API
端点
约定
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,例如 example/model
。一些示例包括 orca-mini:3b-q4_1
和 llama3:70b
。标签是可选的,如果未提供,则默认为 latest
。标签用于标识特定版本。
持续时间
所有持续时间都以纳秒为单位返回。
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completion
shell
POST /api/generate
生成给定提示的响应。这是一个流式端点,因此将有一系列响应。最终的响应对象将包括请求的统计信息和附加数据。
参数
model
: (必需)模型名称prompt
: 生成响应的提示suffix
: 模型响应后的文本images
: (可选)一个 base64 编码的图像列表(适用于多模态模型,如llava
)
高级参数(可选):
format
: 返回响应的格式。目前唯一接受的值是json
options
: 文档中列出的 Modelfile 中的其他模型参数,例如temperature
system
: 系统消息(覆盖Modelfile
中定义的内容)template
: 使用的提示模板(覆盖Modelfile
中定义的内容)context
: 从先前请求/generate
返回的上下文参数,可用于保持简短的对话记忆stream
: 如果为false
,响应将作为单个响应对象返回,而不是一系列对象raw
: 如果为true
,不会对提示进行任何格式化。如果你在请求 API 时指定了完整的模板提示,可以选择使用raw
参数keep_alive
: 控制请求后模型在内存中保持加载的时间(默认:5m
)
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。请参阅下面的 JSON 模式 示例。
IMPORTANT
重要的是要在 prompt
中指示模型使用 JSON。否则,模型可能会生成大量空白。
示例
生成请求(流式)
请求
shell
curl http://localhost:11434/api/generate -d '{
"model": "llama3.2",
"prompt": "Why is the sky blue?"
}'
响应
返回一个 JSON 对象流:
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含有关生成的其他数据:
total_duration
:生成响应所花费的时间load_duration
:加载模型所花费的时间(纳秒)prompt_eval_count
:提示中的令牌数prompt_eval_duration
:评估提示所花费的时间(纳秒)eval_count
:响应中的令牌数eval_duration
:生成响应所花费的时间(纳秒)context
:用于此响应的对话编码,可以在下一个请求中发送以保持对话记忆response
:如果响应是流式的,则为空;如果不是流式的,将包含完整的响应
要计算响应生成的速度(以每秒令牌数为单位),请使用公式:eval_count
/ eval_duration
* 10^9
。
json
{
"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
}
请求(不使用流式传输)
请求
当关闭流式传输时,可以在一次回复中接收响应。
shell
curl http://localhost:11434/api/generate -d '{
"model": "llama3.2",
"prompt": "Why is the sky blue?",
"stream": false
}'
响应
如果将 stream
设置为 false
,响应将是一个单一的 JSON 对象:
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
}
请求(带后缀)
请求
shell
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
}
请求 (JSON 模式)
IMPORTANT
当 format
设置为 json
时,输出将始终是一个格式良好的 JSON 对象。重要的是还要指示模型以 JSON 格式响应。
请求
shell
curl http://localhost:11434/api/generate -d '{
"model": "llama3.2",
"prompt": "What color is the sky at different times of the day? Respond using JSON",
"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 JSON 的字符串:
json
{
"morning": {
"color": "blue"
},
"noon": {
"color": "blue-gray"
},
"afternoon": {
"color": "warm gray"
},
"evening": {
"color": "orange"
}
}
请求(包含图片)
要向多模态模型(如 llava
或 bakllava
)提交图片,请提供一个 base64 编码的 images
列表:
请求
shell
curl http://localhost:11434/api/generate -d '{
"model": "llava",
"prompt":"What is in this picture?",
"stream": false,
"images": ["iVBORw0KGgoAAAANSUhEUgAAAG0AAABmCAYAAADBPx+VAAAACXBIWXMAAAsTAAALEwEAmpwYAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAA3VSURBVHgB7Z27r0zdG8fX743i1bi1ikMoFMQloXRpKFFIqI7LH4BEQ+NWIkjQuSWCRIEoULk0gsK1kCBI0IhrQVT7tz/7zZo888yz1r7MnDl7z5xvsjkzs2fP3uu71nNfa7lkAsm7d++Sffv2JbNmzUqcc8m0adOSzZs3Z+/XES4ZckAWJEGWPiCxjsQNLWmQsWjRIpMseaxcuTKpG/7HP27I8P79e7dq1ars/yL4/v27S0ejqwv+cUOGEGGpKHR37tzJCEpHV9tnT58+dXXCJDdECBE2Ojrqjh071hpNECjx4cMHVycM1Uhbv359B2F79+51586daxN/+pyRkRFXKyRDAqxEp4yMlDDzXG1NPnnyJKkThoK0VFd1ELZu3TrzXKxKfW7dMBQ6bcuWLW2v0VlHjx41z717927ba22U9APcw7Nnz1oGEPeL3m3p2mTAYYnFmMOMXybPPXv2bNIPpFZr1NHn4HMw0KRBjg9NuRw95s8PEcz/6DZELQd/09C9QGq5RsmSRybqkwHGjh07OsJSsYYm3ijPpyHzoiacg35MLdDSIS/O1yM778jOTwYUkKNHWUzUWaOsylE00MyI0fcnOwIdjvtNdW/HZwNLGg+sR1kMepSNJXmIwxBZiG8tDTpEZzKg0GItNsosY8USkxDhD0Rinuiko2gfL/RbiD2LZAjU9zKQJj8RDR0vJBR1/Phx9+PHj9Z7REF4nTZkxzX4LCXHrV271qXkBAPGfP/atWvu/PnzHe4C97F48eIsRLZ9+3a3f/9+87dwP1JxaF7/3r17ba+5l4EcaVo0lj3SBq5kGTJSQmLWMjgYNei2GPT1MuMqGTDEFHzeQSP2wi/jGnkmPJ/nhccs44jvDAxpVcxnq0F6eT8h4ni/iIWpR5lPyA6ETkNXoSukvpJAD3AsXLiwpZs49+fPn5ke4j10TqYvegSfn0OnafC+Tv9ooA/JPkgQysqQNBzagXY55nO/oa1F7qvIPWkRL12WRpMWUvpVDYmxAPehxWSe8ZEXL20sadYIozfmNch4QJPAfeJgW3rNsnzphBKNJM2KKODo1rVOMRYik5ETy3ix4qWNI81qAAirizgMIc+yhTytx0JWZuNI03qsrgWlGtwjoS9XwgUhWGyhUaRZZQNNIEwCiXD16tXcAHUs79co0vSD8rrJCIW98pzvxpAWyyo3HYwqS0+H0BjStClcZJT5coMm6D2LOF8TolGJtK9fvyZpyiC5ePFi9nc/oJU4eiEP0jVoAnHa9wyJycITMP78+eMeP37sXrx44d6+fdt6f82aNdkx1pg9e3Zb5W+RSRE+n+VjksQWifvVaTKFhn5O8my63K8Qabdv33b379/PiAP//vuvW7BggZszZ072/+TJk91YgkafPn166zXB1rQHFvouAWHq9z3SEevSUerqCn2/dDCeta2jxYbr69evk4MHDyY7d+7MjhMnTiTPnz9Pfv/+nfQT2ggpO2dMF8cghuoM7Ygj5iWCqRlGFml0QC/ftGmTmzt3rmsaKDsgBSPh0/8yPeLLBihLkOKJc0jp8H8vUzcxIA1k6QJ/c78tWEyj5P3o4u9+jywNPdJi5rAH9x0KHcl4Hg570eQp3+vHXGyrmEeigzQsQsjavXt38ujRo44LQuDDhw+TW7duRS1HGgMxhNXHgflaNTOsHyKvHK5Ijo2jbFjJBQK9YwFd6RVMzfgRBmEfP37suBBm/p49e1qjEP2mwTViNRo0VJWH1deMXcNK08uUjVUu7s/zRaL+oLNxz1bpANco4npUgX4G2eFbpDFyQoQxojBCpEGSytmOH8qrH5Q9vuzD6ofQylkCUmh8DBAr+q8JCyVNtWQIidKQE9wNtLSQnS4jDSsxNHogzFuQBw4cyM61UKVsjfr3ooBkPSqqQHesUPWVtzi9/vQi1T+rJj7WiTz4Pt/l3LxUkr5P2VYZaZ4URpsE+st/dujQoaBBYokbrz/8TJNQYLSonrPS9kUaSkPeZyj1AWSj+d+VBoy1pIWVNed8P0Ll/ee5HdGRhrHhR5GGN0r4LGZBaj8oFDJitBTJzIZgFcmU0Y8ytWMZMzJOaXUSrUs5RxKnrxmbb5YXO9VGUhtpXldhEUogFr3IzIsvlpmdosVcGVGXFWp2oU9kLFL3dEkSz6NHEY1sjSRdIuDFWEhd8KxFqsRi1uM/nz9/zpxnwlESONdg6dKlbsaMGS4EHFHtjFIDHwKOo46l4TxSuxgDzi+rE2jg+BaFruOX4HXa0Nnf1lwAPufZeF8/r6zD97WK2qFnGjBxTw5qNGPxT+5T/r7/7RawFC3j4vTp09koCxkeHjqbHJqArmH5UrFKKksnxrK7FuRIs8STfBZv+luugXZ2pR/pP9Ois4z+TiMzUUkUjD0iEi1fzX8GmXyuxUBRcaUfykV0YZnlJGKQpOiGB76x5GeWkWWJc3mOrK6S7xdND+W5N6XyaRgtWJFe13GkaZnKOsYqGdOVVVbGupsyA/l7emTLHi7vwTdirNEt0qxnzAvBFcnQF16xh/TMpUuXHDowhlA9vQVraQhkudRdzOnK+04ZSP3DUhVSP61YsaLtd/ks7ZgtPcXqPqEafHkdqa84X6aCeL7YWlv6edGFHb+ZFICPlljHhg0bKuk0CSvVznWsotRu433alNdFrqG45ejoaPCaUkWERpLXjzFL2Rpllp7PJU2a/v7Ab8N05/9t27Z16KUqoFGsxnI9EosS2niSYg9SpU6B4JgTrvVW1flt1sT+0ADIJU2maXzcUTraGCRaL1Wp9rUMk16PMom8QhruxzvZIegJjFU7LLCePfS8uaQdPny4jTTL0dbee5mYokQsXTIWNY46kuMbnt8Kmec+LGWtOVIl9cT1rCB0V8WqkjAsRwta93TbwNYoGKsUSChN44lgBNCoHLHzquYKrU6qZ8lolCIN0Rh6cP0Q3U6I6IXILYOQI513hJaSKAorFpuHXJNfVlpRtmYBk1Su1obZr5dnKAO+L10Hrj3WZW+E3qh6IszE37F6EB+68mGpvKm4eb9bFrlzrok7fvr0Kfv727dvWRmdVTJHw0qiiCUSZ6wCK+7XL/AcsgNyL74DQQ730sv78Su7+t/A36MdY0sW5o40ahslXr58aZ5HtZB8GH64m9EmMZ7FpYw4T6QnrZfgenrhFxaSiSGXtPnz57e9TkNZLvTjeqhr734CNtrK41L40sUQckmj1lGKQ0rC37x544r8eNXRpnVE3ZZY7zXo8NomiO0ZUCj2uHz58rbXoZ6gc0uA+F6ZeKS/jhRDUq8MKrTho9fEkihMmhxtBI1DxKFY9XLpVcSkfoi8JGnToZO5sU5aiDQIW716ddt7ZLYtMQlhECdBGXZZMWldY5BHm5xgAroWj4C0hbYkSc/jBmggIrXJWlZM6pSETsEPGqZOndr2uuuR5rF169a2HoHPdurUKZM4CO1WTPqaDaAd+GFGKdIQkxAn9RuEWcTRyN2KSUgiSgF5aWzPTeA/lN5rZubMmR2bE4SIC4nJoltgAV/dVefZm72AtctUCJU2CMJ327hxY9t7EHbkyJFseq+EJSY16RPo3Dkq1kkr7+q0bNmyDuLQcZBEPYmHVdOBiJyIlrRDq41YPWfXOxUysi5fvtyaj+2BpcnsUV/oSoEMOk2CQGlr4ckhBwaetBhjCwH0ZHtJROPJkyc7UjcYLDjmrH7ADTEBXFfOYmB0k9oYBOjJ8b4aOYSe7QkKcYhFlq3QYLQhSidNmtS2RATwy8YOM3EQJsUjKiaWZ+vZToUQgzhkHXudb/PW5YMHD9yZM2faPsMwoc7RciYJXbGuBqJ1UIGKKLv915jsvgtJxCZDubdXr165mzdvtr1Hz5LONA8jrUwKPqsmVesKa49S3Q4WxmRPUEYdTjgiUcfUwLx589ySJUva3oMkP6IYddq6HMS4o55xBJBUeRjzfa4Zdeg56QZ43LhxoyPo7Lf1kNt7oO8wWAbNwaYjIv5lhyS7kRf96dvm5Jah8vfvX3flyhX35cuX6HfzFHOToS1H4BenCaHvO8pr8iDuwoUL7tevX+b5ZdbBair0xkFIlFDlW4ZknEClsp/TzXyAKVOmmHWFVSbDNw1l1+4f90U6IY/q4V27dpnE9bJ+v87QEydjqx/UamVVPRG+mwkNTYN+9tjkwzEx+atCm/X9WvWtDtAb68Wy9LXa1UmvCDDIpPkyOQ5ZwSzJ4jMrvFcr0rSjOUh+GcT4LSg5ugkW1Io0/SCDQBojh0hPlaJdah+tkVYrnTZowP8iq1F1TgMBBauufyB33x1v+NWFYmT5KmppgHC+NkAgbmRkpD3yn9QIseXymoTQFGQmIOKTxiZIWpvAatenVqRVXf2nTrAWMsPnKrMZHz6bJq5jvce6QK8J1cQNgKxlJapMPdZSR64/UivS9NztpkVEdKcrs5alhhWP9NeqlfWopzhZScI6QxseegZRGeg5a8C3Re1Mfl1ScP36ddcUaMuv24iOJtz7sbUjTS4qBvKmstYJoUauiuD3k5qhyr7QdUHMeCgLa1Ear9NquemdXgmum4fvJ6w1lqsuDhNrg1qSpleJK7K3TF0Q2jSd94uSZ60kK1e3qyVpQK6PVWXp2/FC3mp6jBhKKOiY2h3gtUV64TWM6wDETRPLDfSakXmH3w8g9Jlug8ZtTt4kVF0kLUYYmCCtD/DrQ5YhMGbA9L3ucdjh0y8kOHW5gU/VEEmJTcL4Pz/f7mgoAbYkAAAAAElFTkSuQmCC"]
}'
响应
{
"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
}
请求 (原始模式)
在某些情况下,你可能希望绕过模板系统并提供完整的提示。在这种情况下,你可以使用 raw
参数来禁用模板。请注意,原始模式不会返回上下文。
请求
shell
curl http://localhost:11434/api/generate -d '{
"model": "mistral",
"prompt": "[INST] why is the sky blue? [/INST]",
"raw": true,
"stream": false
}'
请求(可复现的输出)
为了获得可复现的输出,将 seed
设置为一个数字:
请求
shell
curl http://localhost:11434/api/generate -d '{
"model": "mistral",
"prompt": "Why is the sky blue?",
"options": {
"seed": 123
}
}'
响应
json
{
"model": "mistral",
"created_at": "2023-11-03T15:36:02.583064Z",
"response": " The sky appears blue because of a phenomenon called Rayleigh scattering.",
"done": true,
"total_duration": 8493852375,
"load_duration": 6589624375,
"prompt_eval_count": 14,
"prompt_eval_duration": 119039000,
"eval_count": 110,
"eval_duration": 1779061000
}
生成请求(带选项)
如果你希望在运行时而不是在 Modelfile 中设置模型的自定义选项,可以使用 options
参数。此示例设置了所有可用选项,但你可以单独设置其中任何一个,并省略你不希望覆盖的选项。
请求
shell
curl http://localhost:11434/api/generate -d '{
"model": "llama3.2",
"prompt": "Why is the sky blue?",
"stream": false,
"options": {
"num_keep": 5,
"seed": 42,
"num_predict": 100,
"top_k": 20,
"top_p": 0.9,
"min_p": 0.0,
"tfs_z": 0.5,
"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": "The sky is blue because it is the color of the sky.",
"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
如果提供了一个空的提示,模型将被加载到内存中。
请求
shell
curl http://localhost:11434/api/generate -d '{
"model": "llama3.2"
}'
响应
返回一个 JSON 对象:
json
{
"model": "llama3.2",
"created_at": "2023-12-18T19:52:07.071755Z",
"response": "",
"done": true
}
卸载模型
如果提供了一个空提示,并且 keep_alive
参数设置为 0
,则模型将从内存中卸载。
请求
shell
curl http://localhost:11434/api/generate -d '{
"model": "llama3.2",
"keep_alive": 0
}'
响应
返回一个 JSON 对象:
json
{
"model": "llama3.2",
"created_at": "2024-09-12T03:54:03.516566Z",
"response": "",
"done": true,
"done_reason": "unload"
}
生成chat completion
shell
POST /api/chat
生成与提供的模型进行聊天的下一条消息。这是一个流式端点,因此将有一系列响应。可以通过设置 "stream": false
来禁用流式传输。最终的响应对象将包含统计信息和请求的其他数据。
参数
model
: (必需)模型名称messages
: 聊天的消息,可以用于保持聊天记忆tools
: 如果支持,模型可以使用的工具。需要将stream
设置为false
message
对象具有以下字段:
role
: 消息的角色,可以是system
、user
、assistant
或tool
content
: 消息的内容images
(可选): 要包含在消息中的图像列表(适用于多模态模型,如llava
)tool_calls
(可选): 模型希望使用的工具列表
高级参数(可选):
format
: 返回响应的格式。目前唯一接受的值是json
options
: 文档中列出的其他模型参数,如 Modelfile 中的temperature
stream
: 如果设置为false
,响应将作为单个响应对象返回,而不是一系列对象keep_alive
: 控制请求后模型在内存中保持加载的时间(默认:5m
)
示例
Chat请求(流式)
请求
发送一条带有流式响应的聊天消息。
shell
curl http://localhost:11434/api/chat -d '{
"model": "llama3.2",
"messages": [
{
"role": "user",
"content": "why is the sky blue?"
}
]
}'
响应
返回一个 JSON 对象流:
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
}
Chat请求(不使用流式传输)
请求
shell
curl http://localhost:11434/api/chat -d '{
"model": "llama3.2",
"messages": [
{
"role": "user",
"content": "why is the sky blue?"
}
],
"stream": false
}'
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
}
Chat请求(包含历史记录)
发送一条带有对话历史的聊天消息。你可以使用相同的方法通过多轮提示或多步思考提示来开始对话。
请求
shell
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
返回一个 JSON 对象流:
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
}
Chat请求(含图片)
请求
发送一条包含图片的聊天消息。图片应以数组形式提供,每个图片使用 Base64 编码。
shell
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
}
Chat请求(可复现的输出)
请求
shell
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
}
Chat请求(带工具)
请求
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 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
,则模型将从内存中卸载。
请求
curl http://localhost:11434/api/chat -d '{
"model": "llama3.2",
"messages": [],
"keep_alive": 0
}'
响应
返回一个 JSON 对象:
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
shell
POST /api/create
从一个 Modelfile
创建模型。建议将 modelfile
设置为 Modelfile 的内容,而不仅仅是设置 path
。这是远程创建的必要条件。远程模型创建还必须使用 创建 Blob 显式地与服务器创建任何文件 blob、字段(如 FROM
和 ADAPTER
),并将响应中指示的路径值设置为路径。
参数
model
: 要创建的模型名称modelfile
(可选): Modelfile 的内容stream
(可选): 如果为false
,响应将作为单个响应对象返回,而不是对象流path
(可选): Modelfile 的路径quantize
(可选): 量化一个未量化的模型(例如 float16)
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 Modelfile
创建新模型。
请求
shell
curl http://localhost:11434/api/create -d '{
"model": "mario",
"modelfile": "FROM llama3\nSYSTEM You are mario from Super Mario Bros."
}'
响应
返回一个 JSON 对象流:
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
量化一个未量化的模型。
请求
shell
curl http://localhost:11434/api/create -d '{
"model": "llama3.1:quantized",
"modelfile": "FROM llama3.1:8b-instruct-fp16",
"quantize": "q4_K_M"
}'
响应
返回一个 JSON 对象流:
{"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"}
检查 Blob 是否存在
shell
HEAD /api/blobs/:digest
确保用于 FROM 或 ADAPTER 字段的文件 blob 在服务器上存在。这是检查你的 Ollama 服务器,而不是 ollama.com。
查询参数
digest
: blob 的 SHA256 摘要
示例
请求
shell
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。
创建一个 Blob
shell
POST /api/blobs/:digest
从服务器上的文件创建一个 blob。返回服务器文件路径。
查询参数
digest
: 文件的预期 SHA256 摘要
示例
请求
shell
curl -T model.bin -X POST http://localhost:11434/api/blobs/sha256:29fdb92e57cf0827ded04ae6461b5931d01fa595843f55d36f5b275a52087dd2
响应
如果 blob 创建成功,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
shell
GET /api/tags
列出本地可用的模型。
示例
请求
shell
curl http://localhost:11434/api/tags
响应
将返回一个 JSON 对象。
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
shell
POST /api/show
显示模型的信息,包括详细信息、模型文件、模板、参数、许可证、系统提示。
参数
model
: 要显示的模型名称verbose
: (可选)如果设置为true
,则返回详细响应字段的完整数据
示例
请求
shell
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
shell
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
请求
shell
curl http://localhost:11434/api/copy -d '{
"source": "llama3.2",
"destination": "llama3-backup"
}'
响应
如果成功,返回 200 OK;如果源模型不存在,则返回 404 Not Found。
删除模型
shell
DELETE /api/delete
删除模型及其数据。
参数
model
: 要删除的模型名称
示例
请求
shell
curl -X DELETE http://localhost:11434/api/delete -d '{
"model": "llama3:13b"
}'
响应
如果成功,返回 200 OK;如果要删除的模型不存在,则返回 404 Not Found。
拉取模型
shell
POST /api/pull
从 ollama 库下载一个模型。取消的下载会从断点处恢复,多次调用将共享相同的下载进度。
参数
model
: 要下载的模型名称insecure
: (可选)允许与库的不安全连接。仅在开发期间从你自己的库中拉取时使用此选项。stream
: (可选)如果为false
,响应将作为单个响应对象返回,而不是对象流
示例
请求
shell
curl http://localhost:11434/api/pull -d '{
"model": "llama3.2"
}'
响应
如果未指定 stream
,或设置为 true
,则返回一个 JSON 对象流:
第一个对象是清单:
json
{
"status": "pulling manifest"
}
然后是一系列的下载响应。直到任何下载完成之前,completed
键可能不会被包含。需要下载的文件数量取决于清单中指定的层数。
json
{
"status": "downloading digestname",
"digest": "digestname",
"total": 2142590208,
"completed": 241970
}
所有文件下载完成后,最终响应为:
json
{
"status": "verifying sha256 digest"
}
{
"status": "writing manifest"
}
{
"status": "removing any unused layers"
}
{
"status": "success"
}
如果 stream
设置为 false
,则响应是一个单一的 JSON 对象:
json
{
"status": "success"
}
推送模型
shell
POST /api/push
将模型上传到模型库。需要先注册 ollama.ai 并添加公钥。
参数
model
: 要推送的模型名称,格式为<namespace>/<model>:<tag>
insecure
:(可选)允许与库的不安全连接。仅在开发期间推送到库时使用此选项。stream
:(可选)如果false
,则响应将作为单个响应对象返回,而不是对象流
Examples
Request
shell
curl http://localhost:11434/api/push -d '{
"model": "mattw/pygmalion:latest"
}'
响应
如果未指定 stream
,或将其设置为 true
,则返回一个 JSON 对象流:
json
{ "status": "retrieving manifest" }
然后:
json
{
"status": "starting upload",
"digest": "sha256:bc07c81de745696fdf5afca05e065818a8149fb0c77266fb584d9b2cba3711ab",
"total": 1928429856
}
然后是一系列的上传响应:
json
{
"status": "starting upload",
"digest": "sha256:bc07c81de745696fdf5afca05e065818a8149fb0c77266fb584d9b2cba3711ab",
"total": 1928429856
}
最后,当上传完成时:
json
{"status":"pushing manifest"}
{"status":"success"}
如果 stream
设置为 false
,则响应是一个单一的 JSON 对象:
json
{ "status": "success" }
生成嵌入向量
shell
POST /api/embed
生成模型的嵌入向量
参数
model
: 用于生成嵌入向量的模型名称input
: 要生成嵌入向量的文本或文本列表
高级参数:
truncate
: 将每个输入的末尾截断以适应上下文长度。如果设置为false
且上下文长度超出,则返回错误。默认值为true
options
: 文档中列出的其他模型参数,如 Modelfile 中的temperature
keep_alive
: 控制模型在请求后保持加载在内存中的时间(默认值:5m
)
示例
请求
shell
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)
shell
curl http://localhost:11434/api/embed -d '{
"model": "all-minilm",
"input": ["Why is the sky blue?", "Why is the grass green?"]
}'
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
],[
-0.0098027075, 0.06042469, 0.025257962, -0.006364387, 0.07272725,
0.017194884, 0.09032035, -0.051705178, 0.09951512, 0.09072481
]]
}
列出正在运行的模型
shell
GET /api/ps
列出当前已加载到内存中的模型。
示例
请求
shell
curl http://localhost:11434/api/ps
响应
将返回一个 JSON 对象。
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
注意:此端点已被
/api/embed
取代
shell
POST /api/embeddings
生成模型的嵌入向量
参数
model
: 用于生成嵌入向量的模型名称prompt
: 生成嵌入向量的文本
高级参数:
options
: 文档中列出的其他模型参数,如 Modelfile 中的temperature
keep_alive
: 控制模型在请求后保持加载在内存中的时间(默认值:5m
)
示例
请求
shell
curl http://localhost:11434/api/embeddings -d '{
"model": "all-minilm",
"prompt": "Here is an article about llamas..."
}'
响应
json
{
"embedding": [
0.5670403838157654, 0.009260174818336964, 0.23178744316101074, -0.2916173040866852, -0.8924556970596313,
0.8785552978515625, -0.34576427936553955, 0.5742510557174683, -0.04222835972905159, -0.137906014919281
]
}