本文属于机器翻译版本。若本译文内容与英语原文存在差异，则一律以英文原文为准。

# Pixtral Large（25.02）参数和推理
<a name="model-parameters-mistral-pixtral-large"></a>

Pixtral Large 25.02 是一款 124B 参数多模态模型，它将 state-of-the-art图像理解与强大的文本处理功能相结合。 AWS 是第一家将 Pixtral Large (25.02) 作为完全托管、无服务器模式交付的云提供商。该模型在执行文档分析、图表解读和自然图像理解任务时，能呈现前沿级性能，同时保留了 Mistral Large 2 的高级文本处理能力。

凭借 128K 的上下文窗口，Pixtral Large 25.02 在包括 docvQA 和 MathVista在内的关键基准测试上取得了 best-in-class性能。 VQAv2该模型具备覆盖多种语言的全面多语言支持功能，并且已基于 80 多种编程语言进行训练。关键功能包括高级数学推理、原生函数调用、JSON 输出，以及面向 RAG 应用的稳健上下文一致性。

您可以使用 Mistral AI 聊天完成 API 创建对话应用程序。您还可以将 Amazon Bedrock Converse API 与该模型结合使用。您可以使用工具进行函数调用。

**提示**  
您可以将Mistral AI聊天完成 API 与基本推理操作（[InvokeModel](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_InvokeModel.html)或 [InvokeModelWithResponseStream](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_InvokeModelWithResponseStream.html)）配合使用。但是，我们建议您使用 Converse API 在应用程序中实施消息传递。Converse API 提供了一组统一的参数，适用于所有支持消息的模型。有关更多信息，请参阅 [使用 Converse API 操作进行对话](conversation-inference.md)。

Mistral AI Pixtral Large 模型依据 [Mistral 研究许可协议](https://mistral.ai/licenses/MRL-0.1.md)提供。有关使用 Mistral AI 模型的更多信息，请参阅 [https://docs.mistral.ai/](https://docs.mistral.ai/) 文档。

**Topics**
+ [支持的模型](#mistral-supported-models-chat-completion)
+ [请求和响应示例](#model-parameters-pixtral-large-2502-request-response)

## 支持的模型
<a name="mistral-supported-models-chat-completion"></a>

您可以将以下 Mistral AI 模型与本页上的代码示例一起使用...
+ Pixtral Large (25.02)

您需要获取想要使用的模型的模型 ID。要获取模型 ID，请参阅 [Amazon Bedrock 中支持的根基模型](models-supported.md)。

## 请求和响应示例
<a name="model-parameters-pixtral-large-2502-request-response"></a>

------
#### [ Request ]

Pixtral Large（25.02）调用模型示例。

```
import boto3
import json
import base64


input_image = "image.png"
with open(input_image, "rb") as f:
    image = f.read()

image_bytes = base64.b64encode(image).decode("utf-8")

bedrock = boto3.client(
    service_name='bedrock-runtime',
    region_name="us-east-1")


request_body = {
    "messages" : [
        {
          "role" : "user",
          "content" : [
            {
              "text": "Describe this picture:",
              "type": "text"
            },
            {
              "type" : "image_url",
              "image_url" : {
                "url" : f"data:image/png;base64,{image_bytes}"
              }
            }
          ]
        }
      ],
      "max_tokens" : 10
    }

response = bedrock.invoke_model(
        modelId='us.mistral.pixtral-large-2502-v1:0',
        body=json.dumps(request_body)
       )


print(json.dumps(json.loads(response.get('body').read()), indent=4))
```

------
#### [ Converse ]

Pixtral Large（25.02）Converse 示例。

```
import boto3
import json
import base64

input_image = "image.png"
with open(input_image, "rb") as f:
    image_bytes = f.read()


bedrock = boto3.client(
    service_name='bedrock-runtime',
    region_name="us-east-1")

messages =[
    {
        "role" : "user",
        "content" : [
            {
              "text": "Describe this picture:"
            },
            {
                "image": {
                    "format": "png",
                    "source": {
                        "bytes": image_bytes
                    }
                }
            }
        ]
    }
]

response = bedrock.converse(
        modelId='mistral.pixtral-large-2502-v1:0',
        messages=messages
       )

print(json.dumps(response.get('output'), indent=4))
```

------
#### [ invoke\_model\_with\_response\_stream ]

Pixtral Large（25.02）invoke\_model\_with\_response\_stream 示例。

```
import boto3
import json
import base64


input_image = "image.png"
with open(input_image, "rb") as f:
    image = f.read()

image_bytes = base64.b64encode(image).decode("utf-8")

bedrock = boto3.client(
    service_name='bedrock-runtime',
    region_name="us-east-1")


request_body = {
    "messages" : [
        {
          "role" : "user",
          "content" : [
            {
              "text": "Describe this picture:",
              "type": "text"
            },
            {
              "type" : "image_url",
              "image_url" : {
                "url" : f"data:image/png;base64,{image_bytes}"
              }
            }
          ]
        }
      ],
      "max_tokens" : 10
    }

response = bedrock.invoke_model_with_response_stream(
        modelId='us.mistral.pixtral-large-2502-v1:0',
        body=json.dumps(request_body)
       )

stream = response.get('body')
if stream:
    for event in stream:
        chunk=event.get('chunk')
        if chunk:
            chunk_obj=json.loads(chunk.get('bytes').decode())
            print(chunk_obj)
```

------
#### [ converse\_stream ]

Pixtral Large（25.02）converse\_stream 示例。

```
import boto3
import json
import base64

input_image = "image.png"
with open(input_image, "rb") as f:
    image_bytes = f.read()


bedrock = boto3.client(
    service_name='bedrock-runtime',
    region_name="us-east-1")

messages =[
    {
        "role" : "user",
        "content" : [
            {
              "text": "Describe this picture:"
            },
            {
                "image": {
                    "format": "png",
                    "source": {
                        "bytes": image_bytes
                    }
                }
            }
        ]
    }
]

response = bedrock.converse_stream(
        modelId='mistral.pixtral-large-2502-v1:0',
        messages=messages
       )

stream = response.get('stream')
if stream:
    for event in stream:
        if 'messageStart' in event:
            print(f"\nRole: {event['messageStart']['role']}")

        if 'contentBlockDelta' in event:
            print(event['contentBlockDelta']['delta']['text'], end="")

        if 'messageStop' in event:
            print(f"\nStop reason: {event['messageStop']['stopReason']}")

        if 'metadata' in event:
            metadata = event['metadata']
            if 'usage' in metadata:
                print("\nToken usage ... ")
                print(f"Input tokens: {metadata['usage']['inputTokens']}")
                print(
                    f":Output tokens: {metadata['usage']['outputTokens']}")
                print(f":Total tokens: {metadata['usage']['totalTokens']}")
            if 'metrics' in event['metadata']:
                print(
                    f"Latency: {metadata['metrics']['latencyMs']} milliseconds")
```

------
#### [ JSON Output ]

Pixtral Large（25.02）JSON 输出示例。

```
import boto3 
import json

bedrock = session.client('bedrock-runtime', 'us-west-2')
mistral_params = {
        "body": json.dumps({
            "messages": [{"role": "user", "content": "What is the best French meal? Return the name and the ingredients in short JSON object."}]
        }),
        "modelId":"us.mistral.pixtral-large-2502-v1:0",
    }
response = bedrock.invoke_model(**mistral_params)

body = response.get('body').read().decode('utf-8')
print(json.loads(body))
```

------
#### [ Tooling ]

Pixtral Large（25.02）工具示例。

```
data = {
    'transaction_id': ['T1001', 'T1002', 'T1003', 'T1004', 'T1005'],
    'customer_id': ['C001', 'C002', 'C003', 'C002', 'C001'],
    'payment_amount': [125.50, 89.99, 120.00, 54.30, 210.20],
    'payment_date': ['2021-10-05', '2021-10-06', '2021-10-07', '2021-10-05', '2021-10-08'],
    'payment_status': ['Paid', 'Unpaid', 'Paid', 'Paid', 'Pending']
}

# Create DataFrame
df = pd.DataFrame(data)


def retrieve_payment_status(df: data, transaction_id: str) -> str:
    if transaction_id in df.transaction_id.values: 
        return json.dumps({'status': df[df.transaction_id == transaction_id].payment_status.item()})
    return json.dumps({'error': 'transaction id not found.'})

def retrieve_payment_date(df: data, transaction_id: str) -> str:
    if transaction_id in df.transaction_id.values: 
        return json.dumps({'date': df[df.transaction_id == transaction_id].payment_date.item()})
    return json.dumps({'error': 'transaction id not found.'})

tools = [
    {
        "type": "function",
        "function": {
            "name": "retrieve_payment_status",
            "description": "Get payment status of a transaction",
            "parameters": {
                "type": "object",
                "properties": {
                    "transaction_id": {
                        "type": "string",
                        "description": "The transaction id.",
                    }
                },
                "required": ["transaction_id"],
            },
        },
    },
    {
        "type": "function",
        "function": {
            "name": "retrieve_payment_date",
            "description": "Get payment date of a transaction",
            "parameters": {
                "type": "object",
                "properties": {
                    "transaction_id": {
                        "type": "string",
                        "description": "The transaction id.",
                    }
                },
                "required": ["transaction_id"],
            },
        },
    }
]

names_to_functions = {
    'retrieve_payment_status': functools.partial(retrieve_payment_status, df=df),
    'retrieve_payment_date': functools.partial(retrieve_payment_date, df=df)
}



test_tool_input = "What's the status of my transaction T1001?"
message = [{"role": "user", "content": test_tool_input}]


def invoke_bedrock_mistral_tool():
   
    mistral_params = {
        "body": json.dumps({
            "messages": message,
            "tools": tools           
        }),
        "modelId":"us.mistral.pixtral-large-2502-v1:0",
    }
    response = bedrock.invoke_model(**mistral_params)
    body = response.get('body').read().decode('utf-8')
    body = json.loads(body)
    choices = body.get("choices")
    message.append(choices[0].get("message"))

    tool_call = choices[0].get("message").get("tool_calls")[0]
    function_name = tool_call.get("function").get("name")
    function_params = json.loads(tool_call.get("function").get("arguments"))
    print("\nfunction_name: ", function_name, "\nfunction_params: ", function_params)
    function_result = names_to_functions[function_name](**function_params)

    message.append({"role": "tool", "content": function_result, "tool_call_id":tool_call.get("id")})
   
    new_mistral_params = {
        "body": json.dumps({
                "messages": message,
                "tools": tools           
        }),
        "modelId":"us.mistral.pixtral-large-2502-v1:0",
    }
    response = bedrock.invoke_model(**new_mistral_params)
    body = response.get('body').read().decode('utf-8')
    body = json.loads(body)
    print(body)
invoke_bedrock_mistral_tool()
```

------