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

新建渠道

FastGPT配置

配置docker-compose

配置令牌和OneAPI部署地址

配置config.json

配置调用的渠道名称和大模型名称

bash 复制代码
{
  "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

相关推荐
研一计算机小白一枚3 分钟前
VRFF: Video Registration and FusionFramework 论文详解
人工智能·深度学习·计算机视觉
Leo.yuan15 分钟前
数据湖是什么?数据湖和数据仓库的区别是什么?
大数据·运维·数据仓库·人工智能·信息可视化
仙人掌_lz36 分钟前
如何打造一款金融推理工具Financial Reasoning Workflow:WebUI+Ollama+Fin-R1+MCP/RAG
人工智能·搜索引擎·ai·金融·llm·rag·mcp
MILI元宇宙38 分钟前
纳米AI搜索与百度AI搜、豆包的核心差异解析
人工智能·百度
SpikeKing1 小时前
LLM - LlamaFactory 的大模型推理 踩坑记录
人工智能·llm·llamafactory
marteker1 小时前
年度峰会上,抖音依靠人工智能和搜索功能吸引广告主
人工智能·搜索引擎
飞哥数智坊1 小时前
AI编程实战:生成结果不合心意,1个简单思路帮你破解
人工智能·cursor
华清远见成都中心1 小时前
大语言模型(LLM)中的KV缓存压缩与动态稀疏注意力机制设计
人工智能·缓存·语言模型
hao_wujing1 小时前
基于梯度的中毒攻击
大数据·人工智能
Lethehong2 小时前
Gemini 2.5 Pro (0605版本) 深度测评与体验指南
人工智能·chatgpt·googlecloud