希望增加gemini-1.5-pro模型的支持

coulsontl commented 7 months ago

API已开放 https://ai.google.dev/models/gemini?hl=zh-cn#model-variations

catsimple commented 7 months ago

curl \
>   -H 'Content-Type: application/json' \
>   -X GET https://generativelanguage.googleapis.com/v1beta/models?key=
{
  "models": [
    {
      "name": "models/chat-bison-001",
      "version": "001",
      "displayName": "PaLM 2 Chat (Legacy)",
      "description": "A legacy text-only model optimized for chat conversations",
      "inputTokenLimit": 4096,
      "outputTokenLimit": 1024,
      "supportedGenerationMethods": [
        "generateMessage",
        "countMessageTokens"
      ],
      "temperature": 0.25,
      "topP": 0.95,
      "topK": 40
    },
    {
      "name": "models/text-bison-001",
      "version": "001",
      "displayName": "PaLM 2 (Legacy)",
      "description": "A legacy model that understands text and generates text as an output",
      "inputTokenLimit": 8196,
      "outputTokenLimit": 1024,
      "supportedGenerationMethods": [
        "generateText",
        "countTextTokens",
        "createTunedTextModel"
      ],
      "temperature": 0.7,
      "topP": 0.95,
      "topK": 40
    },
    {
      "name": "models/embedding-gecko-001",
      "version": "001",
      "displayName": "Embedding Gecko",
      "description": "Obtain a distributed representation of a text.",
      "inputTokenLimit": 1024,
      "outputTokenLimit": 1,
      "supportedGenerationMethods": [
        "embedText",
        "countTextTokens"
      ]
    },
    {
      "name": "models/gemini-1.0-pro",
      "version": "001",
      "displayName": "Gemini 1.0 Pro",
      "description": "The best model for scaling across a wide range of tasks",
      "inputTokenLimit": 30720,
      "outputTokenLimit": 2048,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 0.9,
      "topP": 1,
      "topK": 1
    },
    {
      "name": "models/gemini-1.0-pro-001",
      "version": "001",
      "displayName": "Gemini 1.0 Pro 001 (Tuning)",
      "description": "The best model for scaling across a wide range of tasks. This is a stable model that supports tuning.",
      "inputTokenLimit": 30720,
      "outputTokenLimit": 2048,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createTunedModel"
      ],
      "temperature": 0.9,
      "topP": 1,
      "topK": 1
    },
    {
      "name": "models/gemini-1.0-pro-latest",
      "version": "001",
      "displayName": "Gemini 1.0 Pro Latest",
      "description": "The best model for scaling across a wide range of tasks. This is the latest model.",
      "inputTokenLimit": 30720,
      "outputTokenLimit": 2048,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 0.9,
      "topP": 1,
      "topK": 1
    },
    {
      "name": "models/gemini-1.0-pro-vision-latest",
      "version": "001",
      "displayName": "Gemini 1.0 Pro Vision",
      "description": "The best image understanding model to handle a broad range of applications",
      "inputTokenLimit": 12288,
      "outputTokenLimit": 4096,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 0.4,
      "topP": 1,
      "topK": 32
    },
    {
      "name": "models/gemini-pro",
      "version": "001",
      "displayName": "Gemini 1.0 Pro",
      "description": "The best model for scaling across a wide range of tasks",
      "inputTokenLimit": 30720,
      "outputTokenLimit": 2048,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 0.9,
      "topP": 1,
      "topK": 1
    },
    {
      "name": "models/gemini-pro-vision",
      "version": "001",
      "displayName": "Gemini 1.0 Pro Vision",
      "description": "The best image understanding model to handle a broad range of applications",
      "inputTokenLimit": 12288,
      "outputTokenLimit": 4096,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 0.4,
      "topP": 1,
      "topK": 32
    },
    {
      "name": "models/embedding-001",
      "version": "001",
      "displayName": "Embedding 001",
      "description": "Obtain a distributed representation of a text.",
      "inputTokenLimit": 2048,
      "outputTokenLimit": 1,
      "supportedGenerationMethods": [
        "embedContent"
      ]
    },
    {
      "name": "models/aqa",
      "version": "001",
      "displayName": "Model that performs Attributed Question Answering.",
      "description": "Model trained to return answers to questions that are grounded in provided sources, along with estimating answerable probability.",
      "inputTokenLimit": 7168,
      "outputTokenLimit": 1024,
      "supportedGenerationMethods": [
        "generateAnswer"
      ],
      "temperature": 0.2,
      "topP": 1,
      "topK": 40
    }
  ]
}

curl \
>   -H 'Content-Type: application/json' \
>   -X GET https://generativelanguage.googleapis.com/v1/models?key=
{
  "models": [
    {
      "name": "models/gemini-1.0-pro",
      "version": "001",
      "displayName": "Gemini 1.0 Pro",
      "description": "The best model for scaling across a wide range of tasks",
      "inputTokenLimit": 30720,
      "outputTokenLimit": 2048,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 0.9,
      "topP": 1,
      "topK": 1
    },
    {
      "name": "models/gemini-1.0-pro-001",
      "version": "001",
      "displayName": "Gemini 1.0 Pro 001 (Tuning)",
      "description": "The best model for scaling across a wide range of tasks. This is a stable model that supports tuning.",
      "inputTokenLimit": 30720,
      "outputTokenLimit": 2048,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createTunedModel"
      ],
      "temperature": 0.9,
      "topP": 1,
      "topK": 1
    },
    {
      "name": "models/gemini-1.0-pro-latest",
      "version": "001",
      "displayName": "Gemini 1.0 Pro Latest",
      "description": "The best model for scaling across a wide range of tasks. This is the latest model.",
      "inputTokenLimit": 30720,
      "outputTokenLimit": 2048,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 0.9,
      "topP": 1,
      "topK": 1
    },
    {
      "name": "models/gemini-1.0-pro-vision-latest",
      "version": "001",
      "displayName": "Gemini 1.0 Pro Vision",
      "description": "The best image understanding model to handle a broad range of applications",
      "inputTokenLimit": 12288,
      "outputTokenLimit": 4096,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 0.4,
      "topP": 1,
      "topK": 32
    },
    {
      "name": "models/gemini-pro",
      "version": "001",
      "displayName": "Gemini 1.0 Pro",
      "description": "The best model for scaling across a wide range of tasks",
      "inputTokenLimit": 30720,
      "outputTokenLimit": 2048,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 0.9,
      "topP": 1,
      "topK": 1
    },
    {
      "name": "models/gemini-pro-vision",
      "version": "001",
      "displayName": "Gemini 1.0 Pro Vision",
      "description": "The best image understanding model to handle a broad range of applications",
      "inputTokenLimit": 12288,
      "outputTokenLimit": 4096,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 0.4,
      "topP": 1,
      "topK": 32
    },
    {
      "name": "models/embedding-001",
      "version": "001",
      "displayName": "Embedding 001",
      "description": "Obtain a distributed representation of a text.",
      "inputTokenLimit": 2048,
      "outputTokenLimit": 1,
      "supportedGenerationMethods": [
        "embedContent"
      ]
    }
  ]
}

没有这个模型

songquanpeng commented 7 months ago

我的 key 没有权限，无法测试

coulsontl commented 7 months ago

@songquanpeng 已经可以使用，但是名字是 gemini-1.5-pro-latest

curl 'https://generativelanguage.googleapis.com/v1beta/models?key=xxx'
{
  "models": [
    {
      "name": "models/chat-bison-001",
      "version": "001",
      "displayName": "PaLM 2 Chat (Legacy)",
      "description": "A legacy text-only model optimized for chat conversations",
      "inputTokenLimit": 4096,
      "outputTokenLimit": 1024,
      "supportedGenerationMethods": [
        "generateMessage",
        "countMessageTokens"
      ],
      "temperature": 0.25,
      "topP": 0.95,
      "topK": 40
    },
    {
      "name": "models/text-bison-001",
      "version": "001",
      "displayName": "PaLM 2 (Legacy)",
      "description": "A legacy model that understands text and generates text as an output",
      "inputTokenLimit": 8196,
      "outputTokenLimit": 1024,
      "supportedGenerationMethods": [
        "generateText",
        "countTextTokens",
        "createTunedTextModel"
      ],
      "temperature": 0.7,
      "topP": 0.95,
      "topK": 40
    },
    {
      "name": "models/embedding-gecko-001",
      "version": "001",
      "displayName": "Embedding Gecko",
      "description": "Obtain a distributed representation of a text.",
      "inputTokenLimit": 1024,
      "outputTokenLimit": 1,
      "supportedGenerationMethods": [
        "embedText",
        "countTextTokens"
      ]
    },
    {
      "name": "models/gemini-1.0-pro",
      "version": "001",
      "displayName": "Gemini 1.0 Pro",
      "description": "The best model for scaling across a wide range of tasks",
      "inputTokenLimit": 30720,
      "outputTokenLimit": 2048,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 0.9,
      "topP": 1,
      "topK": 1
    },
    {
      "name": "models/gemini-1.0-pro-001",
      "version": "001",
      "displayName": "Gemini 1.0 Pro 001 (Tuning)",
      "description": "The best model for scaling across a wide range of tasks. This is a stable model that supports tuning.",
      "inputTokenLimit": 30720,
      "outputTokenLimit": 2048,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createTunedModel"
      ],
      "temperature": 0.9,
      "topP": 1,
      "topK": 1
    },
    {
      "name": "models/gemini-1.0-pro-latest",
      "version": "001",
      "displayName": "Gemini 1.0 Pro Latest",
      "description": "The best model for scaling across a wide range of tasks. This is the latest model.",
      "inputTokenLimit": 30720,
      "outputTokenLimit": 2048,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 0.9,
      "topP": 1,
      "topK": 1
    },
    {
      "name": "models/gemini-1.0-pro-vision-latest",
      "version": "001",
      "displayName": "Gemini 1.0 Pro Vision",
      "description": "The best image understanding model to handle a broad range of applications",
      "inputTokenLimit": 12288,
      "outputTokenLimit": 4096,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 0.4,
      "topP": 1,
      "topK": 32
    },
    {
      "name": "models/gemini-1.0-ultra-latest",
      "version": "001",
      "displayName": "Gemini 1.0 Ultra",
      "description": "The most capable model for highly complex tasks",
      "inputTokenLimit": 30720,
      "outputTokenLimit": 2048,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 0.9,
      "topP": 1,
      "topK": 32
    },
    {
      "name": "models/gemini-1.5-pro-latest",
      "version": "001",
      "displayName": "Gemini 1.5 Pro",
      "description": "Mid-size multimodal model that supports up to 1 million tokens",
      "inputTokenLimit": 1048576,
      "outputTokenLimit": 8192,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 2,
      "topP": 0.4,
      "topK": 32
    },
    {
      "name": "models/gemini-pro",
      "version": "001",
      "displayName": "Gemini 1.0 Pro",
      "description": "The best model for scaling across a wide range of tasks",
      "inputTokenLimit": 30720,
      "outputTokenLimit": 2048,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 0.9,
      "topP": 1,
      "topK": 1
    },
    {
      "name": "models/gemini-pro-vision",
      "version": "001",
      "displayName": "Gemini 1.0 Pro Vision",
      "description": "The best image understanding model to handle a broad range of applications",
      "inputTokenLimit": 12288,
      "outputTokenLimit": 4096,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 0.4,
      "topP": 1,
      "topK": 32
    },
    {
      "name": "models/gemini-ultra",
      "version": "001",
      "displayName": "Gemini 1.0 Ultra",
      "description": "The most capable model for highly complex tasks",
      "inputTokenLimit": 30720,
      "outputTokenLimit": 2048,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 0.9,
      "topP": 1,
      "topK": 32
    },
    {
      "name": "models/embedding-001",
      "version": "001",
      "displayName": "Embedding 001",
      "description": "Obtain a distributed representation of a text.",
      "inputTokenLimit": 2048,
      "outputTokenLimit": 1,
      "supportedGenerationMethods": [
        "embedContent"
      ]
    },
    {
      "name": "models/aqa",
      "version": "001",
      "displayName": "Model that performs Attributed Question Answering.",
      "description": "Model trained to return answers to questions that are grounded in provided sources, along with estimating answerable probability.",
      "inputTokenLimit": 7168,
      "outputTokenLimit": 1024,
      "supportedGenerationMethods": [
        "generateAnswer"
      ],
      "temperature": 0.2,
      "topP": 1,
      "topK": 40
    }
  ]
}

Caixiaopig commented 7 months ago

@songquanpeng 已经可以使用，但是名字是 gemini-1.5-pro-latest

curl 'https://generativelanguage.googleapis.com/v1beta/models?key=xxx'
{
  "models": [
    {
      "name": "models/chat-bison-001",
      "version": "001",
      "displayName": "PaLM 2 Chat (Legacy)",
      "description": "A legacy text-only model optimized for chat conversations",
      "inputTokenLimit": 4096,
      "outputTokenLimit": 1024,
      "supportedGenerationMethods": [
        "generateMessage",
        "countMessageTokens"
      ],
      "temperature": 0.25,
      "topP": 0.95,
      "topK": 40
    },
    {
      "name": "models/text-bison-001",
      "version": "001",
      "displayName": "PaLM 2 (Legacy)",
      "description": "A legacy model that understands text and generates text as an output",
      "inputTokenLimit": 8196,
      "outputTokenLimit": 1024,
      "supportedGenerationMethods": [
        "generateText",
        "countTextTokens",
        "createTunedTextModel"
      ],
      "temperature": 0.7,
      "topP": 0.95,
      "topK": 40
    },
    {
      "name": "models/embedding-gecko-001",
      "version": "001",
      "displayName": "Embedding Gecko",
      "description": "Obtain a distributed representation of a text.",
      "inputTokenLimit": 1024,
      "outputTokenLimit": 1,
      "supportedGenerationMethods": [
        "embedText",
        "countTextTokens"
      ]
    },
    {
      "name": "models/gemini-1.0-pro",
      "version": "001",
      "displayName": "Gemini 1.0 Pro",
      "description": "The best model for scaling across a wide range of tasks",
      "inputTokenLimit": 30720,
      "outputTokenLimit": 2048,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 0.9,
      "topP": 1,
      "topK": 1
    },
    {
      "name": "models/gemini-1.0-pro-001",
      "version": "001",
      "displayName": "Gemini 1.0 Pro 001 (Tuning)",
      "description": "The best model for scaling across a wide range of tasks. This is a stable model that supports tuning.",
      "inputTokenLimit": 30720,
      "outputTokenLimit": 2048,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createTunedModel"
      ],
      "temperature": 0.9,
      "topP": 1,
      "topK": 1
    },
    {
      "name": "models/gemini-1.0-pro-latest",
      "version": "001",
      "displayName": "Gemini 1.0 Pro Latest",
      "description": "The best model for scaling across a wide range of tasks. This is the latest model.",
      "inputTokenLimit": 30720,
      "outputTokenLimit": 2048,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 0.9,
      "topP": 1,
      "topK": 1
    },
    {
      "name": "models/gemini-1.0-pro-vision-latest",
      "version": "001",
      "displayName": "Gemini 1.0 Pro Vision",
      "description": "The best image understanding model to handle a broad range of applications",
      "inputTokenLimit": 12288,
      "outputTokenLimit": 4096,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 0.4,
      "topP": 1,
      "topK": 32
    },
    {
      "name": "models/gemini-1.0-ultra-latest",
      "version": "001",
      "displayName": "Gemini 1.0 Ultra",
      "description": "The most capable model for highly complex tasks",
      "inputTokenLimit": 30720,
      "outputTokenLimit": 2048,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 0.9,
      "topP": 1,
      "topK": 32
    },
    {
      "name": "models/gemini-1.5-pro-latest",
      "version": "001",
      "displayName": "Gemini 1.5 Pro",
      "description": "Mid-size multimodal model that supports up to 1 million tokens",
      "inputTokenLimit": 1048576,
      "outputTokenLimit": 8192,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 2,
      "topP": 0.4,
      "topK": 32
    },
    {
      "name": "models/gemini-pro",
      "version": "001",
      "displayName": "Gemini 1.0 Pro",
      "description": "The best model for scaling across a wide range of tasks",
      "inputTokenLimit": 30720,
      "outputTokenLimit": 2048,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 0.9,
      "topP": 1,
      "topK": 1
    },
    {
      "name": "models/gemini-pro-vision",
      "version": "001",
      "displayName": "Gemini 1.0 Pro Vision",
      "description": "The best image understanding model to handle a broad range of applications",
      "inputTokenLimit": 12288,
      "outputTokenLimit": 4096,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 0.4,
      "topP": 1,
      "topK": 32
    },
    {
      "name": "models/gemini-ultra",
      "version": "001",
      "displayName": "Gemini 1.0 Ultra",
      "description": "The most capable model for highly complex tasks",
      "inputTokenLimit": 30720,
      "outputTokenLimit": 2048,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 0.9,
      "topP": 1,
      "topK": 32
    },
    {
      "name": "models/embedding-001",
      "version": "001",
      "displayName": "Embedding 001",
      "description": "Obtain a distributed representation of a text.",
      "inputTokenLimit": 2048,
      "outputTokenLimit": 1,
      "supportedGenerationMethods": [
        "embedContent"
      ]
    },
    {
      "name": "models/aqa",
      "version": "001",
      "displayName": "Model that performs Attributed Question Answering.",
      "description": "Model trained to return answers to questions that are grounded in provided sources, along with estimating answerable probability.",
      "inputTokenLimit": 7168,
      "outputTokenLimit": 1024,
      "supportedGenerationMethods": [
        "generateAnswer"
      ],
      "temperature": 0.2,
      "topP": 1,
      "topK": 40
    }
  ]
}

我在v0.6.4-aplha-1上会出错，没有配置成功，请问你在哪个版本上正常执行了？

coulsontl commented 7 months ago

我在v0.6.4-aplha-1上会出错，没有配置成功，请问你在哪个版本上正常执行了？

我先手动加了个模型映射

{
  "gemini-1.5-pro": "gemini-1.5-pro-latest"
}

Caixiaopig commented 7 months ago

先谢啦！不过我加了模型映射，还是报错

我在v0.6.4-aplha-1上会出错，没有配置成功，请问你在哪个版本上正常执行了？

我先手动加了个模型映射
{
  "gemini-1.5-pro": "gemini-1.5-pro-latest"
}

MapleEve commented 7 months ago

加映射没用，因为地址请求变成了 v1beta

kdkkkd commented 7 months ago

加映射没用，因为地址请求变成了 v1beta

如何修复啊？

songquanpeng commented 7 months ago

设置环境变量 GEMINI_VERSION 即可控制 One API 所使用的版本

songquanpeng commented 7 months ago

版本：v0.6.5-alpha.18

youjin-git commented 7 months ago

咋控制，不生效 v0.6.5-alpha.18 还是不行

youjin-git commented 7 months ago

这样还是不行

buliaoyin commented 7 months ago

这样还是不行

不要加模型映射，手动添加一个gemini-1.5-pro-latest. 我这边成功了。

kdkkkd commented 7 months ago

这样还是不行

你解决了吗？也是卡在gemini1.5这里

BrownTen commented 7 months ago

这样还是不行

你解决了吗？也是卡在gemini1.5这里

看一下# 1232的处理方法我是这样弄了之后，就可以正常使用gemini-1.5-pro了

songquanpeng / one-api

希望增加gemini-1.5-pro模型的支持 #1211