API
注意：Ollama 的 API 文件正在遷移至 https://docs.ollama.com/api
端點
慣例
模型名稱
模型名稱遵循 model:tag 格式，其中 model 部分可包含可選的命名空間，例如 example/model。常見的例子有 orca-mini:3b-q8_0 和 llama3:70b。標籤（tag）為可選項目，若未提供則預設為 latest。標籤用於識別特定版本的模型。
時長
所有時長均以奈秒為單位回傳。
串流回覆
部分端點會以 JSON 物件的形式串流回覆。針對這些端點，可透過傳入 {"stream": false} 來停用串流功能。
生成回應
POST /api/generate使用指定的模型為給定的提示詞產生回應。此為串流端點，因此會回傳一系列的回應物件。最終的回應物件會包含統計數據以及請求的其他相關資料。
參數
model：（必填）模型名稱prompt：用於產生回應的提示詞suffix：模型回覆後接續的文字images：（可選）一串經過 base64 編碼的圖片（適用於llava等多模態模型）think：（適用於思考型模型）模型是否要在回覆前進行思考？可傳入布林值，或思考層級（"low"、"medium"、"high"或"max"）。
進階參數（可選）：
format：回覆的格式。可為json或 JSON schemaoptions：額外的模型參數，可參考 Modelfile 文件中列出的項目，例如temperaturesystem：系統訊息（會覆蓋Modelfile中定義的內容）template：要使用的提示詞模板（會覆蓋Modelfile中定義的內容）stream：若設為false，回覆會以單一回應物件的形式回傳，而非一系列串流物件raw：若設為true，則不會對提示詞套用任何格式化。若你在 API 請求中指定了完整的模板化提示詞，可使用raw參數keep_alive：控制模型在請求完成後保留在記憶體中的時間（預設值：5m）context（已棄用）：先前請求/generate時回傳的 context 參數，可用於保留短暫的對話記憶
實驗性圖片生成參數（僅適用於圖片生成模型）：
WARNING
這些參數仍處於實驗階段，未來版本可能會有變動。
width：生成圖片的寬度（單位：像素）height：生成圖片的高度（單位：像素）steps：擴散步驟的次數
結構化輸出
只要在 format 參數中提供 JSON schema，即可支援結構化輸出。模型會產生符合該 schema 的回應，可參考下方的結構化輸出範例。
JSON 模式
將 format 參數設為 json 即可啟用 JSON 模式。此模式會將回覆結構化為有效的 JSON 物件，可參考下方的 JSON 模式範例。
IMPORTANT
務必在 prompt 中指示模型使用 JSON 格式回覆，否則模型可能會產生大量空白。
範例
生成請求（串流模式）
請求
shell
curl http://localhost:11434/api/generate -d '{
"model": "llama3.2",
"prompt": "Why is the sky blue?"
}'回覆
會回傳一串 JSON 物件的串流：
json
{
"model": "llama3.2",
"created_at": "2023-08-04T08:52:19.385406455-07:00",
"response": "The",
"done": false
}串流中的最終回覆還會包含生成過程的額外資料：
total_duration：產生回覆所花費的總時間load_duration：載入模型所花費的奈秒數prompt_eval_count：提示詞中的 token 數量prompt_eval_duration：評估提示詞所花費的奈秒數eval_count：回覆中的 token 數量eval_duration：產生回覆所花費的奈秒數context：本次回覆所使用的對話編碼，可於下一次請求中傳入以保留對話記憶response：若回覆為串流模式則為空字串，若非串流模式則包含完整回覆內容
若要計算回覆生成速度（每秒 token 數，即 token/s），請將 eval_count 除以 eval_duration 後乘以 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
}請求（無串流）
請求
關閉串流功能時，可於單一回覆中收到完整回應。
shell
curl http://localhost:11434/api/generate -d '{
"model": "llama3.2",
"prompt": "Why is the sky blue?",
"stream": false
}'回覆
若 stream 設為 false，回覆會是單一的 JSON 物件：
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
}請求（含後綴文字）
請求
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
}'回覆
json5
{
"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
}請求（結構化輸出）
請求
shell
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"
]
}
}'回覆
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
}請求（JSON 模式）
IMPORTANT
當 format 設為 json 時，輸出永遠會是格式正確的 JSON 物件。務必同時指示模型以 JSON 格式回覆。
請求
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
}'回覆
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 的值會是包含如下 JSON 內容的字串：
json
{
"morning": {
"color": "blue"
},
"noon": {
"color": "blue-gray"
},
"afternoon": {
"color": "warm gray"
},
"evening": {
"color": "orange"
}
}請求（含圖片）
若要將圖片傳送給 llava 或 bakllava 等多模態模型，請提供一串經過 base64 編碼的 images 參數：
請求
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"]
}'回覆
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
}請求（原始模式）
某些情況下，你可能會希望跳過模板系統並提供完整的提示詞。此時可使用 raw 參數來停用模板功能。請注意，原始模式不會回傳 context 參數。
請求
shell
curl http://localhost:11434/api/generate -d '{
"model": "mistral",
"prompt": "[INST] why is the sky blue? [/INST]",
"raw": true,
"stream": false
}'請求（可重複的輸出）
若要取得可重複的輸出結果，可將 seed 設定為一個數字：
請求
shell
curl http://localhost:11434/api/generate -d '{
"model": "mistral",
"prompt": "Why is the sky blue?",
"options": {
"seed": 123
}
}'回覆
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
}生成請求（含參數設定）
若要在執行階段為模型設定自訂參數，而非在 Modelfile 中設定，可使用 options 參數達成。此範例列出了所有可用的參數，你也可以單獨設定需要的參數，並省略不想覆蓋的項目。
請求
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,
"draft_num_predict": 4,
"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,
"penalize_newline": true,
"stop": ["\n", "user:"],
"numa": false,
"num_ctx": 1024,
"num_batch": 2,
"num_gpu": 1,
"main_gpu": 0,
"use_mmap": true,
"num_thread": 8
}
}'回覆
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
}載入模型
若提供空的提示詞，模型便會載入至記憶體中。
請求
shell
curl http://localhost:11434/api/generate -d '{
"model": "llama3.2"
}'回覆
會回傳單一的 JSON 物件：
json
{
"model": "llama3.2",
"created_at": "2023-12-18T19:52:07.071755Z",
"response": "",
"done": true
}卸載模型
若提供空的提示詞，且 keep_alive 參數設為 0，模型便會從記憶體中卸載。
請求
shell
curl http://localhost:11434/api/generate -d '{
"model": "llama3.2",
"keep_alive": 0
}'回覆
會回傳單一的 JSON 物件：
json
{
"model": "llama3.2",
"created_at": "2024-09-12T03:54:03.516566Z",
"response": "",
"done": true,
"done_reason": "unload"
}生成聊天完成結果
POST /api/chat使用指定的模型生成聊天中的下一則訊息。這是一個串流端點，因此會返回一系列回應。可透過設定 "stream": false 停用串流功能。最終的回應物件會包含統計數據以及請求的額外資料。
參數
model：（必填）模型名稱messages：聊天的訊息列表，可用於保留聊天記憶tools：JSON 格式的工具列表，供模型在支援的情況下使用think：（適用於思考型模型）模型是否需要在回覆前進行思考？可設定為布林值，或思考層級（"low"、"medium"、"high"、"max"）
message 物件包含以下欄位：
role：訊息的角色，可為system、user、assistant或toolcontent：訊息的內容thinking：（適用於思考型模型）模型的思考過程images（可選）：要包含在訊息中的圖片列表（適用於llava等多模態模型）tool_calls（可選）：模型想要使用的 JSON 格式工具列表tool_name（可選）：新增已執行工具的名稱，以便告知模型執行結果
進階參數（可選）：
format：回覆的格式，可為json或 JSON schemaoptions：額外的模型參數，詳見 Modelfile 的說明，例如temperaturestream：若設為false，回覆會以單一回應物件返回，而非物件串流keep_alive：控制請求完成後模型保留在記憶體中的時間（預設值：5m）
工具呼叫
工具呼叫功能可透過在 tools 參數中提供工具列表來啟用。模型會生成包含工具呼叫列表的回應。請參考下方的〈串流模式搭配工具呼叫的聊天請求〉範例。模型也可在回覆中解釋工具呼叫的結果。請參考下方的〈搭配歷史記錄與工具呼叫的聊天請求〉範例。查看支援工具呼叫功能的模型
結構化輸出
結構化輸出可透過在 format 參數中提供 JSON schema 來啟用。模型會生成符合該 schema 的回應。請參考下方的〈結構化輸出的聊天請求〉範例。
範例
聊天請求（串流模式）
請求
發送帶有串流回覆的聊天訊息。
shell
curl http://localhost:11434/api/chat -d '{
"model": "llama3. 2",
"messages": [
{
"role": "user",
"content": "why is the sky blue? "
}
]
}'回覆
返回一系列 JSON 物件：
json
{
"model": "llama3. 2",
"created_at": "2023-08-04T08:52:19. 385406455-07:00",
"message": {
"role": "assistant",
"content": "The",
"images": null
},
"done": false
}最終回覆：
json
{
"model": "llama3. 2",
"created_at": "2023-08-04T19:22:45. 499127Z",
"message": {
"role": "assistant",
"content": ""
},
"done": true,
"total_duration": 4883583458,
"load_duration": 1334875,
"prompt_eval_count": 26,
"prompt_eval_duration": 342546000,
"eval_count": 282,
"eval_duration": 4535599000
}聊天請求（串流模式搭配工具呼叫）
請求
shell
curl http://localhost:11434/api/chat -d '{
"model": "llama3. 2",
"messages": [
{
"role": "user",
"content": "what is the weather in tokyo? "
}
],
"tools": [
{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get the weather in a given city",
"parameters": {
"type": "object",
"properties": {
"city": {
"type": "string",
"description": "The city to get the weather for"
}
},
"required": ["city"]
}
}
}
],
"stream": true
}'回覆
返回一系列 JSON 物件：
json
{
"model": "llama3. 2",
"created_at": "2025-07-07T20:22:19. 184789Z",
"message": {
"role": "assistant",
"content": "",
"tool_calls": [
{
"function": {
"name": "get_weather",
"arguments": {
"city": "Tokyo"
}
}
}
]
},
"done": false
}最終回覆：
json
{
"model": "llama3. 2",
"created_at": "2025-07-07T20:22:19. 19314Z",
"message": {
"role": "assistant",
"content": ""
},
"done_reason": "stop",
"done": true,
"total_duration": 182242375,
"load_duration": 41295167,
"prompt_eval_count": 169,
"prompt_eval_duration": 24573166,
"eval_count": 15,
"eval_duration": 115959084
}聊天請求（無串流模式）
請求
shell
curl http://localhost:11434/api/chat -d '{
"model": "llama3. 2",
"messages": [
{
"role": "user",
"content": "why is the sky blue? "
}
],
"stream": false
}'回覆
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
}聊天請求（無串流模式，搭配工具呼叫）
請求
shell
curl http://localhost:11434/api/chat -d '{
"model": "llama3. 2",
"messages": [
{
"role": "user",
"content": "what is the weather in tokyo? "
}
],
"tools": [
{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get the weather in a given city",
"parameters": {
"type": "object",
"properties": {
"city": {
"type": "string",
"description": "The city to get the weather for"
}
},
"required": ["city"]
}
}
}
],
"stream": false
}'回覆
json
{
"model": "llama3. 2",
"created_at": "2025-07-07T20:32:53. 844124Z",
"message": {
"role": "assistant",
"content": "",
"tool_calls": [
{
"function": {
"name": "get_weather",
"arguments": {
"city": "Tokyo"
}
}
}
]
},
"done_reason": "stop",
"done": true,
"total_duration": 3244883583,
"load_duration": 2969184542,
"prompt_eval_count": 169,
"prompt_eval_duration": 141656333,
"eval_count": 18,
"eval_duration": 133293625
}聊天請求（結構化輸出）
請求
shell
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
}
}'回覆
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
}聊天請求（搭配歷史記錄）
發送帶有對話歷史記錄的聊天訊息。您可以使用相同的方式，透過多樣本提示（multi-shot prompting）或思維鏈提示（chain-of-thought prompting）來開啟對話。
請求
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? "
}
]
}'回覆
返回一系列 JSON 物件：
json
{
"model": "llama3. 2",
"created_at": "2023-08-04T08:52:19. 385406455-07:00",
"message": {
"role": "assistant",
"content": "The"
},
"done": false
}最終回覆：
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
}聊天請求（搭配歷史記錄與工具呼叫）
請求
shell
curl http://localhost:11434/api/chat -d '{
"model": "llama3. 2",
"messages": [
{
"role": "user",
"content": "what is the weather in Toronto? "
},
// the message from the model appended to history
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"function": {
"name": "get_weather",
"arguments": {
"city": "Toronto"
}
}
}
]
},
// the tool call result appended to history
{
"role": "tool",
"content": "11 degrees celsius",
"tool_name": "get_weather"
}
],
"stream": false,
"tools": [
{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get the weather in a given city",
"parameters": {
"type": "object",
"properties": {
"city": {
"type": "string",
"description": "The city to get the weather for"
}
},
"required": ["city"]
}
}
}
]
}'回覆
json
{
"model": "llama3. 2",
"created_at": "2025-07-07T20:43:37. 688511Z",
"message": {
"role": "assistant",
"content": "The current temperature in Toronto is 11°C. "
},
"done_reason": "stop",
"done": true,
"total_duration": 890771750,
"load_duration": 707634750,
"prompt_eval_count": 94,
"prompt_eval_duration": 91703208,
"eval_count": 11,
"eval_duration": 90282125
}聊天請求（搭配圖片）
請求
發送帶有圖片的聊天訊息。圖片需以陣列形式提供，單張圖片需以 Base64 編碼。
shell
curl http://localhost:11434/api/chat -d '{
"model": "llava",
"messages": [
{
"role": "user",
"content": "what is in this image?", "images": ["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"] } ] }'
##### 回應
```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
}聊天請求（可重複輸出）
請求
shell
curl http://localhost:11434/api/chat -d '{
"model": "llama3. 2",
"messages": [
{
"role": "user",
"content": "Hello! "
}
],
"options": {
"seed": 101,
"temperature": 0
}
}'回應
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
}聊天請求（含工具）
請求
shell
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"]
}
}
}
]
}'回應
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
}載入模型
如果 messages 陣列為空，模型將會載入記憶體。
請求
shell
curl http://localhost:11434/api/chat -d '{
"model": "llama3. 2",
"messages": []
}'回應
會回傳單一 JSON 物件：
json
{
"model": "llama3. 2",
"created_at": "2024-09-12T21:17:29. 110811Z",
"message": {
"role": "assistant",
"content": ""
},
"done_reason": "load",
"done": true
}卸載模型
如果 messages 陣列為空，且 keep_alive 參數設定為 0，模型將會從記憶體中卸載。
請求
shell
curl http://localhost:11434/api/chat -d '{
"model": "llama3. 2",
"messages": [],
"keep_alive": 0
}'回應
會回傳單一 JSON 物件：
json
{
"model": "llama3. 2",
"created_at": "2024-09-12T21:33:17. 547535Z",
"message": {
"role": "assistant",
"content": ""
},
"done_reason": "unload",
"done": true
}建立模型
POST /api/create可從以下來源建立模型：
- 另一個模型；
- safetensors 目錄；或
- GGUF 檔案。
若您要從 safetensors 目錄或 GGUF 檔案建立模型，必須先為每個檔案建立 blob，接著在 files 欄位中使用每個 blob 對應的檔案名稱與 SHA256 摘要。
參數
model：要建立的模型名稱from：（可選）要作為新模型基礎的現有模型名稱files：（可選）用於建立模型的 blob 的「檔案名稱 → SHA256 摘要」字典adapters：（可選）LORA 適配器的 blob 的「檔案名稱 → SHA256 摘要」字典template：（可選）模型的提示詞模板renderer：（可選）模型的渲染器名稱parser：（可選）模型的剖析器名稱license：（可選）包含模型授權的字符串或字符串列表system：（可選）模型的系統提示詞字符串parameters：（可選）模型的參數字典（參數列表請見 Modelfile）messages：（可選）用於建立對話的訊息物件列表stream：（可選）若為false，回應會以單一回應物件返回，而非物件串流quantize（可選）：對非量化（例如 float16）的模型進行量化
量化類型
| 類型 | 建議使用 |
|---|---|
| q4_K_M | * |
| q4_K_S | |
| q8_0 | * |
範例
建立新模型
從現有模型建立新模型。
請求
shell
curl http://localhost:11434/api/create -d '{
"model": "mario",
"from": "llama3.2",
"system": "You are Mario from Super Mario Bros."
}'回應
會返回 JSON 物件的串流：
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
對非量化模型進行量化。
請求
shell
curl http://localhost:11434/api/create -d '{
"model": "llama3.2:quantized",
"from": "llama3.2:3b-instruct-fp16",
"quantize": "q4_K_M"
}'回應
會返回 JSON 物件的串流：
json
{"status":"quantizing F16 model to Q4_K_M","digest":"0","total":6433687776,"completed":12302}
{"status":"quantizing F16 model to Q4_K_M","digest":"0","total":6433687776,"completed":6433687552}
{"status":"verifying conversion"}
{"status":"creating new layer sha256:fb7f4f211b89c6c4928ff4ddb73db9f9c0cfca3e000c3e40d6cf27ddc6ca72eb"}
{"status":"using existing layer sha256:966de95ca8a62200913e3f8bfbf84c8494536f1b94b49166851e76644e966396"}
{"status":"using existing layer sha256:fcc5a6bec9daf9b561a68827b67ab6088e1dba9d1fa2a50d7bbcc8384e0a265d"}
{"status":"using existing layer sha256:a70ff7e570d97baaf4e62ac6e6ad9975e04caa6d900d3742d37698494479e0cd"}
{"status":"using existing layer sha256:56bb8bd477a519ffa694fc449c2413c6f0e1d3b1c88fa7e3c9d88d3ae49d4dcb"}
{"status":"writing manifest"}
{"status":"success"}從 GGUF 建立模型
從 GGUF 檔案建立模型。files 參數需填寫欲使用的 GGUF 檔案的檔案名稱與 SHA256 摘要。在呼叫此 API 前，請使用 /api/blobs/:digest 將 GGUF 檔案推送至伺服器。
請求
shell
curl http://localhost:11434/api/create -d '{
"model": "my-gguf-model",
"files": {
"test.gguf": "sha256:432f310a77f4650a88d0fd59ecdd7cebed8d684bafea53cbff0473542964f0c3"
}
}'回應
會返回 JSON 物件的串流：
json
{"status":"parsing GGUF"}
{"status":"using existing layer sha256:432f310a77f4650a88d0fd59ecdd7cebed8d684bafea53cbff0473542964f0c3"}
{"status":"writing manifest"}
{"status":"success"}從 Safetensors 目錄建立模型
files 參數需包含 safetensors 模型的檔案字典，其中包括每個檔案的檔案名稱與 SHA256 摘要。在呼叫此 API 前，請先使用 /api/blobs/:digest 將每個檔案推送至伺服器。檔案會保留在快取中，直到 Ollama 伺服器重新啟動為止。
請求
shell
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"
}
}'回應
會返回 JSON 物件的串流：
shell
{"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"}檢查 Blob 是否存在
shell
HEAD /api/blobs/:digest確保用於建立模型的檔案 Blob（Binary Large Object，二進位大型物件）存在於伺服器上。此檢查會針對您本地的 Ollama 伺服器，而非 ollama.com。
查詢參數
digest：Blob 的 SHA256 摘要
範例
請求
shell
curl -I http://localhost:11434/api/blobs/sha256:29fdb92e57cf0827ded04ae6461b5931d01fa595843f55d36f5b275a52087dd2回應
若 Blob 存在則回傳 200 OK，若不存在則回傳 404 Not Found。
推送 Blob
POST /api/blobs/:digest將檔案推送至 Ollama 伺服器以建立「Blob」（Binary Large Object，二進位大型物件）。
查詢參數
digest：檔案的預期 SHA256 摘要
範例
請求
shell
curl -T model.gguf -X POST http://localhost:11434/api/blobs/sha256:29fdb92e57cf0827ded04ae6461b5931d01fa595843f55d36f5b275a52087dd2回應
若 Blob 成功建立則回傳 201 Created，若使用的摘要與預期不符則回傳 400 Bad Request。
列出本地模型
GET /api/tags列出本地可用的模型。
範例
請求
shell
curl http://localhost:11434/api/tags回應
將回傳單一 JSON 物件。
json
{
"models": [
{
"name": "deepseek-r1:latest",
"model": "deepseek-r1:latest",
"modified_at": "2025-05-10T08:06:48.639712648-07:00",
"size": 4683075271,
"digest": "0a8c266910232fd3291e71e5ba1e058cc5af9d411192cf88b6d30e92b6e73163",
"details": {
"parent_model": "",
"format": "gguf",
"family": "qwen2",
"families": ["qwen2"],
"parameter_size": "7.6B",
"quantization_level": "Q4_K_M"
}
},
{
"name": "llama3.2:latest",
"model": "llama3.2:latest",
"modified_at": "2025-05-04T17:37:44.706015396-07:00",
"size": 2019393189,
"digest": "a80c4f17acd55265feec403c7aef86be0c25983ab279d83f3bcd3abbcb5b8b72",
"details": {
"parent_model": "",
"format": "gguf",
"family": "llama",
"families": ["llama"],
"parameter_size": "3.2B",
"quantization_level": "Q4_K_M"
}
}
]
}顯示模型資訊
POST /api/show顯示模型的相關資訊，包含詳細資料、Modelfile、模板、參數、授權條款、系統提示詞。
參數
model：要顯示的模型名稱verbose：（可選）若設為true，則回傳詳細回應欄位的完整資料
範例
請求
shell
curl http://localhost:11434/api/show -d '{
"model": "llava"
}'回應
json5
{
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`
},
capabilities: ["completion", "vision"],
}複製模型
POST /api/copy複製模型。從現有模型建立一個名稱不同的新模型。
範例
請求
shell
curl http://localhost:11434/api/copy -d '{
"source": "llama3.2",
"destination": "llama3-backup"
}'回應
若成功則回傳 200 OK，若來源模型不存在則回傳 404 Not Found。
刪除模型
DELETE /api/delete刪除模型及其相關資料。
參數
model：要刪除的模型名稱
範例
請求
shell
curl -X DELETE http://localhost:11434/api/delete -d '{
"model": "llama3:13b"
}'回應
若成功則回傳 200 OK，若要刪除的模型不存在則回傳 404 Not Found。
拉取模型
POST /api/pull從 Ollama 函式庫下載模型。已取消的拉取作業會從中斷處繼續執行，多次呼叫會共享相同的下載進度。
參數
model：要拉取的模型名稱insecure：（可選）允許與函式庫建立不安全連線。僅在開發期間從自有函式庫拉取模型時使用此選項stream：（可選）若設為false，回應會以單一回應物件的形式回傳，而非物件串流
範例
請求
shell
curl http://localhost:11434/api/pull -d '{
"model": "llama3.2"
}'回應
若未指定 stream 或設為 true，則會回傳 JSON 物件串流：
第一個物件為清單（manifest）：
json
{
"status": "pulling manifest"
}接著會有一系列下載回應。在下載完成前，可能不會包含 completed 鍵。要下載的檔案數量取決於清單中指定的圖層數量。
json
{
"status": "pulling digestname",
"digest": "digestname",
"total": 2142590208,
"completed": 241970
}所有檔案下載完成後，最終回應如下：
json
{
"status": "verifying sha256 digest"
}
{
"status": "writing manifest"
}
{
"status": "removing any unused layers"
}
{
"status": "success"
}若 stream 設為 false，則回應為單一 JSON 物件：
json
{
"status": "success"
}推送模型
POST /api/push將模型上傳至模型函式庫。需要先註冊 ollama.ai 帳號並新增公開金鑰。
參數
model：要推送的模型名稱，格式為<namespace>/<model>:<tag>insecure：（可選）允許與函式庫建立不安全連線。僅在開發期間推送至自有函式庫時使用此選項stream：（可選）若設為false，回應會以單一回應物件的形式回傳，而非物件串流
範例
請求
shell
curl http://localhost:11434/api/push -d '{
"model": "mattw/pygmalion:latest"
}'回應
若未指定 stream 或設為 true，則會回傳 JSON 物件串流：
json
{ "status": "retrieving manifest" }接著：
json
{
"status": "starting upload",
"digest": "sha256:bc07c81de745696fdf5afca05e065818a8149fb0c77266fb584d9b2cba3711ab",
"total": 1928429856
}隨後會有一系列上傳回應：
json
{
"status": "starting upload",
"digest": "sha256:bc07c81de745696fdf5afca05e065818a8149fb0c77266fb584d9b2cba3711ab",
"total": 1928429856
}最後，當上傳完成時：
json
{"status":"pushing manifest"}
{"status":"success"}若 stream 設為 false，則回應為單一 JSON 物件：
json
{ "status": "success" }產生嵌入向量
POST /api/embed從模型產生嵌入向量
參數
model：用於產生嵌入向量的模型名稱input：要產生嵌入的文字或文字清單
進階參數：
truncate：截斷每個輸入的末尾以符合上下文長度。若上下文長度超限且設為false則回傳錯誤。預設為trueoptions：Modelfile 文件中列出的額外模型參數，例如temperaturekeep_alive：控制請求完成後模型保留在記憶體中的時間（預設：5m）dimensions：嵌入向量的維度數
範例
請求
shell
curl http://localhost:11434/api/embed -d '{
"model": "all-minilm",
"input": "Why is the sky blue?"
}'回應
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
}請求（多筆輸入）
shell
curl http://localhost:11434/api/embed -d '{
"model": "all-minilm",
"input": ["Why is the sky blue?", "Why is the grass green?"]
}'回應
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
]
]
}列出執行中的模型
GET /api/ps列出目前已載入記憶體的模型。
範例
請求
shell
curl http://localhost:11434/api/ps回應
將回傳單一 JSON 物件。
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
}
]
}產生嵌入向量
注意：此端點已被
/api/embed取代
POST /api/embeddings從模型產生嵌入向量
參數
model：用於產生嵌入向量的模型名稱prompt：要產生嵌入的文字
進階參數：
options：Modelfile 文件中列出的額外模型參數，例如temperaturekeep_alive：控制請求完成後模型保留在記憶體中的時間（預設：5m）
範例
請求
shell
curl http://localhost:11434/api/embeddings -d '{
"model": "all-minilm",
"prompt": "Here is an article about llamas..."
}'回應
json
{
"embedding": [
0.5670403838157654, 0.009260174818336964, 0.23178744316101074,
-0.2916173040866852, -0.8924556970596313, 0.8785552978515625,
-0.34576427936553955, 0.5742510557174683, -0.04222835972905159,
-0.137906014919281
]
}版本
GET /api/version取得 Ollama 版本
範例
請求
shell
curl http://localhost:11434/api/version回應
json
{
"version": "0.5.1"
}實驗性功能
圖像生成（實驗性）
[!警告] 圖像生成功能尚處於實驗階段，未來版本可能會有變更。
使用圖像生成模型時，現在可透過標準的 /api/generate 端點來進行圖像生成。API 會自動偵測是否正在使用圖像生成模型。
完整的 API 說明請參閱 產生完成回應 小節，實驗性的圖像生成參數（width、height、steps）也記載於該處。
範例
請求
shell
curl http://localhost:11434/api/generate -d '{
"model": "x/z-image-turbo",
"prompt": "a sunset over mountains",
"width": 1024,
"height": 768
}'回應（串流）
生成過程中的進度更新：
json
{
"model": "x/z-image-turbo",
"created_at": "2024-01-15T10:30:00.000000Z",
"completed": 5,
"total": 20,
"done": false
}最終回應
json
{
"model": "x/z-image-turbo",
"created_at": "2024-01-15T10:30:15.000000Z",
"image": "iVBORw0KGgoAAAANSUhEUg...",
"done": true,
"done_reason": "stop",
"total_duration": 15000000000,
"load_duration": 2000000000
}