Terjemahan disediakan oleh mesin penerjemah. Jika konten terjemahan yang diberikan bertentangan dengan versi bahasa Inggris aslinya, utamakan versi bahasa Inggris.

# Parameter dan inferensi Pixtral Large (25,02)
<a name="model-parameters-mistral-pixtral-large"></a>

Pixtral Large 25.02 adalah model multimodal parameter 124B yang menggabungkan pemahaman state-of-the-art gambar dengan kemampuan pemrosesan teks yang kuat. AWS adalah penyedia cloud pertama yang menghadirkan Pixtral Large (25.02) sebagai model tanpa server yang dikelola sepenuhnya. Model ini memberikan kinerja kelas perbatasan saat melakukan analisis dokumen, interpretasi bagan, dan tugas pemahaman gambar alami, sambil mempertahankan kemampuan teks lanjutan Mistral Large 2.

Dengan jendela konteks 128K, Pixtral Large 25.02 mencapai best-in-class kinerja pada tolok ukur utama termasuk, DocVQA, dan. MathVista VQAv2 Model ini memiliki dukungan multibahasa yang komprehensif di banyak bahasa dan dilatih pada lebih dari 80 bahasa pemrograman. Kemampuan utama termasuk penalaran matematika tingkat lanjut, panggilan fungsi asli, keluaran JSON, dan kepatuhan konteks yang kuat untuk aplikasi RAG.

API penyelesaian Mistral AI obrolan memungkinkan Anda membuat aplikasi percakapan. Anda juga dapat menggunakan Amazon Bedrock Converse API dengan model ini. Anda dapat menggunakan alat untuk melakukan panggilan fungsi.

**Tip**  
Anda dapat menggunakan API penyelesaian Mistral AI obrolan dengan operasi inferensi dasar ([InvokeModel](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_InvokeModel.html)atau [InvokeModelWithResponseStream](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_InvokeModelWithResponseStream.html)). Namun, kami menyarankan Anda menggunakan Converse API untuk mengimplementasikan pesan dalam aplikasi Anda. ConverseAPI menyediakan serangkaian parameter terpadu yang bekerja di semua model yang mendukung pesan. Untuk informasi selengkapnya, lihat [Melakukan percakapan dengan operasi Converse API](conversation-inference.md).

Model Mistral AI Pixtral Large tersedia di bawah Lisensi Penelitian [Mistral.](https://mistral.ai/licenses/MRL-0.1.md) Untuk informasi selengkapnya tentang penggunaan Mistral AI model, lihat [Mistral AIdokumentasi](https://docs.mistral.ai/).

**Topics**
+ [Model yang didukung](#mistral-supported-models-chat-completion)
+ [Contoh Permintaan dan Respons](#model-parameters-pixtral-large-2502-request-response)

## Model yang didukung
<a name="mistral-supported-models-chat-completion"></a>

Anda dapat menggunakan Mistral AI model berikut dengan contoh kode di halaman ini..
+ Pixtral Large (25.02)

Anda memerlukan ID model untuk model yang ingin Anda gunakan. Untuk mendapatkan ID model, lihat[Model pondasi yang didukung di Amazon Bedrock](models-supported.md). 

## Contoh Permintaan dan Respons
<a name="model-parameters-pixtral-large-2502-request-response"></a>

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

Pixtral Large (25.02) memanggil contoh model.

```
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) Contoh Converse.

```
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\$1model\$1with\$1response\$1stream ]

Pixtral Large (25.02) invoke\$1model\$1with\$1response\$1stream contoh. 

```
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\$1stream ]

Contoh converse\$1stream Pixtral Large (25.02). 

```
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 ]

Contoh keluaran JSON Pixtral Large (25.02). 

```
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 ]

Contoh alat Pixtral Large (25.02). 

```
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()
```

------