开发者-导航 猿导航

Ollama API 文档

发布时间:

目录

模型名称 #

模型名称遵循 Model:tag 格式，其中 Model 可以有一个可选的命名空间，如 example/Model 。一些例子是 orca-mini:3b-q4_1 和 llama3:70b 。标签是可选的，如果没有提供，将默认为 latest 。标签用于标识特定版本。

持续时间 #

所有持续时间均以纳秒为单位返回。

流式响应 #

某些端点以JSON对象的形式流式传输响应。可以通过为这些端点提供 {"stream": false} 来禁用流式传输。

生成一个完成 #

POST /api/generate

为给定的提示提供模型生成响应。这是一个流式端点，因此将有一系列的响应。最终的响应对象将包括请求的统计信息和额外数据。

参数 #

高级参数（可选）:

结构化输出 #

通过在 format 参数中提供 JSON 模式来支持结构化输出。模型将生成与模式匹配的响应。请参见下面的结构化输出示例。

JSON模式 #

通过将 format 参数设置为 json 来启用 JSON 模式。这将使响应结构化为有效的 JSON 对象。请参见下面的 JSON 模式示例。

警告

重要的是要指示模型在 prompt 中使用 JSON。否则，模型可能会生成大量空白字符。

示例 #

流式 #

请求 curl
curl http://localhost:11434/api/generate -d '{
  "model": "llama3.2",
  "prompt": "为什么天空是蓝色的?"
}'
响应 json
{
  "model": "llama3.2",
  "created_at": "2023-08-04T08:52:19.385406455-07:00",
  "response": "The",
  "done": false
}

流中的最终响应还包括关于生成的额外数据：

{
  "model": "llama3.2",
  "created_at": "2023-08-04T19:22:45.499127Z",
  "response": "",
  "done": true,
  "context": [1, 2, 3],
  "total_duration": 10706818083,
  "load_duration": 6338219291,
  "prompt_eval_count": 26,
  "prompt_eval_duration": 130079000,
  "eval_count": 259,
  "eval_duration": 4232710000
}

无流式 #

当流式传输关闭时，可以在一次回复中接收响应。

请求 curl
curl http://localhost:11434/api/generate -d '{
  "model": "llama3.2",
  "prompt": "为什么天空是蓝色的?",
  "stream": false
}'

如果 stream 设置为 false，响应将是一个单个的 JSON 对象：

响应 json
{
  "model": "llama3.2",
  "created_at": "2023-08-04T19:22:45.499127Z",
  "response": "The sky is blue because it is the color of the sky.",
  "done": true,
  "context": [1, 2, 3],
  "total_duration": 5043500667,
  "load_duration": 5025959,
  "prompt_eval_count": 26,
  "prompt_eval_duration": 325953000,
  "eval_count": 290,
  "eval_duration": 4709213000
}

带后缀的请求 #

请求 curl
curl http://localhost:11434/api/generate -d '{
  "model": "codellama:code",
  "prompt": "def compute_gcd(a, b):",
  "suffix": "    return result",
  "options": {
    "temperature": 0
  },
  "stream": false
}'
响应 json
{
  "model": "codellama:code",
  "created_at": "2024-07-22T20:47:51.147561Z",
  "response": "\n  if a == 0:\n    return b\n  else:\n    return compute_gcd(b % a, a)\n\ndef compute_lcm(a, b):\n  result = (a * b) / compute_gcd(a, b)\n",
  "done": true,
  "done_reason": "stop",
  "context": [...],
  "total_duration": 1162761250,
  "load_duration": 6683708,
  "prompt_eval_count": 17,
  "prompt_eval_duration": 201222000,
  "eval_count": 63,
  "eval_duration": 953997000
}

结构化输出的请求 #

请求 curl
curl -X POST http://localhost:11434/api/generate -H "Content-Type: application/json" -d '{
  "model": "llama3.1:8b",
  "prompt": "Ollama is 22 years old and is busy saving the world. Respond using JSON",
  "stream": false,
  "format": {
    "type": "object",
    "properties": {
      "age": {
        "type": "integer"
      },
      "available": {
        "type": "boolean"
      }
    },
    "required": [
      "age",
      "available"
    ]
  }
}'
响应 json
{
  "model": "llama3.1:8b",
  "created_at": "2024-12-06T00:48:09.983619Z",
  "response": "{\n  \"age\": 22,\n  \"available\": true\n}",
  "done": true,
  "done_reason": "stop",
  "context": [1, 2, 3],
  "total_duration": 1075509083,
  "load_duration": 567678166,
  "prompt_eval_count": 28,
  "prompt_eval_duration": 236000000,
  "eval_count": 16,
  "eval_duration": 269000000
}

JSON模式的请求 #

警告

当 format 设置为 json 时，输出将始终是一个格式良好的JSON对象。指导模型以JSON格式响应也同样重要。

请求 curl
curl http://localhost:11434/api/generate -d '{
  "model": "llama3.2",
  "prompt": "一天中不同时间天空的颜色是什么？请使用JSON响应",
  "format": "json",
  "stream": false
}'
响应 json
{
  "model": "llama3.2",
  "created_at": "2023-11-09T21:07:55.186497Z",
  "response": "{\n\"morning\": {\n\"color\": \"blue\"\n},\n\"noon\": {\n\"color\": \"blue-gray\"\n},\n\"afternoon\": {\n\"color\": \"warm gray\"\n},\n\"evening\": {\n\"color\": \"orange\"\n}\n}\n",
  "done": true,
  "context": [1, 2, 3],
  "total_duration": 4648158584,
  "load_duration": 4071084,
  "prompt_eval_count": 36,
  "prompt_eval_duration": 439038000,
  "eval_count": 180,
  "eval_duration": 4196918000
}

response 的值将是一个包含类似以下内容的JSON字符串：

response json
{
  "morning": {
    "color": "blue"
  },
  "noon": {
    "color": "blue-gray"
  },
  "afternoon": {
    "color": "warm gray"
  },
  "evening": {
    "color": "orange"
  }
}

带图像的请求 #

为了向像 llava 或 bakllava 这样的多模态模型提交图像，需要提供一个 base64 编码的 images 列表：

请求 curl
curl http://localhost:11434/api/generate -d '{
  "model": "llava",
  "prompt":"What is in this picture?",
  "stream": false,
  "images": ["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
响应 json
{
  "model": "llava",
  "created_at": "2023-11-03T15:36:02.583064Z",
  "response": "A happy cartoon character, which is cute and cheerful.",
  "done": true,
  "context": [1, 2, 3],
  "total_duration": 2938432250,
  "load_duration": 2559292,
  "prompt_eval_count": 1,
  "prompt_eval_duration": 2195557000,
  "eval_count": 44,
  "eval_duration": 736432000
}

原生模式请求 #

在某些情况下，您可能希望绕过模板系统并提供一个完整的提示。在这种情况下，您可以使用 raw 参数来禁用模板。请注意，原生模式不会返回上下文。

请求 curl
curl http://localhost:11434/api/generate -d '{
  "model": "mistral",
  "prompt": "[INST] why is the sky blue? [/INST]",
  "raw": true,
  "stream": false
}'

请求（可复现输出） #

为了获得可复现的输出，将 seed 设置为一个数字：

生成请求（带选项） #

如果您想在运行时为模型设置自定义选项，而不是在Modelfile中设置，您可以使用 options 参数。以下示例设置了所有可用的选项，但您可以选择性地设置任何选项，并省略您不想覆盖的选项。

请求 curl
curl http://localhost:11434/api/generate -d '{
  "model": "llama3.2",
  "prompt": "为什么天空是蓝色的？",
  "stream": false,
  "options": {
    "num_keep": 5,
    "seed": 42,
    "num_predict": 100,
    "top_k": 20,
    "top_p": 0.9,
    "min_p": 0.0,
    "typical_p": 0.7,
    "repeat_last_n": 33,
    "temperature": 0.8,
    "repeat_penalty": 1.2,
    "presence_penalty": 1.5,
    "frequency_penalty": 1.0,
    "mirostat": 1,
    "mirostat_tau": 0.8,
    "mirostat_eta": 0.6,
    "penalize_newline": true,
    "stop": ["\n", "user:"],
    "numa": false,
    "num_ctx": 1024,
    "num_batch": 2,
    "num_gpu": 1,
    "main_gpu": 0,
    "low_vram": false,
    "vocab_only": false,
    "use_mmap": true,
    "use_mlock": false,
    "num_thread": 8
  }
}'
响应 json
{
  "model": "llama3.2",
  "created_at": "2023-08-04T19:22:45.499127Z",
  "response": "天空是蓝色的，因为它是天空的颜色。",
  "done": true,
  "context": [1, 2, 3],
  "total_duration": 4935886791,
  "load_duration": 534986708,
  "prompt_eval_count": 26,
  "prompt_eval_duration": 107345000,
  "eval_count": 237,
  "eval_duration": 4289432000
}

加载模型 #

如果提供了空提示，模型将被加载到内存中。

请求 curl
curl http://localhost:11434/api/generate -d '{
  "model": "llama3.2"
}'
响应 json
{
  "model": "llama3.2",
  "created_at": "2023-12-18T19:52:07.071755Z",
  "response": "",
  "done": true
}

卸载模型 #

如果提供了空提示，并且 keep_alive 参数设置为 0，模型将从内存中卸载。

请求 curl
curl http://localhost:11434/api/generate -d '{
  "model": "llama3.2",
  "keep_alive": 0
}'
响应 json
{
  "model": "llama3.2",
  "created_at": "2024-09-12T03:54:03.516566Z",
  "response": "",
  "done": true,
  "done_reason": "unload"
}

生成聊天完成 #

POST /api/chat

使用提供的模型在聊天中生成下一条消息。这是一个流式端点，因此将有一系列的响应。可以通过设置 "stream": false 来禁用流式传输。最终的响应对象将包括请求的统计信息和附加数据。

参数 #

message 对象具有以下字段：

高级参数（可选）：

结构化输出 #

通过在 format 参数中提供 JSON 模式，支持结构化输出。模型将生成与模式匹配的响应。请参见下面的 聊天请求（结构化输出） 示例。

示例 #

聊天请求（流式响应） #

发送带有流式响应的聊天消息。

请求 curl
curl http://localhost:11434/api/chat -d '{
  "model": "llama3.2",
  "messages": [
    {
      "role": "user",
      "content": "为什么天空是蓝色的？"
    }
  ]
}'
响应 json
{
  "model": "llama3.2",
  "created_at": "2023-08-04T08:52:19.385406455-07:00",
  "message": {
    "role": "assistant",
    "content": "The",
    "images": null
  },
  "done": false
}
最终响应 json
{
  "model": "llama3.2",
  "created_at": "2023-08-04T19:22:45.499127Z",
  "done": true,
  "total_duration": 4883583458,
  "load_duration": 1334875,
  "prompt_eval_count": 26,
  "prompt_eval_duration": 342546000,
  "eval_count": 282,
  "eval_duration": 4535599000
}

聊天请求（无流式传输） #

请求 curl
curl http://localhost:11434/api/chat -d '{
  "model": "llama3.2",
  "messages": [
    {
      "role": "user",
      "content": "为什么天空是蓝色的？"
    }
  ],
  "stream": false
}'
响应 json
{
  "model": "llama3.2",
  "created_at": "2023-12-12T14:13:43.416799Z",
  "message": {
    "role": "assistant",
    "content": "你好！你今天怎么样？"
  },
  "done": true,
  "total_duration": 5191566416,
  "load_duration": 2154458,
  "prompt_eval_count": 26,
  "prompt_eval_duration": 383809000,
  "eval_count": 298,
  "eval_duration": 4799921000
}

聊天请求（结构化输出） #

请求 curl
curl -X POST http://localhost:11434/api/chat -H "Content-Type: application/json" -d '{
  "model": "llama3.1",
  "messages": [{"role": "user", "content": "Ollama is 22 years old and busy saving the world. Return a JSON object with the age and availability."}],
  "stream": false,
  "format": {
    "type": "object",
    "properties": {
      "age": {
        "type": "integer"
      },
      "available": {
        "type": "boolean"
      }
    },
    "required": [
      "age",
      "available"
    ]
  },
  "options": {
    "temperature": 0
  }
}'
响应 json
{
  "model": "llama3.1",
  "created_at": "2024-12-06T00:46:58.265747Z",
  "message": { "role": "assistant", "content": "{"age": 22, "available": false}" },
  "done_reason": "stop",
  "done": true,
  "total_duration": 2254970291,
  "load_duration": 574751416,
  "prompt_eval_count": 34,
  "prompt_eval_duration": 1502000000,
  "eval_count": 12,
  "eval_duration": 175000000
}

聊天请求（带历史记录） #

发送带有聊天历史记录的聊天消息。您可以使用相同的方法使用多镜头或思维链提示来开始对话。

请求 curl
curl http://localhost:11434/api/chat -d '{
  "model": "llama3.2",
  "messages": [
    {
      "role": "user",
      "content": "why is the sky blue?"
    },
    {
      "role": "assistant",
      "content": "due to rayleigh scattering."
    },
    {
      "role": "user",
      "content": "how is that different than mie scattering?"
    }
  ]
}'
响应 json
{
  "model": "llama3.2",
  "created_at": "2023-08-04T08:52:19.385406455-07:00",
  "message": {
    "role": "assistant",
    "content": "The"
  },
  "done": false
}
最终响应 json
{
  "model": "llama3.2",
  "created_at": "2023-08-04T19:22:45.499127Z",
  "done": true,
  "total_duration": 8113331500,
  "load_duration": 6396458,
  "prompt_eval_count": 61,
  "prompt_eval_duration": 398801000,
  "eval_count": 468,
  "eval_duration": 7701267000
}

聊天请求（带图片） #

发送带有图片的聊天消息。图片应以Base64编码作为数组提供。

请求 curl
curl http://localhost:11434/api/chat -d '{
  "model": "llava",
  "messages": [
    {
      "role": "user",
      "content": "what is in this image?",
      "images": ["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"]
    }
  ]
}'
响应 json
{
  "model": "llava",
  "created_at": "2023-12-13T22:42:50.203334Z",
  "message": {
    "role": "assistant",
    "content": " The image features a cute, little pig with an angry facial expression. It's wearing a heart on its shirt and is waving in the air. This scene appears to be part of a drawing or sketching project.",
    "images": null
  },
  "done": true,
  "total_duration": 1668506709,
  "load_duration": 1986209,
  "prompt_eval_count": 26,
  "prompt_eval_duration": 359682000,
  "eval_count": 83,
  "eval_duration": 1303285000
}

聊天请求（可重现输出） #

请求 curl
curl http://localhost:11434/api/chat -d '{
  "model": "llama3.2",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "options": {
    "seed": 101,
    "temperature": 0
  }
}'
响应 json
{
  "model": "llama3.2",
  "created_at": "2023-12-12T14:13:43.416799Z",
  "message": {
    "role": "assistant",
    "content": "Hello! How are you today?"
  },
  "done": true,
  "total_duration": 5191566416,
  "load_duration": 2154458,
  "prompt_eval_count": 26,
  "prompt_eval_duration": 383809000,
  "eval_count": 298,
  "eval_duration": 4799921000
}

聊天请求（带工具） #

请求 curl
curl http://localhost:11434/api/chat -d '{
  "model": "llama3.2",
  "messages": [
    {
      "role": "user",
      "content": "What is the weather today in Paris?"
    }
  ],
  "stream": false,
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_current_weather",
        "description": "Get the current weather for a location",
        "parameters": {
          "type": "object",
          "properties": {
            "location": {
              "type": "string",
              "description": "The location to get the weather for, e.g. San Francisco, CA"
            },
            "format": {
              "type": "string",
              "description": "The format to return the weather in, e.g. 'celsius' or 'fahrenheit'",
              "enum": ["celsius", "fahrenheit"]
            }
          },
          "required": ["location", "format"]
        }
      }
    }
  ]
}'
响应 json
{
  "model": "llama3.2",
  "created_at": "2024-07-22T20:33:28.123648Z",
  "message": {
    "role": "assistant",
    "content": "",
    "tool_calls": [
      {
        "function": {
          "name": "get_current_weather",
          "arguments": {
            "format": "celsius",
            "location": "Paris, FR"
          }
        }
      }
    ]
  },
  "done_reason": "stop",
  "done": true,
  "total_duration": 885095291,
  "load_duration": 3753500,
  "prompt_eval_count": 122,
  "prompt_eval_duration": 328493000,
  "eval_count": 33,
  "eval_duration": 552222000
}

加载模型 #

如果消息数组为空，模型将被加载到内存中。

请求 curl
curl http://localhost:11434/api/chat -d '{
  "model": "llama3.2",
  "messages": []
}'
响应 json
{
  "model": "llama3.2",
  "created_at":"2024-09-12T21:17:29.110811Z",
  "message": {
    "role": "assistant",
    "content": ""
  },
  "done_reason": "load",
  "done": true
}

卸载模型 #

如果消息数组为空且 keep_alive 参数设置为0，模型将从内存中卸载。

请求 curl
curl http://localhost:11434/api/chat -d '{
  "model": "llama3.2",
  "messages": [],
  "keep_alive": 0
}'
响应 json
{
  "model": "llama3.2",
  "created_at":"2024-09-12T21:33:17.547535Z",
  "message": {
    "role": "assistant",
    "content": ""
  },
  "done_reason": "unload",
  "done": true
}

创建模型 #

POST /api/create

从以下来源创建模型：

如果您从safetensors目录或GGUF文件创建模型，您必须为每个文件创建一个blob，然后在files字段中使用每个blob关联的文件名和SHA256摘要。

参数 #

量化类型 #

类型 推荐
q2_K
q3_K_L
q3_K_M
q3_K_S
q4_0
q4_1
q4_K_M *
q4_K_S
q5_0
q5_1
q5_K_M
q5_K_S
q6_K
q8_0 *

示例 #

创建新模型 #

从现有模型创建新模型。

请求 curl
curl http://localhost:11434/api/create -d '{
  "model": "mario",
  "from": "llama3.2",
  "system": "You are Mario from Super Mario Bros."
}'
响应 json
{"status":"reading model metadata"}
{"status":"creating system layer"}
{"status":"using already created layer sha256:22f7f8ef5f4c791c1b03d7eb414399294764d7cc82c7e94aa81a1feb80a983a2"}
{"status":"using already created layer sha256:8c17c2ebb0ea011be9981cc3922db8ca8fa61e828c5d3f44cb6ae342bf80460b"}
{"status":"using already created layer sha256:7c23fb36d80141c4ab8cdbb61ee4790102ebd2bf7aeff414453177d4f2110e5d"}
{"status":"using already created layer sha256:2e0493f67d0c8c9c68a8aeacdf6a38a2151cb3c4c1d42accf296e19810527988"}
{"status":"using already created layer sha256:2759286baa875dc22de5394b4a925701b1896a7e3f8e53275c36f75a877a82c9"}
{"status":"writing layer sha256:df30045fe90f0d750db82a058109cecd6d4de9c90a3d75b19c09e5f64580bb42"}
{"status":"writing layer sha256:f18a68eb09bf925bb1b669490407c1b1251c5db98dc4d3d81f3088498ea55690"}
{"status":"writing manifest"}
{"status":"success"}

量化模型 #

量化非量化模型。

请求 curl
curl http://localhost:11434/api/create -d '{
  "model": "llama3.1:quantized",
  "from": "llama3.1:8b-instruct-fp16",
  "quantize": "q4_K_M"
}'
响应 json
{"status":"quantizing F16 model to Q4_K_M"}
{"status":"creating new layer sha256:667b0c1932bc6ffc593ed1d03f895bf2dc8dc6df21db3042284a6f4416b06a29"}
{"status":"using existing layer sha256:11ce4ee3e170f6adebac9a991c22e22ab3f8530e154ee669954c4bc73061c258"}
{"status":"using existing layer sha256:0ba8f0e314b4264dfd19df045cde9d4c394a52474bf92ed6a3de22a4ca31a177"}
{"status":"using existing layer sha256:56bb8bd477a519ffa694fc449c2413c6f0e1d3b1c88fa7e3c9d88d3ae49d4dcb"}
{"status":"creating new layer sha256:455f34728c9b5dd3376378bfb809ee166c145b0b4c1f1a6feca069055066ef9a"}
{"status":"writing manifest"}
{"status":"success"}

从GGUF文件创建模型 #

从GGUF文件创建模型。files参数应填写您希望使用的GGUF文件的文件名和SHA256摘要。在调用此API之前，使用/api/blobs/:digest将GGUF文件推送到服务器。

请求 curl
curl http://localhost:11434/api/create -d '{
  "model": "my-gguf-model",
  "files": {
    "test.gguf": "sha256:432f310a77f4650a88d0fd59ecdd7cebed8d684bafea53cbff0473542964f0c3"
  }
}'
响应 json
{"status":"parsing GGUF"}
{"status":"using existing layer sha256:432f310a77f4650a88d0fd59ecdd7cebed8d684bafea53cbff0473542964f0c3"}
{"status":"writing manifest"}
{"status":"success"}

从Safetensors目录创建模型 #

files参数应包括safetensors模型的文件字典，包括每个文件的文件名和SHA256摘要。在调用此API之前，使用/api/blobs/:digest首先将每个文件推送到服务器。文件将保留在缓存中，直到Ollama服务器重新启动。

请求 curl
curl http://localhost:11434/api/create -d '{
  "model": "fred",
  "files": {
    "config.json": "sha256:dd3443e529fb2290423a0c65c2d633e67b419d273f170259e27297219828e389",
    "generation_config.json": "sha256:88effbb63300dbbc7390143fbbdd9d9fa50587b37e8bfd16c8c90d4970a74a36",
    "special_tokens_map.json": "sha256:b7455f0e8f00539108837bfa586c4fbf424e31f8717819a6798be74bef813d05",
    "tokenizer.json": "sha256:bbc1904d35169c542dffbe1f7589a5994ec7426d9e5b609d07bab876f32e97ab",
    "tokenizer_config.json": "sha256:24e8a6dc2547164b7002e3125f10b415105644fcf02bf9ad8b674c87b1eaaed6",
    "model.safetensors": "sha256:1ff795ff6a07e6a68085d206fb84417da2f083f68391c2843cd2b8ac6df8538f"
  }
}'
响应 json
{"status":"converting model"}
{"status":"creating new layer sha256:05ca5b813af4a53d2c2922933936e398958855c44ee534858fcfd830940618b6"}
{"status":"using autodetected template llama3-instruct"}
{"status":"using existing layer sha256:56bb8bd477a519ffa694fc449c2413c6f0e1d3b1c88fa7e3c9d88d3ae49d4dcb"}
{"status":"writing manifest"}
{"status":"success"}

检查Blob是否存在 #

HEAD /api/blobs/:digest

确保用于创建模型的文件blob（二进制大对象）存在于服务器上。这检查的是您的Ollama服务器，而不是ollama.com。

查询参数 #

示例 #

请求 curl
curl -I http://localhost:11434/api/blobs/sha256:29fdb92e57cf0827ded04ae6461b5931d01fa595843f55d36f5b275a52087dd2
响应

如果blob存在，则返回200 OK，如果不存在，则返回404 Not Found。

推送 Blob #

POST /api/blobs/:digest

将文件推送到Ollama服务器以创建一个"blob"（二进制大对象）。

查询参数 #

示例 #

请求 curl
curl -T model.gguf -X POST http://localhost:11434/api/blobs/sha256:29fdb92e57cf0827ded04ae6461b5931d01fa595843f55d36f5b275a52087dd2
响应

如果Blob成功创建，则返回201 Created，如果使用的摘要不符合预期，则返回400 Bad Request。

列出本地模型 #

GET /api/tags

列出可用的本地模型。

示例 #

请求 curl
curl http://localhost:11434/api/tags
响应 json
{
  "models": [
    {
      "name": "codellama:13b",
      "modified_at": "2023-11-04T14:56:49.277302595-07:00",
      "size": 7365960935,
      "digest": "9f438cb9cd581fc025612d27f7c1a6669ff83a8bb0ed86c94fcf4c5440555697",
      "details": {
        "format": "gguf",
        "family": "llama",
        "families": null,
        "parameter_size": "13B",
        "quantization_level": "Q4_0"
      }
    },
    {
      "name": "llama3:latest",
      "modified_at": "2023-12-07T09:32:18.757212583-08:00",
      "size": 3825819519,
      "digest": "fe938a131f40e6f6d40083c9f0f430a515233eb2edaa6d72eb85c50d64f2300e",
      "details": {
        "format": "gguf",
        "family": "llama",
        "families": null,
        "parameter_size": "7B",
        "quantization_level": "Q4_0"
      }
    }
  ]
}

显示模型信息 #

POST /api/show

显示有关模型的信息，包括详细信息、modelfile、模板、参数、许可证和系统提示。

参数 #

示例 #

请求 curl
curl http://localhost:11434/api/show -d '{
  "model": "llama3.2"
}'
响应 json
{
  "modelfile": "# Modelfile generated by "ollama show"\n# To build a new Modelfile based on this one, replace the FROM line with:\n# FROM llava:latest\n\nFROM /Users/matt/.ollama/models/blobs/sha256:200765e1283640ffbd013184bf496e261032fa75b99498a9613be4e94d63ad52\nTEMPLATE """{{ .System }}\nUSER: {{ .Prompt }}\nASSISTANT: """\nPARAMETER num_ctx 4096\nPARAMETER stop "\u003c/s\u003e"\nPARAMETER stop "USER:"\nPARAMETER stop "ASSISTANT:",
  "parameters": "num_keep                       24\nstop                           "<|start_header_id|>"\nstop                           "<|end_header_id|>"\nstop                           "<|eot_id|>"",
  "template": "{{ if .System }}<|start_header_id|>system<|end_header_id|>\n\n{{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>\n\n{{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|>\n\n{{ .Response }}<|eot_id|>",
  "details": {
    "parent_model": "",
    "format": "gguf",
    "family": "llama",
    "families": [
      "llama"
    ],
    "parameter_size": "8.0B",
    "quantization_level": "Q4_0"
  },
  "model_info": {
    "general.architecture": "llama",
    "general.file_type": 2,
    "general.parameter_count": 8030261248,
    "general.quantization_version": 2,
    "llama.attention.head_count": 32,
    "llama.attention.head_count_kv": 8,
    "llama.attention.layer_norm_rms_epsilon": 0.00001,
    "llama.block_count": 32,
    "llama.context_length": 8192,
    "llama.embedding_length": 4096,
    "llama.feed_forward_length": 14336,
    "llama.rope.dimension_count": 128,
    "llama.rope.freq_base": 500000,
    "llama.vocab_size": 128256,
    "tokenizer.ggml.bos_token_id": 128000,
    "tokenizer.ggml.eos_token_id": 128009,
    "tokenizer.ggml.merges": [],            // populates if `verbose=true`
    "tokenizer.ggml.model": "gpt2",
    "tokenizer.ggml.pre": "llama-bpe",
    "tokenizer.ggml.token_type": [],        // populates if `verbose=true`
    "tokenizer.ggml.tokens": []             // populates if `verbose=true`
  }
}

复制模型 #

POST /api/copy

复制模型。从现有模型创建一个具有另一个名称的模型。

示例 #

curl http://localhost:11434/api/copy -d '{
  "source": "llama3.2",
  "destination": "llama3-backup"
}'

响应

如果成功，则返回200 OK，如果源模型不存在，则返回404 Not Found。

删除模型 #

DELETE /api/delete

删除模型及其数据。

参数 #

示例 #

请求 curl
curl -X DELETE http://localhost:11434/api/delete -d '{
  "model": "llama3:13b"
}'

响应

如果成功，则返回200 OK，如果待删除的模型不存在，则返回404 Not Found。

拉取模型 #

POST /api/pull

从ollama库下载模型。已取消的拉取将在上次停止的地方恢复，并且多个调用将共享相同的下载进度。

参数 #

示例 #

请求 curl
curl http://localhost:11434/api/pull -d '{
  "model": "llama3.2"
}'

响应

如果未指定stream，或设置为true，则返回一系列JSON对象：

第一个对象是清单：

{
  "status": "pulling manifest"
}

然后是一系列下载响应。在任何下载完成之前，可能不包括completed键。要下载的文件数量取决于清单中指定的层数量。

{
  "status": "downloading digestname",
  "digest": "digestname",
  "total": 2142590208,
  "completed": 241970
}

在所有文件下载完成后，最终响应是：

{
    "status": "verifying sha256 digest"
}
{
    "status": "writing manifest"
}
{
    "status": "removing any unused layers"
}
{
    "status": "success"
}

如果stream设置为false，则响应是单个JSON对象：

{
  "status": "success"
}

推送模型 #

POST /api/push

将模型上传到模型库。首先需要在ollama.ai注册并添加公钥。

参数 #

示例 #

请求 curl
curl http://localhost:11434/api/push -d '{
  "model": "mattw/pygmalion:latest"
}'

响应

如果未指定stream，或设置为true，则返回一系列JSON对象：

{ "status": "retrieving manifest" }

然后是：

{
  "status": "starting upload",
  "digest": "sha256:bc07c81de745696fdf5afca05e065818a8149fb0c77266fb584d9b2cba3711ab",
  "total": 1928429856
}

然后是一系列上传响应：

{
  "status": "starting upload",
  "digest": "sha256:bc07c81de745696fdf5afca05e065818a8149fb0c77266fb584d9b2cba3711ab",
  "total": 1928429856
}

最后，在上传完成后：

{"status":"pushing manifest"}
{"status":"success"}

如果stream设置为false，则响应是单个JSON对象：

{ "status": "success" }

生成嵌入 #

POST /api/embed

从模型生成嵌入

参数 #

高级参数：

示例 #

请求 curl
curl http://localhost:11434/api/embed -d '{
  "model": "all-minilm",
  "input": "Why is the sky blue?"
}'
响应 json
{
  "model": "all-minilm",
  "embeddings": [[
    0.010071029, -0.0017594862, 0.05007221, 0.04692972, 0.054916814,
    0.008599704, 0.105441414, -0.025878139, 0.12958129, 0.031952348
  ]],
  "total_duration": 14143917,
  "load_duration": 1019500,
  "prompt_eval_count": 8
}

请求（多个输入） #

curl http://localhost:11434/api/embed -d '{
  "model": "all-minilm",
  "input": ["Why is the sky blue?", "Why is the grass green?"]
}'

响应 #

{
  "model": "all-minilm",
  "embeddings": [[
    0.010071029, -0.0017594862, 0.05007221, 0.04692972, 0.054916814,
    0.008599704, 0.105441414, -0.025878139, 0.12958129, 0.031952348
  ],[
    -0.0098027075, 0.06042469, 0.025257962, -0.006364387, 0.07272725,
    0.017194884, 0.09032035, -0.051705178, 0.09951512, 0.09072481
  ]]
}

列出运行中的模型 #

GET /api/ps

列出当前加载到内存中的模型。

示例 #

请求 curl
curl http://localhost:11434/api/ps
响应 json
{
  "models": [
    {
      "name": "mistral:latest",
      "model": "mistral:latest",
      "size": 5137025024,
      "digest": "2ae6f6dd7a3dd734790bbbf58b8909a606e0e7e97e94b7604e0aa7ae4490e6d8",
      "details": {
        "parent_model": "",
        "format": "gguf",
        "family": "llama",
        "families": [
          "llama"
        ],
        "parameter_size": "7.2B",
        "quantization_level": "Q4_0"
      },
      "expires_at": "2024-06-04T14:38:31.83753-07:00",
      "size_vram": 5137025024
    }
  ]
}

生成嵌入 #

警告

此端点已被/api/embed取代

POST /api/embeddings

从模型生成嵌入

参数 #

高级参数：