Ollama大模型本地部署教程

前提条件

一台Linux服务器
安装完docker
安装完Anaconda

安装Ollama

启动 ollama

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

加载一个模型，这里以llama2为例

1	docker exec -itd ollama ollama run llama2

安装Open WebUI

1	docker run -d -p 8080:8080 --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main

安装完成后访问服务器8080端口，点击注册登入即可使用。
登陆界面
注册界面

提供API服务

ollama本身提供了API服务，但是流式处理有点问题，python版本的没问题，这里以一个api_demo为例对齐chatgpt的api。

安装依赖

1	pip install ollama sse_starlette fastapi

创建api_demo.py文件

import asyncio
import json
import os
from typing import Any, Dict, Sequence

import ollama
from sse_starlette.sse import EventSourceResponse
from fastapi import FastAPI, HTTPException, status
from fastapi.middleware.cors import CORSMiddleware
import uvicorn
import time
from enum import Enum, unique
from typing import List, Optional

from pydantic import BaseModel, Field
from typing_extensions import Literal


@unique
class Role(str, Enum):
    USER = "user"
    ASSISTANT = "assistant"
    SYSTEM = "system"
    FUNCTION = "function"
    TOOL = "tool"
    OBSERVATION = "observation"


@unique
class Finish(str, Enum):
    STOP = "stop"
    LENGTH = "length"
    TOOL = "tool_calls"


class ModelCard(BaseModel):
    id: str
    object: Literal["model"] = "model"
    created: int = Field(default_factory=lambda: int(time.time()))
    owned_by: Literal["owner"] = "owner"


class ModelList(BaseModel):
    object: Literal["list"] = "list"
    data: List[ModelCard] = []


class Function(BaseModel):
    name: str
    arguments: str


class FunctionCall(BaseModel):
    id: Literal["call_default"] = "call_default"
    type: Literal["function"] = "function"
    function: Function


class ChatMessage(BaseModel):
    role: Role
    content: str


class ChatCompletionMessage(BaseModel):
    role: Optional[Role] = None
    content: Optional[str] = None
    tool_calls: Optional[List[FunctionCall]] = None


class ChatCompletionRequest(BaseModel):
    model: str
    messages: List[ChatMessage]
    tools: Optional[list] = []
    do_sample: bool = True
    temperature: Optional[float] = None
    top_p: Optional[float] = None
    n: int = 1
    max_tokens: Optional[int] = None
    stream: bool = False


class ChatCompletionResponseChoice(BaseModel):
    index: int
    message: ChatCompletionMessage
    finish_reason: Finish


class ChatCompletionResponseStreamChoice(BaseModel):
    index: int
    delta: ChatCompletionMessage
    finish_reason: Optional[Finish] = None


class ChatCompletionResponseUsage(BaseModel):
    prompt_tokens: int
    completion_tokens: int
    total_tokens: int


class ChatCompletionResponse(BaseModel):
    id: Literal["chatcmpl-default"] = "chatcmpl-default"
    object: Literal["chat.completion"] = "chat.completion"
    created: int = Field(default_factory=lambda: int(time.time()))
    model: str
    choices: List[ChatCompletionResponseChoice]
    usage: ChatCompletionResponseUsage


class ChatCompletionStreamResponse(BaseModel):
    id: Literal["chatcmpl-default"] = "chatcmpl-default"
    object: Literal["chat.completion.chunk"] = "chat.completion.chunk"
    created: int = Field(default_factory=lambda: int(time.time()))
    model: str
    choices: List[ChatCompletionResponseStreamChoice]


class ScoreEvaluationRequest(BaseModel):
    model: str
    messages: List[str]
    max_length: Optional[int] = None


class ScoreEvaluationResponse(BaseModel):
    id: Literal["scoreeval-default"] = "scoreeval-default"
    object: Literal["score.evaluation"] = "score.evaluation"
    model: str
    scores: List[float]


def dictify(data: "BaseModel") -> Dict[str, Any]:
    try: # pydantic v2
        return data.model_dump(exclude_unset=True)
    except AttributeError: # pydantic v1
        return data.dict(exclude_unset=True)


def jsonify(data: "BaseModel") -> str:
    try: # pydantic v2
        return json.dumps(data.model_dump(exclude_unset=True), ensure_ascii=False)
    except AttributeError: # pydantic v1
        return data.json(exclude_unset=True, ensure_ascii=False)


def create_app() -> "FastAPI":
    app = FastAPI()

    app.add_middleware(
        CORSMiddleware,
        allow_origins=["*"],
        allow_credentials=True,
        allow_methods=["*"],
        allow_headers=["*"],
    )

    semaphore = asyncio.Semaphore(int(os.environ.get("MAX_CONCURRENT", 1)))

    @app.get("/v1/models", response_model=ModelList)
    async def list_models():
        model_card = ModelCard(id="gpt-3.5-turbo")
        return ModelList(data=[model_card])

    @app.post("/v1/chat/completions", response_model=ChatCompletionResponse, status_code=status.HTTP_200_OK)
    async def create_chat_completion(request: ChatCompletionRequest):

        if len(request.messages) == 0 or request.messages[-1].role not in [Role.USER, Role.TOOL]:
            raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Invalid length")

        messages = [dictify(message) for message in request.messages]
        if len(messages) and messages[0]["role"] == Role.SYSTEM:
            system = messages.pop(0)["content"]
        else:
            system = None

        if len(messages) % 2 == 0:
            raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Only supports u/a/u/a/u...")

        for i in range(len(messages)):
            if i % 2 == 0 and messages[i]["role"] not in [Role.USER, Role.TOOL]:
                raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Invalid role")
            elif i % 2 == 1 and messages[i]["role"] not in [Role.ASSISTANT, Role.FUNCTION]:
                raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Invalid role")
            elif messages[i]["role"] == Role.TOOL:
                messages[i]["role"] = Role.OBSERVATION

        tool_list = request.tools
        if len(tool_list):
            try:
                tools = json.dumps([tool_list[0]["function"]], ensure_ascii=False)
            except Exception:
                raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Invalid tools")
        else:
            tools = ""

        async with semaphore:
            loop = asyncio.get_running_loop()
            return await loop.run_in_executor(None, chat_completion, messages, system, tools, request)

    def chat_completion(messages: Sequence[Dict[str, str]], system: str, tools: str, request: ChatCompletionRequest):
        if request.stream:
            generate = stream_chat_completion(messages, system, tools, request)
            return EventSourceResponse(generate, media_type="text/event-stream")

        responses = ollama.chat(model=request.model,
                                messages=messages,
                                options={
                                    "top_p": request.top_p,
                                    "temperature": request.temperature
                                })

        prompt_length, response_length = 0, 0
        choices = []

        result = responses['message']['content']
        response_message = ChatCompletionMessage(role=Role.ASSISTANT, content=result)
        finish_reason = Finish.STOP if responses.get("done", False) == True else Finish.LENGTH

        choices.append(
            ChatCompletionResponseChoice(index=0, message=response_message, finish_reason=finish_reason)
        )
        prompt_length = -1
        response_length += -1

        usage = ChatCompletionResponseUsage(
            prompt_tokens=prompt_length,
            completion_tokens=response_length,
            total_tokens=prompt_length + response_length,
        )

        return ChatCompletionResponse(model=request.model, choices=choices, usage=usage)

    def stream_chat_completion(
            messages: Sequence[Dict[str, str]], system: str, tools: str, request: ChatCompletionRequest
    ):
        choice_data = ChatCompletionResponseStreamChoice(
            index=0, delta=ChatCompletionMessage(role=Role.ASSISTANT, content=""), finish_reason=None
        )
        chunk = ChatCompletionStreamResponse(model=request.model, choices=[choice_data])
        yield jsonify(chunk)

        for new_text in ollama.chat(
                model=request.model,
                messages=messages,
                stream=True,
                options={
                    "top_p": request.top_p,
                    "temperature": request.temperature
                }
        ):
            if len(new_text) == 0:
                continue

            choice_data = ChatCompletionResponseStreamChoice(
                index=0, delta=ChatCompletionMessage(content=new_text['message']['content']), finish_reason=None
            )
            chunk = ChatCompletionStreamResponse(model=request.model, choices=[choice_data])
            yield jsonify(chunk)

        choice_data = ChatCompletionResponseStreamChoice(
            index=0, delta=ChatCompletionMessage(), finish_reason=Finish.STOP
        )
        chunk = ChatCompletionStreamResponse(model=request.model, choices=[choice_data])
        yield jsonify(chunk)
        yield "[DONE]"

    return app


if __name__ == "__main__":
    app = create_app()
    uvicorn.run(app, host="0.0.0.0", port=int(os.environ.get("API_PORT", 8000)), workers=1)

测试

curl --location 'http://127.0.0.1:8000/v1/chat/completions' \
--header 'Content-Type: application/json' \
--data '{
  "model": "qwen:7b",
  "messages": [{"role": "user", "content": "What is the OpenAI mission?"}],
  "stream": true,
  "temperature": 0.7,
  "top_p": 1
}'