你当前正在访问 Microsoft Azure Global Edition 技术文档网站。如果需要访问由世纪互联运营的 Microsoft Azure 中国技术文档网站，请访问 https://docs.azure.cn。

Azure OpenAI 助手入门（预览版）

项目
05/24/2024

使用 Azure OpenAI 助手（预览版），可以创建通过自定义说明按需定制和使用高级工具（如代码解释器和自定义函数）增强的 AI 助手。在本文中，我们将深入演示助手 API 入门。

注意

文件搜索可为每个助手最多引入 10000 个文件，这比之前多 500 倍。它速度快，支持通过多线程搜索进行并行查询，并具有增强的重新排序和查询重写功能。
- 矢量存储是 API 中的新对象。文件一旦添加到矢量存储中，就会自动进行分析、分块和嵌入，以便随时搜索。矢量存储可跨助手和线程使用，简化了文件管理和计费。
我们添加了对 tool_choice 参数的支持，该参数可用于在特定运行中强制使用特定工具（如文件搜索、代码解释器或函数）。

助手支持

区域和模型支持

代码解释器可在 Azure OpenAI 助手支持的所有区域中使用。模型页包含有关目前支持助手的区域/模型的最新信息。

API 版本

2024-02-15-preview
2024-05-01-preview

支持的文件类型

文件格式	MIME 类型	代码解释器
c.	text/x-c	✅
.cpp	text/x-c++	✅
.csv	application/csv	✅
.docx	application/vnd.openxmlformats-officedocument.wordprocessingml.document	✅
.html	text/html	✅
.java	text/x-java	✅
.json	application/json	✅
.md	text/markdown	✅
.pdf	application/pdf	✅
.php	text/x-php	✅
.pptx	application/vnd.openxmlformats-officedocument.presentationml.presentation	✅
.py	text/x-python	✅
.py	text/x-script.python	✅
.rb	text/x-ruby	✅
.tex	text/x-tex	✅
.txt	text/plain	✅
.css	text/css	✅
.jpeg	image/jpeg	✅
.jpg	image/jpeg	✅
.js	text/javascript	✅
.gif	image/gif	✅
.png	image/png	✅
.tar	application/x-tar	✅
.ts	application/typescript	✅
.xlsx	application/vnd.openxmlformats-officedocument.spreadsheetml.sheet	✅
.xml	application/xml 或“text/xml”	✅
.zip	application/zip	✅

工具

提示

我们添加了对 tool_choice 参数的支持，该参数可用于在特定运行中强制使用特定工具（如 file_search、code_interpreter 或 function）。

单个助手最多可以访问 128 个工具（其中包括代码解释器和文件搜索），但你也可以通过函数定义自己的自定义工具。

文件

可以通过 Studio 上传文件，也可以编程方式上传。需要使用 file_ids 参数才能向 code_interpreter 等工具提供对文件的访问权限。使用文件上传终结点时，必须将 purpose 设置为要与助手 API 一起使用的助手。

助手操场

我们在快速入门指南中提供了助手操场演练。它提供了一个无代码环境来测试助手的功能。

助手组件

组件	描述
助手	将 Azure OpenAI 模型与工具结合使用的自定义 AI。
线程	助手和用户之间的对话会话。线程存储消息并自动处理截断，使内容适合模型的上下文。
消息	由助手或用户创建的消息。消息可以包括文本、图像和其他文件。消息以列表的形式存储在线程上。
运行	激活助手以根据线程的内容开始运行。助手使用其配置和线程的消息通过调用模型和工具来执行任务。在运行期间，助手会将消息追加到线程。
运行步骤	助手在运行期间所采取的步骤的详细列表。助手可以在运行期间调用工具或创建消息。检查运行步骤可以了解助手如何获得最终结果。

设置第一个助手

创建助手

在本示例中，我们将创建一个助手，它会编写代码以使用 code_interpreter 工具的功能生成可视化效果。以下示例旨在按顺序在 Jupyter Notebooks 等环境中运行。

import os
import json
from openai import AzureOpenAI
    
client = AzureOpenAI(
    api_key=os.getenv("AZURE_OPENAI_API_KEY"),  
    api_version="2024-05-01-preview",
    azure_endpoint = os.getenv("AZURE_OPENAI_ENDPOINT")
    )

# Create an assistant
assistant = client.beta.assistants.create(
    name="Data Visualization",
    instructions=f"You are a helpful AI assistant who makes interesting visualizations based on data." 
    f"You have access to a sandboxed environment for writing and testing code."
    f"When you are asked to create a visualization you should follow these steps:"
    f"1. Write the code."
    f"2. Anytime you write new code display a preview of the code to show your work."
    f"3. Run the code to confirm that it runs."
    f"4. If the code is successful display the visualization."
    f"5. If the code is unsuccessful display the error message and try to revise the code and rerun going through the steps from above again.",
    tools=[{"type": "code_interpreter"}],
    model="gpt-4-1106-preview" #You must replace this value with the deployment name for your model.
)

应从上述配置中记下一些详细信息：

我们支持此助手使用行 tools=[{"type": "code_interpreter"}], 访问代码解释器。通过此操作，模型能够访问沙箱式 Python 环境来运行和执行代码，以帮助生成对用户问题的答复。
在说明中，我们会提醒模型可以执行代码。有时，模型需要帮助，以引导它找到正确的工具来解决给定查询。如果你知道你希望使用特定库来生成某些你知道属于代码解释器一部分的响应，它可以通过说出“使用 Matplotlib 执行 x”之类的内容来帮助提供指导。
由于这是 Azure OpenAI，因此为 model= 输入的值必须与部署名称匹配。

接下来，我们将打印刚刚创建的助手的内容，以确认创建是否成功：

print(assistant.model_dump_json(indent=2))

{
  "id": "asst_7AZSrv5I3XzjUqWS40X5UgRr",
  "created_at": 1705972454,
  "description": null,
  "file_ids": [],
  "instructions": "You are a helpful AI assistant who makes interesting visualizations based on data.You have access to a sandboxed environment for writing and testing code.When you are asked to create a visualization you should follow these steps:1. Write the code.2. Anytime you write new code display a preview of the code to show your work.3. Run the code to confirm that it runs.4. If the code is successful display the visualization.5. If the code is unsuccessful display the error message and try to revise the code and rerun going through the steps from above again.",
  "metadata": {},
  "model": "gpt-4-1106-preview",
  "name": "Data Visualization",
  "object": "assistant",
  "tools": [
    {
      "type": "code_interpreter"
    }
  ]
}

创建线程

现在让我们创建一个线程。

# Create a thread
thread = client.beta.threads.create()
print(thread)

Thread(id='thread_6bunpoBRZwNhovwzYo7fhNVd', created_at=1705972465, metadata={}, object='thread')

线程实质上是助手和用户之间对话会话的记录。这类似于典型的聊天补全 API 调用中的消息数组/列表。关键差异之一是，与聊天补全消息数组不同，你无需通过每个调用跟踪令牌，以确保你仍位于模型的上下文长度以下。线程会抽象化此管理详细信息，并根据需要压缩线程历史记录，以允许对话继续。使用具有较大上下文长度以及支持最新功能的最新模型时，可以增强线程通过较大对话来完成此任务的能力。

接下来，创建要添加到线程的第一个用户问题。

# Add a user question to the thread
message = client.beta.threads.messages.create(
    thread_id=thread.id,
    role="user",
    content="Create a visualization of a sinewave"
)

列出线程消息

thread_messages = client.beta.threads.messages.list(thread.id)
print(thread_messages.model_dump_json(indent=2))

{
  "data": [
    {
      "id": "msg_JnkmWPo805Ft8NQ0gZF6vA2W",
      "assistant_id": null,
      "content": [
        {
          "text": {
            "annotations": [],
            "value": "Create a visualization of a sinewave"
          },
          "type": "text"
        }
      ],
      "created_at": 1705972476,
      "file_ids": [],
      "metadata": {},
      "object": "thread.message",
      "role": "user",
      "run_id": null,
      "thread_id": "thread_6bunpoBRZwNhovwzYo7fhNVd"
    }
  ],
  "object": "list",
  "first_id": "msg_JnkmWPo805Ft8NQ0gZF6vA2W",
  "last_id": "msg_JnkmWPo805Ft8NQ0gZF6vA2W",
  "has_more": false
}

运行线程

run = client.beta.threads.runs.create(
  thread_id=thread.id,
  assistant_id=assistant.id,
  #instructions="New instructions" #You can optionally provide new instructions but these will override the default instructions
)

我们也可以在此处传递参数 instructions，但这将替代我们已经为助手提供的现有说明。

检索线程状态

# Retrieve the status of the run
run = client.beta.threads.runs.retrieve(
  thread_id=thread.id,
  run_id=run.id
)

status = run.status
print(status)

completed

根据所运行查询的复杂性，线程的执行时间可能更长。在这种情况下，可以创建一个循环，以使用如以下示例所示的代码监视线程的运行状态：

import time
from IPython.display import clear_output

start_time = time.time()

status = run.status

while status not in ["completed", "cancelled", "expired", "failed"]:
    time.sleep(5)
    run = client.beta.threads.runs.retrieve(thread_id=thread.id,run_id=run.id)
    print("Elapsed time: {} minutes {} seconds".format(int((time.time() - start_time) // 60), int((time.time() - start_time) % 60)))
    status = run.status
    print(f'Status: {status}')
    clear_output(wait=True)

messages = client.beta.threads.messages.list(
  thread_id=thread.id
) 

print(f'Status: {status}')
print("Elapsed time: {} minutes {} seconds".format(int((time.time() - start_time) // 60), int((time.time() - start_time) % 60)))
print(messages.model_dump_json(indent=2))

当运行处于 in_progress 或其他非终止状态时，线程会被锁定。当线程被锁定时，将无法添加新消息，并且无法创建新运行。

列出运行后的线程消息

运行状态指示成功完成后，可以再次列出线程的内容，以检索模型和任何工具响应：

messages = client.beta.threads.messages.list(
  thread_id=thread.id
)

print(messages.model_dump_json(indent=2))

{
  "data": [
    {
      "id": "msg_M5pz73YFsJPNBbWvtVs5ZY3U",
      "assistant_id": "asst_eHwhP4Xnad0bZdJrjHO2hfB4",
      "content": [
        {
          "text": {
            "annotations": [],
            "value": "Is there anything else you would like to visualize or any additional features you'd like to add to the sine wave plot?"
          },
          "type": "text"
        }
      ],
      "created_at": 1705967782,
      "file_ids": [],
      "metadata": {},
      "object": "thread.message",
      "role": "assistant",
      "run_id": "run_AGQHJrrfV3eM0eI9T3arKgYY",
      "thread_id": "thread_ow1Yv29ptyVtv7ixbiKZRrHd"
    },
    {
      "id": "msg_oJbUanImBRpRran5HSa4Duy4",
      "assistant_id": "asst_eHwhP4Xnad0bZdJrjHO2hfB4",
      "content": [
        {
          "image_file": {
            "file_id": "assistant-1YGVTvNzc2JXajI5JU9F0HMD"
          },
          "type": "image_file"
        },
        {
          "text": {
            "annotations": [],
            "value": "Here is the visualization of a sine wave: \n\nThe wave is plotted using values from 0 to \\( 4\\pi \\) on the x-axis, and the corresponding sine values on the y-axis. I've also added grid lines for easier reading of the plot."
          },
          "type": "text"
        }
      ],
      "created_at": 1705967044,
      "file_ids": [],
      "metadata": {},
      "object": "thread.message",
      "role": "assistant",
      "run_id": "run_8PsweDFn6gftUd91H87K0Yts",
      "thread_id": "thread_ow1Yv29ptyVtv7ixbiKZRrHd"
    },
    {
      "id": "msg_Pu3eHjM10XIBkwqh7IhnKKdG",
      "assistant_id": null,
      "content": [
        {
          "text": {
            "annotations": [],
            "value": "Create a visualization of a sinewave"
          },
          "type": "text"
        }
      ],
      "created_at": 1705966634,
      "file_ids": [],
      "metadata": {},
      "object": "thread.message",
      "role": "user",
      "run_id": null,
      "thread_id": "thread_ow1Yv29ptyVtv7ixbiKZRrHd"
    }
  ],
  "object": "list",
  "first_id": "msg_M5pz73YFsJPNBbWvtVs5ZY3U",
  "last_id": "msg_Pu3eHjM10XIBkwqh7IhnKKdG",
  "has_more": false
}

检索文件 ID

我们已要求模型生成正弦波的图像。为了下载图像，首先需要检索图像文件 ID。

data = json.loads(messages.model_dump_json(indent=2))  # Load JSON data into a Python object
image_file_id = data['data'][0]['content'][0]['image_file']['file_id']

print(image_file_id)  # Outputs: assistant-1YGVTvNzc2JXajI5JU9F0HMD

下载映像

content = client.files.content(image_file_id)

image= content.write_to_file("sinewave.png")

下载图像后，在本地打开该图像：

from PIL import Image

# Display the image in the default image viewer
image = Image.open("sinewave.png")
image.show()

在线程上提出后续问题

由于助手没有完全按照我们的说明操作，并且包含在其响应的文本部分中运行的代码，因此我们可以显式请求该信息。

# Add a new user question to the thread
message = client.beta.threads.messages.create(
    thread_id=thread.id,
    role="user",
    content="Show me the code you used to generate the sinewave"
)

同样，我们需要运行并检索线程的状态：

run = client.beta.threads.runs.create(
  thread_id=thread.id,
  assistant_id=assistant.id,
  #instructions="New instructions" #You can optionally provide new instructions  but these will override the default instructions
)

# Retrieve the status of the run
run = client.beta.threads.runs.retrieve(
  thread_id=thread.id,
  run_id=run.id
)

status = run.status
print(status)

completed

运行状态完成后，我们将再次列出线程中的消息，现在它们应包含对最新问题的响应。

messages = client.beta.threads.messages.list(
  thread_id=thread.id
)

print(messages.model_dump_json(indent=2))

{
  "data": [
    {
      "id": "msg_oaF1PUeozAvj3KrNnbKSy4LQ",
      "assistant_id": "asst_eHwhP4Xnad0bZdJrjHO2hfB4",
      "content": [
        {
          "text": {
            "annotations": [],
            "value": "Certainly, here is the code I used to generate the sine wave visualization:\n\n```python\nimport numpy as np\nimport matplotlib.pyplot as plt\n\n# Generating data for the sinewave\nx = np.linspace(0, 4 * np.pi, 1000)  # Generate values from 0 to 4*pi\ny = np.sin(x)  # Compute the sine of these values\n\n# Plotting the sine wave\nplt.plot(x, y)\nplt.title('Sine Wave')\nplt.xlabel('x')\nplt.ylabel('sin(x)')\nplt.grid(True)\nplt.show()\n```\n\nThis code snippet uses `numpy` to generate an array of x values and then computes the sine for each x value. It then uses `matplotlib` to plot these values and display the resulting graph."
          },
          "type": "text"
        }
      ],
      "created_at": 1705969710,
      "file_ids": [],
      "metadata": {},
      "object": "thread.message",
      "role": "assistant",
      "run_id": "run_oDS3fH7NorCUVwROTZejKcZN",
      "thread_id": "thread_ow1Yv29ptyVtv7ixbiKZRrHd"
    },
    {
      "id": "msg_moYE3aNwFYuRq2aXpxpt2Wb0",
      "assistant_id": null,
      "content": [
        {
          "text": {
            "annotations": [],
            "value": "Show me the code you used to generate the sinewave"
          },
          "type": "text"
        }
      ],
      "created_at": 1705969678,
      "file_ids": [],
      "metadata": {},
      "object": "thread.message",
      "role": "user",
      "run_id": null,
      "thread_id": "thread_ow1Yv29ptyVtv7ixbiKZRrHd"
    },
    {
      "id": "msg_M5pz73YFsJPNBbWvtVs5ZY3U",
      "assistant_id": "asst_eHwhP4Xnad0bZdJrjHO2hfB4",
      "content": [
        {
          "text": {
            "annotations": [],
            "value": "Is there anything else you would like to visualize or any additional features you'd like to add to the sine wave plot?"
          },
          "type": "text"
        }
      ],
      "created_at": 1705967782,
      "file_ids": [],
      "metadata": {},
      "object": "thread.message",
      "role": "assistant",
      "run_id": "run_AGQHJrrfV3eM0eI9T3arKgYY",
      "thread_id": "thread_ow1Yv29ptyVtv7ixbiKZRrHd"
    },
    {
      "id": "msg_oJbUanImBRpRran5HSa4Duy4",
      "assistant_id": "asst_eHwhP4Xnad0bZdJrjHO2hfB4",
      "content": [
        {
          "image_file": {
            "file_id": "assistant-1YGVTvNzc2JXajI5JU9F0HMD"
          },
          "type": "image_file"
        },
        {
          "text": {
            "annotations": [],
            "value": "Here is the visualization of a sine wave: \n\nThe wave is plotted using values from 0 to \\( 4\\pi \\) on the x-axis, and the corresponding sine values on the y-axis. I've also added grid lines for easier reading of the plot."
          },
          "type": "text"
        }
      ],
      "created_at": 1705967044,
      "file_ids": [],
      "metadata": {},
      "object": "thread.message",
      "role": "assistant",
      "run_id": "run_8PsweDFn6gftUd91H87K0Yts",
      "thread_id": "thread_ow1Yv29ptyVtv7ixbiKZRrHd"
    },
    {
      "id": "msg_Pu3eHjM10XIBkwqh7IhnKKdG",
      "assistant_id": null,
      "content": [
        {
          "text": {
            "annotations": [],
            "value": "Create a visualization of a sinewave"
          },
          "type": "text"
        }
      ],
      "created_at": 1705966634,
      "file_ids": [],
      "metadata": {},
      "object": "thread.message",
      "role": "user",
      "run_id": null,
      "thread_id": "thread_ow1Yv29ptyVtv7ixbiKZRrHd"
    }
  ],
  "object": "list",
  "first_id": "msg_oaF1PUeozAvj3KrNnbKSy4LQ",
  "last_id": "msg_Pu3eHjM10XIBkwqh7IhnKKdG",
  "has_more": false
}

要仅提取对最新问题的响应，请执行以下操作：

data = json.loads(messages.model_dump_json(indent=2))
code = data['data'][0]['content'][0]['text']['value']
print(code)

当然，下面是我用于生成正弦波可视化效果的代码：

import numpy as np
import matplotlib.pyplot as plt

# Generating data for the sinewave
x = np.linspace(0, 4 * np.pi, 1000)  # Generate values from 0 to 4*pi
y = np.sin(x)  # Compute the sine of these values

# Plotting the sine wave
plt.plot(x, y)
plt.title('Sine Wave')
plt.xlabel('x')
plt.ylabel('sin(x)')
plt.grid(True)
plt.show()

深色模式

让我们向线程添加最后一个问题，以查看代码解释器是否可以将图表切换到深色模式。

# Add a user question to the thread
message = client.beta.threads.messages.create(
    thread_id=thread.id,
    role="user",
    content="I prefer visualizations in darkmode can you change the colors to make a darkmode version of this visualization."
)

# Run the thread
run = client.beta.threads.runs.create(
  thread_id=thread.id,
  assistant_id=assistant.id,
)

# Retrieve the status of the run
run = client.beta.threads.runs.retrieve(
  thread_id=thread.id,
  run_id=run.id
)

status = run.status
print(status)

completed

messages = client.beta.threads.messages.list(
  thread_id=thread.id
)

print(messages.model_dump_json(indent=2))

{
  "data": [
    {
      "id": "msg_KKzOHCArWGvGpuPo0pVZTHgV",
      "assistant_id": "asst_eHwhP4Xnad0bZdJrjHO2hfB4",
      "content": [
        {
          "text": {
            "annotations": [],
            "value": "You're viewing the dark mode version of the sine wave visualization in the image above. The plot is set against a dark background with a cyan colored sine wave for better contrast and visibility. If there's anything else you'd like to adjust or any other assistance you need, feel free to let me know!"
          },
          "type": "text"
        }
      ],
      "created_at": 1705971199,
      "file_ids": [],
      "metadata": {},
      "object": "thread.message",
      "role": "assistant",
      "run_id": "run_izZFyTVB1AlFM1VVMItggRn4",
      "thread_id": "thread_ow1Yv29ptyVtv7ixbiKZRrHd"
    },
    {
      "id": "msg_30pXFVYNgP38qNEMS4Zbozfk",
      "assistant_id": null,
      "content": [
        {
          "text": {
            "annotations": [],
            "value": "I prefer visualizations in darkmode can you change the colors to make a darkmode version of this visualization."
          },
          "type": "text"
        }
      ],
      "created_at": 1705971194,
      "file_ids": [],
      "metadata": {},
      "object": "thread.message",
      "role": "user",
      "run_id": null,
      "thread_id": "thread_ow1Yv29ptyVtv7ixbiKZRrHd"
    },
    {
      "id": "msg_3j31M0PaJLqO612HLKVsRhlw",
      "assistant_id": "asst_eHwhP4Xnad0bZdJrjHO2hfB4",
      "content": [
        {
          "image_file": {
            "file_id": "assistant-kfqzMAKN1KivQXaEJuU0u9YS"
          },
          "type": "image_file"
        },
        {
          "text": {
            "annotations": [],
            "value": "Here is the dark mode version of the sine wave visualization. I've used the 'dark_background' style in Matplotlib and chosen a cyan color for the plot line to ensure it stands out against the dark background."
          },
          "type": "text"
        }
      ],
      "created_at": 1705971123,
      "file_ids": [],
      "metadata": {},
      "object": "thread.message",
      "role": "assistant",
      "run_id": "run_B91erEPWro4bZIfryQeIDDlx",
      "thread_id": "thread_ow1Yv29ptyVtv7ixbiKZRrHd"
    },
    {
      "id": "msg_FgDZhBvvM1CLTTFXwgeJLdua",
      "assistant_id": null,
      "content": [
        {
          "text": {
            "annotations": [],
            "value": "I prefer visualizations in darkmode can you change the colors to make a darkmode version of this visualization."
          },
          "type": "text"
        }
      ],
      "created_at": 1705971052,
      "file_ids": [],
      "metadata": {},
      "object": "thread.message",
      "role": "user",
      "run_id": null,
      "thread_id": "thread_ow1Yv29ptyVtv7ixbiKZRrHd"
    },
    {
      "id": "msg_oaF1PUeozAvj3KrNnbKSy4LQ",
      "assistant_id": "asst_eHwhP4Xnad0bZdJrjHO2hfB4",
      "content": [
        {
          "text": {
            "annotations": [],
            "value": "Certainly, here is the code I used to generate the sine wave visualization:\n\n```python\nimport numpy as np\nimport matplotlib.pyplot as plt\n\n# Generating data for the sinewave\nx = np.linspace(0, 4 * np.pi, 1000)  # Generate values from 0 to 4*pi\ny = np.sin(x)  # Compute the sine of these values\n\n# Plotting the sine wave\nplt.plot(x, y)\nplt.title('Sine Wave')\nplt.xlabel('x')\nplt.ylabel('sin(x)')\nplt.grid(True)\nplt.show()\n```\n\nThis code snippet uses `numpy` to generate an array of x values and then computes the sine for each x value. It then uses `matplotlib` to plot these values and display the resulting graph."
          },
          "type": "text"
        }
      ],
      "created_at": 1705969710,
      "file_ids": [],
      "metadata": {},
      "object": "thread.message",
      "role": "assistant",
      "run_id": "run_oDS3fH7NorCUVwROTZejKcZN",
      "thread_id": "thread_ow1Yv29ptyVtv7ixbiKZRrHd"
    },
    {
      "id": "msg_moYE3aNwFYuRq2aXpxpt2Wb0",
      "assistant_id": null,
      "content": [
        {
          "text": {
            "annotations": [],
            "value": "Show me the code you used to generate the sinewave"
          },
          "type": "text"
        }
      ],
      "created_at": 1705969678,
      "file_ids": [],
      "metadata": {},
      "object": "thread.message",
      "role": "user",
      "run_id": null,
      "thread_id": "thread_ow1Yv29ptyVtv7ixbiKZRrHd"
    },
    {
      "id": "msg_M5pz73YFsJPNBbWvtVs5ZY3U",
      "assistant_id": "asst_eHwhP4Xnad0bZdJrjHO2hfB4",
      "content": [
        {
          "text": {
            "annotations": [],
            "value": "Is there anything else you would like to visualize or any additional features you'd like to add to the sine wave plot?"
          },
          "type": "text"
        }
      ],
      "created_at": 1705967782,
      "file_ids": [],
      "metadata": {},
      "object": "thread.message",
      "role": "assistant",
      "run_id": "run_AGQHJrrfV3eM0eI9T3arKgYY",
      "thread_id": "thread_ow1Yv29ptyVtv7ixbiKZRrHd"
    },
    {
      "id": "msg_oJbUanImBRpRran5HSa4Duy4",
      "assistant_id": "asst_eHwhP4Xnad0bZdJrjHO2hfB4",
      "content": [
        {
          "image_file": {
            "file_id": "assistant-1YGVTvNzc2JXajI5JU9F0HMD"
          },
          "type": "image_file"
        },
        {
          "text": {
            "annotations": [],
            "value": "Here is the visualization of a sine wave: \n\nThe wave is plotted using values from 0 to \\( 4\\pi \\) on the x-axis, and the corresponding sine values on the y-axis. I've also added grid lines for easier reading of the plot."
          },
          "type": "text"
        }
      ],
      "created_at": 1705967044,
      "file_ids": [],
      "metadata": {},
      "object": "thread.message",
      "role": "assistant",
      "run_id": "run_8PsweDFn6gftUd91H87K0Yts",
      "thread_id": "thread_ow1Yv29ptyVtv7ixbiKZRrHd"
    },
    {
      "id": "msg_Pu3eHjM10XIBkwqh7IhnKKdG",
      "assistant_id": null,
      "content": [
        {
          "text": {
            "annotations": [],
            "value": "Create a visualization of a sinewave"
          },
          "type": "text"
        }
      ],
      "created_at": 1705966634,
      "file_ids": [],
      "metadata": {},
      "object": "thread.message",
      "role": "user",
      "run_id": null,
      "thread_id": "thread_ow1Yv29ptyVtv7ixbiKZRrHd"
    }
  ],
  "object": "list",
  "first_id": "msg_KKzOHCArWGvGpuPo0pVZTHgV",
  "last_id": "msg_Pu3eHjM10XIBkwqh7IhnKKdG",
  "has_more": false
}

提取新的图像文件 ID 并下载和显示图像：

data = json.loads(messages.model_dump_json(indent=2))  # Load JSON data into a Python object
image_file_id = data['data'][0]['content'][0]['image_file']['file_id'] # index numbers can vary if you have had a different conversation over the course of the thread.

print(image_file_id)

content = client.files.content(image_file_id)
image= content.write_to_file("dark_sine.png")

# Display the image in the default image viewer
image = Image.open("dark_sine.png")
image.show()

其他参考

运行状态定义

Status	定义
`queued`	首次创建运行或完成 required_action 时，它们将移动到排队状态。它们几乎应该立即移动到 in_progress。
`in_progress`	在处于 in_progress 时，助手将使用模型和工具执行步骤。可以通过检查运行步骤来查看该运行的进度。
`completed`	运行已成功完成！现在，可以查看助手已添加到线程的所有消息，以及该运行执行的所有步骤。还可以通过将更多用户消息添加到线程并创建另一个运行来继续对话。
`requires_action`	使用函数调用工具时，运行将在模型确定了要调用的函数的名称和参数后移动到 required_action 状态。然后，必须运行这些函数，并在运行继续之前提交输出。如果在超过 expires_at 时间戳之前未提供输出（大约在创建后 10 分钟），则运行将移动到过期状态。
`expired`	如果在 expires_at 之前未提交调用输出的函数并且运行过期，则会发生这种情况。此外，如果运行执行时间过长且超出 expires_at 中所述的时间，则我们的系统会将该运行设为过期。
`cancelling`	可以使用“取消运行”终结点尝试取消 in_progress 运行。取消尝试成功后，运行状态将会变为已取消。可以尝试取消，但不能保证取消成功。
`cancelled`	已成功取消运行。
`failed`	可以通过查看运行中的 `last_error` 对象来查看失败的原因。失败的时间戳将记录在 failed_at 下。

消息注释

助理消息注释与完成和聊天补全 API 响应中显示的内容筛选批注不同。助手注释可以在对象的内容数组内发生。注释提供了有关如何在对用户的响应中注释文本的信息。

当消息内容数组中存在注释时，你将在需要替换为正确注释的文本中看到无法辨认的由模型生成的子字符串。这些字符串的外观可能类似于 【13†source】 或 sandbox:/mnt/data/file.csv。下面是 OpenAI 中的 Python 代码片段，它会将这些字符串替换为注释中提供的信息。


from openai import AzureOpenAI
    
client = AzureOpenAI(
    api_key=os.getenv("AZURE_OPENAI_API_KEY"),  
    api_version="2024-05-01-preview",
    azure_endpoint = os.getenv("AZURE_OPENAI_ENDPOINT")
    )

# Retrieve the message object
message = client.beta.threads.messages.retrieve(
  thread_id="...",
  message_id="..."
)

# Extract the message content
message_content = message.content[0].text
annotations = message_content.annotations
citations = []

# Iterate over the annotations and add footnotes
for index, annotation in enumerate(annotations):
    # Replace the text with a footnote
    message_content.value = message_content.value.replace(annotation.text, f' [{index}]')

    # Gather citations based on annotation attributes
    if (file_citation := getattr(annotation, 'file_citation', None)):
        cited_file = client.files.retrieve(file_citation.file_id)
        citations.append(f'[{index}] {file_citation.quote} from {cited_file.filename}')
    elif (file_path := getattr(annotation, 'file_path', None)):
        cited_file = client.files.retrieve(file_path.file_id)
        citations.append(f'[{index}] Click <here> to download {cited_file.filename}')
        # Note: File download functionality not implemented above for brevity

# Add footnotes to the end of the message before displaying to user
message_content.value += '\n' + '\n'.join(citations)

消息注释	说明
`file_citation`	文件引文由检索工具创建，它定义了对特定文件中特定引文的引用，该文件由助手上传并用于生成响应。
`file_path`	文件路径注释由 code_interpreter 工具创建，并且包含对该工具生成的文件的引用。

另请参阅

详细了解助手和代码解释器
详细了解助手和函数调用
Azure OpenAI 助手 API 示例

通过