Ollama安装与使用_ollama 集成显卡-CSDN博客

1、安装Ollama

# 纯CPU计算（集成显卡就用这种方式）

docker run -d -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama

# Nvidia GPU # 英伟达显卡安装 NVIDIA Container Toolkit https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html#installation docker run -d --runtime=nvidia --gpus=all -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama

# AMD GPU 参考 docker run -d --device /dev/kfd --device /dev/dri -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama:rocm

2、运行大模型

模型查找：https://ollama.com/search

#ollama 官方仓库

ollama pull llama3.2

#直接使用huggingface上的模型

ollama pull hf.co/Qwen/Qwen2-7B-Instruct-GGUF:Q4_K_M

# 使用魔搭社区的模型

ollama pull modelscope.cn/Qwen/Qwen2.5-3B-Instruct-GGUF

ollama run deepseek-r1

# 1.5b模型 ollama run deepseek-r1:1.5b

# 14b模型 ollama run deepseek-r1:14b

3、代码调用大模型

Ollama Api

curl http://localhost:11434/api/tags

curl http://localhost:11434/api/generate -d '{ "model": "llama3.2", "prompt":"Why is the sky blue?" }'

curl http://localhost:11434/api/chat -d '{ "model": "llama3.2", "messages": [ { "role": "user", "content": "why is the sky blue?" } ] }'

curl http://localhost:11434/api/embed -d '{ "model": "mxbai-embed-large", "input": "Why is the sky blue?" }'

curl http://localhost:11434/api/embeddings -d '{ "model": "mxbai-embed-large", "prompt": "Here is an article about llamas..." }'

client

demo：ollama

# pip install ollama

import ollama

response = ollama.chat(model='llama3.1', messages=[ { 'role': 'user', 'content': 'Why is the sky blue?', }, ])

print(response['message']['content'])

demo：langchain-ollama

#pip install -qU langchain-ollama

from langchain_ollama import ChatOllama

from langchain_core.messages import AIMessage

llm = ChatOllama( model="llama3.1", temperature=0, # other params... )

messages = [ ( "system", "You are a helpful assistant that translates English to French. Translate the user sentence.", ), ("human", "I love programming."), ]

ai_msg = llm.invoke(messages)

ai_msg

demo：OpenAi

import openai

openai.base_url = "http://localhost:11434/v1"

openai.api_key = 'ollama'

response = openai.chat.completions.create( model="llama3.1", messages=messages, tools=tools, )

demo：weather

def weather(city: str):
    """
    查询天气
    """
    if city == '北京':
        return '北京晴朗'
    elif city == '上海':
        return '上海多云'
    else:
        return f'不知道 {city}.'

def test_agent():
    from langgraph.prebuilt import create_react_agent

    llm = ChatOllama(model='qwen2.5', temperature=0)
    tools = [weather]
    langgraph_agent_executor = create_react_agent(llm, tools)

    query = '北京天气如何'

    messages = langgraph_agent_executor.invoke({"messages": [("human", query)]})
    print(json.dumps([message.model_dump() for message in messages['messages']], indent=2, ensure_ascii=False))

# 输出结果
[
  {
    "content": "北京天气如何",
    "additional_kwargs": {},
    "response_metadata": {},
    "type": "human",
    "name": null,
    "id": "0d312e83-dd8a-4638-af7d-c8e47585e380",
    "example": false
  },
  {
    "content": "",
    "additional_kwargs": {},
    "response_metadata": {
      "model": "qwen2.5",
      "created_at": "2024-10-30T10:35:51.32219Z",
      "message": {
        "role": "assistant",
        "content": "",
        "tool_calls": [
          {
            "function": {
              "name": "weather",
              "arguments": {
                "city": "北京"
              }
            }
          }
        ]
      },
      "done_reason": "stop",
      "done": true,
      "total_duration": 660820709,
      "load_duration": 33652000,
      "prompt_eval_count": 151,
      "prompt_eval_duration": 216216000,
      "eval_count": 19,
      "eval_duration": 408378000
    },
    "type": "ai",
    "name": null,
    "id": "run-44766d01-3e92-4688-9e3c-3a7557338bce-0",
    "example": false,
    "tool_calls": [
      {
        "name": "weather",
        "args": {
          "city": "北京"
        },
        "id": "99331cef-b8f5-481a-9e10-1ea5e5c0b4f2",
        "type": "tool_call"
      }
    ],
    "invalid_tool_calls": [],
    "usage_metadata": {
      "input_tokens": 151,
      "output_tokens": 19,
      "total_tokens": 170
    }
  },
  {
    "content": "北京晴朗",
    "additional_kwargs": {},
    "response_metadata": {},
    "type": "tool",
    "name": "weather",
    "id": "b74bfc72-8dd1-4541-a653-da6e8e299725",
    "tool_call_id": "99331cef-b8f5-481a-9e10-1ea5e5c0b4f2",
    "artifact": null,
    "status": "success"
  },
  {
    "content": "北京现在是晴朗的天气。请注意防晒哦！",
    "additional_kwargs": {},
    "response_metadata": {
      "model": "qwen2.5",
      "created_at": "2024-10-30T10:35:51.727177Z",
      "message": {
        "role": "assistant",
        "content": "北京现在是晴朗的天气。请注意防晒哦！"
      },
      "done_reason": "stop",
      "done": true,
      "total_duration": 399748125,
      "load_duration": 11164250,
      "prompt_eval_count": 190,
      "prompt_eval_duration": 112236000,
      "eval_count": 13,
      "eval_duration": 270630000
    },
    "type": "ai",
    "name": null,
    "id": "run-bafa67a6-9a7d-4fa5-b240-861e9b39e99b-0",
    "example": false,
    "tool_calls": [],
    "invalid_tool_calls": [],
    "usage_metadata": {
      "input_tokens": 190,
      "output_tokens": 13,
      "total_tokens": 203
    }
  }
]