[Azure OpenAI ]Azure OpenAI助手入门（预览版）

Azure OpenAI Assistants (Preview) allows you to create AI assistants tailored to your needs through custom instructions and augmented by advanced tools like code interpreter, and custom functions. In this article, we provide an in-depth walkthrough of getting started with the Assistants API.

Code interpreter is available in all regions supported by Azure OpenAI Assistants. The models page contains the most up-to-date information on regions/models where Assistants are currently supported.

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

An individual assistant can access up to 128 tools including code interpreter and file search, but you can also define your own custom tools via functions.

Files can be uploaded via Studio, or programmatically. The file_ids parameter is required to give tools like code_interpreter access to files. When using the File upload endpoint, you must have the purpose set to assistants to be used with the Assistants API.

We provide a walkthrough of the Assistants playground in our quickstart guide. This provides a no-code environment to test out the capabilities of assistants.

For this example we'll create an assistant that writes code to generate visualizations using the capabilities of the code_interpreter tool. The examples below are intended to be run sequentially in an environment like Jupyter Notebooks.

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.
)

There are a few details you should note from the configuration above:

• We enable this assistant to access code interpreter with the line tools=[{"type": "code_interpreter"}],. This gives the model access to a sand-boxed python environment to run and execute code to help formulating responses to a user's question.
• In the instructions we remind the model that it can execute code. Sometimes the model needs help guiding it towards the right tool to solve a given query. If you know you want to use a particular library to generate a certain response that you know is part of code interpreter, it can help to provide guidance by saying something like "Use Matplotlib to do x."
• Since this is Azure OpenAI the value you enter for model= must match the deployment name.

Next we're going to print the contents of assistant that we just created to confirm that creation was successful:

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"
    }
  ]
}

Now let's create a thread.

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

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

A thread is essentially the record of the conversation session between the assistant and the user. It's similar to the messages array/list in a typical chat completions 

API call. One of the key differences, is unlike a chat completions messages array, you don't need to track tokens with each call to make sure that you're remaining 

below the context length of the model. Threads abstract away this management detail and will compress the thread history as needed in order to allow the 

conversation to continue. The ability for threads to accomplish this with larger conversations is enhanced when using the latest models, which have larger context

 lengths and support for the latest features.

Next create the first user question to add to the thread.

# 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"
)

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
}

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
)

We could also pass an instructions parameter here, but this would override the existing instructions that we have already provided for the assistant.

# 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

Depending on the complexity of the query you run, the thread could take longer to execute. In that case you can create a loop to monitor the run status of

 the thread with code like the example below:

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))

When a Run is in_progress or in other nonterminal states the thread is locked. When a thread is locked new messages can't be added, and new runs can't be created.

Once the run status indicates successful completion, you can list the contents of the thread again to retrieve the model's and any tools response:

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
}

We had requested that the model generate an image of a sine wave. In order to download the image, we first need to retrieve the images file 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

content = client.files.content(image_file_id)

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

Open the image locally once it's downloaded:

from PIL import Image

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

Since the assistant didn't quite follow our instructions and include the code that was run in the text portion of its response lets explicitly ask for that information.

# 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"
)

Again we'll need to run and retrieve the status of the thread:

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

Once the run status reaches completed, we'll list the messages in the thread again which should now include the response to our latest question.

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
}

To extract only the response to our latest question:

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

Certainly, here is the code I used to generate the sine wave visualization:

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()

Let's add one last question to the thread to see if code interpreter can swap the chart to dark mode for us.

# 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
}

Extract the new image file ID and download and display the image:

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()

Assistant message annotations are different from the content filtering annotations that are present in completion and chat completion API responses. Assistant annotations can occur within the content array of the object. Annotations provide information around how you should annotate the text in the responses to the user.

When annotations are present in the Message content array, you'll see illegible model-generated substrings in the text that you need to replace with the correct annotations. These strings might look something like 【13†source】 or sandbox:/mnt/data/file.csv. Here’s a Python code snippet from OpenAI that replaces these strings with the information present in the annotations.

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)

• Learn more about Assistants and Code Interpreter
• Learn more about Assistants and function calling
• Azure OpenAI Assistants API samples