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。

# 使用聊天完成 API 进行推理
<a name="inference-chat-completions-mantle"></a>

OpenAI聊天完成 API 使用 Amazon Bedrock 模型生成对话回复。您可以在`bedrock-mantle`和`bedrock-runtime`端点上使用聊天完成 API。我们建议尽可能使用终`bedrock-mantle`端节点。如需了解完整的 API 详情，请参阅[OpenAI聊天完成文档。](https://developers.openai.com/api/reference/chat-completions/overview)


| **Endpoint** | **基本网址** | **身份验证** | 
| --- | --- | --- | 
| bedrock-mantle（推荐） | https://bedrock-mantle.{region}.api.aws/v1/chat/completions | 亚马逊 Bedrock API 密钥或证书 AWS  | 
| bedrock-runtime | https://bedrock-runtime.{region}.amazonaws.com/v1/chat/completions | AWS 凭证 (Sigv4) 或 Amazon Bedrock API 密钥 | 

每个端点都有自己的每个型号的令牌配额。有关应用于每个终端节点上流量的配额的详细信息，请参阅[基岩地幔端点的配额](quotas-mantle.md)和[基底运行时端点的配额](quotas-runtime.md)。

## 使用基岩地幔端点完成聊天
<a name="inference-chat-completions-mantle-endpoint"></a>

该`bedrock-mantle`终端节点支持 Amazon Bedrock API 密钥身份验证和OpenAI软件开发工具包。

### 列出可用型号
<a name="inference-chat-completions-mantle-list-models"></a>

要列出`bedrock-mantle`端点上可用的模型，请选择首选方法的选项卡，然后按照以下步骤操作：

------
#### [ OpenAI SDK (Python) ]

```
# List all available models using the OpenAI SDK
# Requires OPENAI_API_KEY and OPENAI_BASE_URL environment variables

from openai import OpenAI

client = OpenAI()

models = client.models.list()

for model in models.data:
    print(model.id)
```

------
#### [ HTTP request ]

```
# List all available models
# Requires OPENAI_API_KEY and OPENAI_BASE_URL environment variables

curl -X GET $OPENAI_BASE_URL/models \
   -H "Authorization: Bearer $OPENAI_API_KEY"
```

------

### 创建聊天补全
<a name="inference-chat-completions-mantle-create"></a>

选择与您的首选方法对应的选项卡，然后按照以下步骤操作：

------
#### [ OpenAI SDK (Python) ]

使用环境变量配置OpenAI客户端：

```
# Create a chat completion using the OpenAI SDK
# Requires OPENAI_API_KEY and OPENAI_BASE_URL environment variables

from openai import OpenAI

client = OpenAI()

completion = client.chat.completions.create(
    model="openai.gpt-oss-120b",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello!"}
    ]
)

print(completion.choices[0].message)
```

------
#### [ HTTP request ]

向以下地址发出 POST 请求`/v1/chat/completions`：

```
# Create a chat completion
# Requires OPENAI_API_KEY and OPENAI_BASE_URL environment variables

curl -X POST $OPENAI_BASE_URL/chat/completions \
   -H "Content-Type: application/json" \
   -H "Authorization: Bearer $OPENAI_API_KEY" \
   -d '{
    "model": "openai.gpt-oss-120b",
    "messages": [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello!"}
    ]
}'
```

------

**流式传输**  
要逐步接收回复，请选择首选方法的选项卡，然后按照以下步骤操作：

------
#### [ OpenAI SDK (Python) ]

```
# Stream chat completion responses incrementally using the OpenAI SDK
# Requires OPENAI_API_KEY and OPENAI_BASE_URL environment variables

from openai import OpenAI

client = OpenAI()

stream = client.chat.completions.create(
    model="openai.gpt-oss-120b",
    messages=[{"role": "user", "content": "Tell me a story"}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content is not None:
        print(chunk.choices[0].delta.content, end="")
```

------
#### [ HTTP request ]

向发出 POST 请求`/v1/chat/completions`，`stream`设置为`true`：

```
# Stream chat completion responses incrementally
# Requires OPENAI_API_KEY and OPENAI_BASE_URL environment variables

curl -X POST $OPENAI_BASE_URL/chat/completions \
   -H "Content-Type: application/json" \
   -H "Authorization: Bearer $OPENAI_API_KEY" \
   -d '{
    "model": "openai.gpt-oss-120b",
    "messages": [
        {"role": "user", "content": "Tell me a story"}
    ],
    "stream": true
}'
```

------

## 使用基底运行时端点完成聊天
<a name="inference-chat-completions-runtime-endpoint"></a>

`bedrock-runtime`终端节点支持 AWS Sigv4 身份验证和 Amazon Bedrock API 密钥身份验证。

### 列出可用型号
<a name="inference-chat-completions-runtime-list-models"></a>

要列出`bedrock-runtime`端点上可用的模型，请选择首选方法的选项卡，然后按照以下步骤操作：

------
#### [ OpenAI SDK (Python) ]

```
from openai import OpenAI
import os

client = OpenAI(
    base_url="https://bedrock-runtime.us-east-1.amazonaws.com/v1",
    api_key=os.environ.get("AWS_BEARER_TOKEN_BEDROCK")
)

models = client.models.list()
for model in models.data:
    print(model.id)
```

------
#### [ HTTP request ]

```
curl -X GET "https://bedrock-runtime.us-east-1.amazonaws.com/v1/models" \
  -H "Authorization: Bearer $AWS_BEARER_TOKEN_BEDROCK"
```

------

### 创建聊天补全
<a name="inference-chat-completions-runtime-create"></a>

选择与您的首选方法对应的选项卡，然后按照以下步骤操作：

------
#### [ OpenAI SDK (Python) ]

将OpenAI客户端配置为指向`bedrock-runtime`终端：

```
from openai import OpenAI
import os

client = OpenAI(
    base_url="https://bedrock-runtime.us-east-1.amazonaws.com/v1",
    api_key=os.environ.get("AWS_BEARER_TOKEN_BEDROCK")
)

response = client.chat.completions.create(
    model="us.anthropic.claude-sonnet-4-6",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)
```

------
#### [ HTTP request (API key) ]

```
curl -X POST "https://bedrock-runtime.us-east-1.amazonaws.com/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $AWS_BEARER_TOKEN_BEDROCK" \
  -d '{
    "model": "us.anthropic.claude-sonnet-4-6",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
```

------
#### [ HTTP request (SigV4) ]

```
curl -X POST "https://bedrock-runtime.us-east-1.amazonaws.com/v1/chat/completions" \
  -H "Content-Type: application/json" \
  --aws-sigv4 "aws:amz:us-east-1:bedrock" \
  --user "$AWS_ACCESS_KEY_ID:$AWS_SECRET_ACCESS_KEY" \
  -d '{
    "model": "us.anthropic.claude-sonnet-4-6",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
```

------

有关`bedrock-runtime`终端节点支持的型号、地区和高级功能的更多详细信息，请参阅[聊天完成 API（旧版参考）](inference-chat-completions.md)。

## 在聊天补全中添加护栏
<a name="inference-chat-completions-guardrails"></a>

要在模型输入和响应中加入保护措施，请在运行模型调用时通过在请求正文中添加以下[额外参数](https://github.com/openai/openai-python#undocumented-request-params)作为字段来应用[护栏](guardrails.md)：
+ `extra_headers` – 映射到包含以下字段的对象，这些字段在请求中指定了额外的标头：
  + `X-Amzn-Bedrock-GuardrailIdentifier`（必填）– 护栏的 ID。
  + `X-Amzn-Bedrock-GuardrailVersion`（必填）– 护栏的版本。
  + `X-Amzn-Bedrock-Trace`（可选）– 是否启用护栏跟踪。
+ `extra_body` – 映射到对象。在该对象中，您可以包含 `amazon-bedrock-guardrailConfig` 字段，该字段映射到包含以下字段的对象：
  + `tagSuffix`（可选）– 包含此字段以用于[输入标记](guardrails-tagging.md)。

有关 Amazon Bedrock 护栏中这些参数的更多信息，请参阅[测试护栏](guardrails-test.md)。

要查看在 OpenAI 聊天补全中使用护栏的示例，请选择首选方法的选项卡，然后按照以下步骤操作：

------
#### [ OpenAI SDK (Python) ]

```
import openai
from openai import OpenAIError

# Endpoint for Amazon Bedrock Runtime
bedrock_endpoint = "https://bedrock-runtime.us-west-2.amazonaws.com/openai/v1"

# Model ID
model_id = "openai.gpt-oss-20b-1:0"

# Replace with actual values
bedrock_api_key = "$AWS_BEARER_TOKEN_BEDROCK"
guardrail_id = "GR12345"
guardrail_version = "DRAFT"

client = openai.OpenAI(
    api_key=bedrock_api_key,
    base_url=bedrock_endpoint,
)

try:
    response = client.chat.completions.create(
        model=model_id,
        # Specify guardrail information in the header
        extra_headers={
            "X-Amzn-Bedrock-GuardrailIdentifier": guardrail_id,
            "X-Amzn-Bedrock-GuardrailVersion": guardrail_version,
            "X-Amzn-Bedrock-Trace": "ENABLED",
        },
        # Additional guardrail information can be specified in the body
        extra_body={
            "amazon-bedrock-guardrailConfig": {
                "tagSuffix": "xyz"  # Used for input tagging
            }
        },
        messages=[
            {
                "role": "system",
                "content": "You are a helpful assistant."
            },
            {
                "role": "assistant", 
                "content": "Hello! How can I help you today?"
            },
            {
                "role": "user",
                "content": "What is the weather like today?"
            }
        ]
    )

    request_id = response._request_id
    print(f"Request ID: {request_id}")
    print(response)
    
except OpenAIError as e:
    print(f"An error occurred: {e}")
    if hasattr(e, 'response') and e.response is not None:
        request_id = e.response.headers.get("x-request-id")
        print(f"Request ID: {request_id}")
```

------
#### [ OpenAI SDK (Java) ]

```
import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.core.http.HttpResponseFor;
import com.openai.models.chat.completions.ChatCompletion;
import com.openai.models.chat.completions.ChatCompletionCreateParams;

// Endpoint for Amazon Bedrock Runtime
String bedrockEndpoint = "http://bedrock-runtime.us-west-2.amazonaws.com/openai/v1"

// Model ID
String modelId = "openai.gpt-oss-20b-1:0"

// Replace with actual values
String bedrockApiKey = "$AWS_BEARER_TOKEN_BEDROCK"
String guardrailId = "GR12345"
String guardrailVersion = "DRAFT"

OpenAIClient client = OpenAIOkHttpClient.builder()
        .apiKey(bedrockApiKey)
        .baseUrl(bedrockEndpoint)
        .build()

ChatCompletionCreateParams request = ChatCompletionCreateParams.builder()
        .addUserMessage("What is the temperature in Seattle?")
        .model(modelId)
        // Specify additional headers for the guardrail
        .putAdditionalHeader("X-Amzn-Bedrock-GuardrailIdentifier", guardrailId)
        .putAdditionalHeader("X-Amzn-Bedrock-GuardrailVersion", guardrailVersion)
        // Specify additional body parameters for the guardrail
        .putAdditionalBodyProperty(
                "amazon-bedrock-guardrailConfig",
                JsonValue.from(Map.of("tagSuffix", JsonValue.of("xyz"))) // Allows input tagging
        )
        .build();
        
HttpResponseFor<ChatCompletion> rawChatCompletionResponse =
        client.chat().completions().withRawResponse().create(request);

final ChatCompletion chatCompletion = rawChatCompletionResponse.parse();

System.out.println(chatCompletion);
```

------