneAPI配置

新建令牌

在这里插入图片描述

新建渠道

在这里插入图片描述

FastGPT配置

配置docker-compose

配置令牌和OneAPI部署地址
在这里插入图片描述

配置config.json

配置调用的渠道名称和大模型名称

{
  "systemEnv": {
    "pluginBaseUrl": "",
    "vectorMaxProcess": 15,
    "qaMaxProcess": 15,
    "pgHNSWEfSearch": 100
  },
  "chatModels": [
	{
      "model": "qwen:1.8b", 
      "name": "lingmouAIOllama", 
      "maxContext": 8000, 
      "maxResponse": 4000, 
      "quoteMaxToken": 2000, 
      "maxTemperature": 1, 
      "vision": false, 
      "defaultSystemChatPrompt": "" 
    }

  ],
  "qaModels": [
  	{
      "model": "qwen:1.8b", 
      "name": "lingmouAIOllama", 
      "maxContext": 8000, 
      "maxResponse": 4000, 
      "quoteMaxToken": 2000, 
      "maxTemperature": 1, 
      "vision": false, 
      "defaultSystemChatPrompt": "" 
    }
  ],
  "cqModels": [
    {
      "model": "qwen:1.8b", 
      "name": "lingmouAIOllama", 
      "maxContext": 8000, 
      "maxResponse": 4000, 
      "quoteMaxToken": 2000, 
      "maxTemperature": 1, 
      "vision": false, 
      "defaultSystemChatPrompt": "" 
    }
  ],
  "extractModels": [
   	{
      "model": "qwen:1.8b", 
      "name": "lingmouAIOllama", 
      "maxContext": 8000, 
      "maxResponse": 4000, 
      "quoteMaxToken": 2000, 
      "maxTemperature": 1, 
      "vision": false, 
      "defaultSystemChatPrompt": "" 
    }
  ],
  "qgModels": [
    {
      "model": "gpt-3.5-turbo-1106",
      "name": "GPT35-1106",
      "maxContext": 1600,
      "maxResponse": 4000,
      "inputPrice": 0,
      "outputPrice": 0
    }
  ],
  "vectorModels": [
	{
      "model": "text-embedding-v1",
      "name": "lingmouAI",
      "inputPrice": 0,
      "outputPrice": 0,
      "defaultToken": 700,
      "maxToken": 3000,
      "weight": 100
    },
	{
      "model": "text-embedding-ada-002",
      "name": "lingmouAI",
      "inputPrice": 0,
      "outputPrice": 0,
      "defaultToken": 700,
      "maxToken": 3000,
      "weight": 100
    }
  ],
  "reRankModels": [],
  "audioSpeechModels": [
    {
      "model": "tts-1",
      "name": "OpenAI TTS1",
      "inputPrice": 0,
      "outputPrice": 0,
      "voices": [
        { "label": "Alloy", "value": "alloy", "bufferId": "openai-Alloy" },
        { "label": "Echo", "value": "echo", "bufferId": "openai-Echo" },
        { "label": "Fable", "value": "fable", "bufferId": "openai-Fable" },
        { "label": "Onyx", "value": "onyx", "bufferId": "openai-Onyx" },
        { "label": "Nova", "value": "nova", "bufferId": "openai-Nova" },
        { "label": "Shimmer", "value": "shimmer", "bufferId": "openai-Shimmer" }
      ]
    }
  ],
  "whisperModel": {
    "model": "whisper-1",
    "name": "Whisper1",
    "inputPrice": 0,
    "outputPrice": 0
  }
}

FastGPT测试

在这里插入图片描述

相关推荐

最近更新

  1. TCP协议是安全的吗?

    2024-05-25 18:16:27       16 阅读
  2. 阿里云服务器执行yum,一直下载docker-ce-stable失败

    2024-05-25 18:16:27       16 阅读
  3. 【Python教程】压缩PDF文件大小

    2024-05-25 18:16:27       15 阅读
  4. 通过文章id递归查询所有评论(xml)

    2024-05-25 18:16:27       18 阅读

热门阅读

  1. SpringBoot

    2024-05-25 18:16:27       12 阅读
  2. 分账系统说明

    2024-05-25 18:16:27       10 阅读
  3. 探索电子邮件的神奇世界

    2024-05-25 18:16:27       11 阅读
  4. 赶紧收藏!2024 年最常见 20道 Redis面试题(六)

    2024-05-25 18:16:27       12 阅读
  5. Spring的依赖注入

    2024-05-25 18:16:27       9 阅读
  6. JVM-调优之-高内存占用问题排查

    2024-05-25 18:16:27       10 阅读
  7. OOM不会导致JVM退出

    2024-05-25 18:16:27       9 阅读
  8. 「Electron」Electron 应用程序详解

    2024-05-25 18:16:27       12 阅读
  9. 什么是UDP服务器?

    2024-05-25 18:16:27       8 阅读
  10. 根据标签名递归读取xml字符串中element

    2024-05-25 18:16:27       9 阅读
  11. 网络协议——有状态协议和无状态协议

    2024-05-25 18:16:27       10 阅读