要在Postman中訪問Ollama API并調用DeepSeek模型，你需要遵循以下步驟。首先，確保你有一個有效的Ollama服務器實例運行中，并且DeepSeek模型已經被加載。

可以參考我的這篇博客 保姆級！使用Ollama本地部署DeepSeek-R1大模型 并java通過api 調用

具體的代碼實現參考我這個博客 保姆級！springboot訪問Ollama API并調用DeepSeek模型 Api

使用Postman配置請求

單論對話

請求類型為 POST。

在“輸入”框中輸入Ollama的API URL，通常是 http://localhost:11434/v1/completions（確保你的Ollama服務正在本地運行，并且使用的是正確的端口）。

在“頭”標簽頁中，添加以下內容：

Key: Content-Type

Value: application/json

編寫請求體:

在“Body”標簽頁中，選擇“raw”并設置編碼為“JSON (application/json)”。

輸入以下JSON格式的請求體：

{"model": "deepseek-r1:32b","prompt": "你好","max_tokens": 50,"temperature": 0.7,"top_p": 1,"stream": false
}

model: 指定要使用的模型名稱。

prompt: 輸入你想要模型生成文本的起始語句。

max_tokens: 生成文本的最大token數。

temperature: 控制輸出的隨機性。較低的值意味著更確定的輸出。值越低，生成的文本越保守和一致，越高則越具創意。如果不需要非常有創意的回答，可以將其設置為 0.7 或更低。

top_p: 核取樣參數，用于多樣性控制。控制采樣的累積概率，通常在 0 到 1 之間，越接近 1，模型越可能嘗試不同的答案。

stream: 如果設置為true，將流式傳輸結果。

具體如下圖

上面的 http://localhost:11434/v1/completions 是deepseek的api 地址 我們繼續訪問一下 Ollama Api http://192.168.110.118:7777/api/generate

一樣是可以的

多輪對話補全

我們訪問 http://localhost:7777/api/chat 試一下

請求體 傳入

{"model": "deepseek-r1:14b","messages": [{"role": "user", "content": "你好"},{"role": "assistant", "content": "你好！很高興見到你，有什么我可以幫忙的嗎？無論是學習、工作還是生活中的問題，都可以告訴我哦！??"},{"role": "user", "content": "請問1+1等于幾？"}],"max_tokens": 50,"temperature": 0.7,"top_p": 1,"stream": false
}

返回

{"model": "deepseek-r1:14b","created_at": "2025-02-25T01:06:00.1257844Z","message": {"role": "assistant","content": "<think>\n嗯，用戶之前用中文問候了我，我也回應了他。現在他問了一個數學題：“請問1+1等于幾？”這看起來很簡單，可能是在測試我的基本能力，或者他真的需要幫助計算。\n\n首先，我要確定他的身份。也許是個學生，在做作業時遇到了問題，或者是家長在輔導孩子，甚至可能是想確認我是否能正確回答基礎問題。不管怎樣，這個問題本身不難，但作為AI，我需要準確無誤地回答。\n\n接下來，考慮用戶的真實需求。表面上是數學題，但實際上他可能在測試我的反應速度和準確性，或者有其他隱藏的需求，比如驗證我的知識庫是否更新到最新的數學知識。\n\n另外，用戶的使用場景可能是學習環境，比如在學校或家里。如果是在課堂上，學生可能會用這個問題來確認老師的知識點是否正確，或者作為開始對話的簡單問題。\n\n可能還有深層需求，比如用戶想了解我能否處理更復雜的數學問題，所以先從簡單的題目入手。因此，正確的回答不僅是對當前問題的回答，也是建立信任的第一步。\n\n綜上所述，我應該直接給出準確的答案，并且保持友好的語氣，讓用戶感到被支持和幫助。\n</think>\n\n你好！1 + 1 等于 **2**。??"},"done_reason": "stop","done": true,"total_duration": 58231935600,"load_duration": 10134100,"prompt_eval_count": 40,"prompt_eval_duration": 459000000,"eval_count": 266,"eval_duration": 57761000000
}

文件上傳并提問

先看這里 Official Prompts

文檔內容翻譯如下：

官方提示
在官方的DeepSeek網絡/應用程序中，我們不使用系統提示，而是為文件上傳和網絡搜索設計了兩個特定的提示，以獲得更好的用戶體驗。此外，web/app中的溫度為0.6。
對于文件上傳，請按照模板創建提示，其中｛file_name｝、｛file_content｝和｛question｝是參數。
file_template =
“”“[file name]: {file_name}
[file content begin]
{file_content}
[file content end]
{question}”“”

我們先用postman請求試試
14b模型是不支持文件的 我們用32b model

body內容如下

{"model": "deepseek-r1:32b","messages":[{"role":"user","content":"[file name]: 1111.txt\n[file content begin]\n123456789\n[file content end]\n文檔中寫了什么？"}],"max_tokens": 50,"temperature": 0.7,"top_p": 1,"stream": true
}

返回內容

{"model": "deepseek-r1:32b","created_at": "2025-02-25T09:49:26.5392927Z","message": {"role": "assistant","content": "<think>"},"done": false
}
{"model": "deepseek-r1:32b","created_at": "2025-02-25T09:49:27.1561499Z","message": {"role": "assistant","content": "\n"},"done": false
}
{"model": "deepseek-r1:32b","created_at": "2025-02-25T09:49:27.753368Z","message": {"role": "assistant","content": "嗯"},"done": false
}
{"model": "deepseek-r1:32b","created_at": "2025-02-25T09:49:28.3850472Z","message": {"role": "assistant","content": "，"},"done": false
}
{"model": "deepseek-r1:32b","created_at": "2025-02-25T09:49:29.0560203Z","message": {"role": "assistant","content": "我"},"done": false
}
{"model": "deepseek-r1:32b","created_at": "2025-02-25T09:49:29.7279329Z","message": {"role": "assistant","content": "需要"},"done": false
}
{"model": "deepseek-r1:32b","created_at": "2025-02-25T09:49:30.3989966Z","message": {"role": "assistant","content": "回答"},"done": false
}
{"model": "deepseek-r1:32b","created_at": "2025-02-25T09:49:31.0669576Z","message": {"role": "assistant","content": "用戶"},"done": false
}
{"model": "deepseek-r1:32b","created_at": "2025-02-25T09:49:31.738556Z","message": {"role": "assistant","content": "關于"},"done": false
}
{"model": "deepseek-r1:32b","created_at": "2025-02-25T09:49:32.4179008Z","message": {"role": "assistant","content": "文件"},"done": false
}
{"model": "deepseek-r1:32b","created_at": "2025-02-25T09:49:33.0881279Z","message": {"role": "assistant","content": "內容"},"done": false
}
{"model": "deepseek-r1:32b","created_at": "2025-02-25T09:49:33.6911414Z","message": {"role": "assistant","content": "的問題"},"done": false
}
{"model": "deepseek-r1:32b","created_at": "2025-02-25T09:49:34.2884323Z","message": {"role": "assistant","content": "。"},"done": false
}
{"model": "deepseek-r1:32b","created_at": "2025-02-25T09:49:34.8879486Z","message": {"role": "assistant","content": "用戶提供"},"done": false
}
{"model": "deepseek-r1:32b","created_at": "2025-02-25T09:49:35.5587474Z","message": {"role": "assistant","content": "了一個"},"done": false
}
{"model": "deepseek-r1:32b","created_at": "2025-02-25T09:49:36.344929Z","message": {"role": "assistant","content": "文本"},"done": false
}
{"model": "deepseek-r1:32b","created_at": "2025-02-25T09:49:36.9433939Z","message": {"role": "assistant","content": "文件"},"done": false
}
{"model": "deepseek-r1:32b","created_at": "2025-02-25T09:49:37.5398887Z","message": {"role": "assistant","content": "的"},"done": false
}
{"model": "deepseek-r1:32b","created_at": "2025-02-25T09:49:38.1336335Z","message": {"role": "assistant","content": "名稱"},"done": false
}
{"model": "deepseek-r1:32b","created_at": "2025-02-25T09:49:38.8162284Z","message": {"role": "assistant","content": "和"},"done": false
}
{"model": "deepseek-r1:32b","created_at": "2025-02-25T09:49:39.602469Z","message": {"role": "assistant","content": "內容"},"done": false
}
{"model": "deepseek-r1:32b","created_at": "2025-02-25T09:49:40.1967921Z","message": {"role": "assistant","content": "。\n\n"},"done": false
}
{"model": "deepseek-r1:32b","created_at": "2025-02-25T09:49:40.7911033Z","message": {"role": "assistant","content": "首先"},"done": false
}
{"model": "deepseek-r1:32b","created_at": "2025-02-25T09:49:41.3901296Z","message": {"role": "assistant","content": "，"},"done": false
}
{"model": "deepseek-r1:32b","created_at": "2025-02-25T09:49:42.054903Z","message"