Merge branch 'feat/support_reasoning' into 'integration_2025-02-06_695254313218'

feat: [development task] ark-runtime-manual-Python (999432)

See merge request iaasng/volcengine-python-sdk!503

Author: BitsAdmin

volcenginesdkarkruntime/types/chat/chat_completion_chunk.py

@@ -70,6 +70,9 @@ class ChoiceDelta(BaseModel):
 
     tool_calls: Optional[List[ChoiceDeltaToolCall]] = None
 
+    reasoning_content: Optional[str] = None
+    """The reasoning content of the message."""
+
 
 class ChoiceLogprobs(BaseModel):
     content: Optional[List[ChatCompletionTokenLogprob]] = None

volcenginesdkarkruntime/types/chat/chat_completion_message.py

@@ -40,3 +40,6 @@ class ChatCompletionMessage(BaseModel):
 
     audio: Optional[ChatCompletionAudio] = None
     """Audio response from the model."""
+
+    reasoning_content: Optional[str] = None
+    """The reasoning content of the message."""

volcenginesdkarkruntime/types/completion_usage.py

@@ -11,6 +11,11 @@ class PromptTokensDetails(BaseModel):
     """Number of tokens hit cache."""
 
 
+class CompletionTokensDetails(BaseModel):
+    reasoning_tokens: Optional[int] = None
+    """Tokens generated by the model for reasoning."""
+
+
 class CompletionUsage(BaseModel):
     completion_tokens: int
     """Number of tokens in the generated completion."""
@@ -23,3 +28,6 @@ class CompletionUsage(BaseModel):
 
     prompt_tokens_details: Optional[PromptTokensDetails] = None
     """Prompt tokens details."""
+
+    completion_tokens_details: Optional[CompletionTokensDetails] = None
+    """Breakdown of tokens used in a completion."""

volcenginesdkexamples/volcenginesdkarkruntime/reasoning_completions.py

@@ -0,0 +1,44 @@
+from volcenginesdkarkruntime import Ark
+
+# Authentication
+# 1.If you authorize your endpoint using an API key, you can set your api key to environment variable "ARK_API_KEY"
+# or specify api key by Ark(api_key="${YOUR_API_KEY}").
+# Note: If you use an API key, this API key will not be refreshed.
+# To prevent the API from expiring and failing after some time, choose an API key with no expiration date.
+
+# 2.If you authorize your endpoint with Volcengine Identity and Access Management（IAM),
+# set your api key to environment variable "VOLC_ACCESSKEY", "VOLC_SECRETKEY"
+# or specify ak&sk by Ark(ak="${YOUR_AK}", sk="${YOUR_SK}").
+# To get your ak&sk, please refer to this document(https://www.volcengine.com/docs/6291/65568)
+# For more information，please check this document（https://www.volcengine.com/docs/82379/1263279）
+client = Ark()
+
+if __name__ == "__main__":
+    # Non-streaming:
+    print("----- standard request -----")
+    completion = client.chat.completions.create(
+        model="${YOUR_ENDPOINT_ID}",
+        messages=[
+            {"role": "user", "content": "How many Rs are there in the word 'strawberry'?"},
+        ],
+    )
+    print(completion.choices[0].message.reasoning_content)
+    print(completion.choices[0].message.content)
+
+    # Streaming:
+    print("----- streaming request -----")
+    stream = client.chat.completions.create(
+        model="${YOUR_ENDPOINT_ID}",
+        messages=[
+            {"role": "user", "content": "How many Rs are there in the word 'strawberry'?"},
+        ],
+        stream=True
+    )
+    for chunk in stream:
+        if not chunk.choices:
+            continue
+        if chunk.choices[0].delta.reasoning_content:
+            print(chunk.choices[0].delta.reasoning_content, end="")
+        else:
+            print(chunk.choices[0].delta.content, end="")
+    print()