Remove request arg from chat completion response processing (#240)

Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>

llama_stack/providers/adapters/inference/databricks/databricks.py

@@ -91,7 +91,7 @@ class DatabricksInferenceAdapter(ModelRegistryHelper, Inference):
     ) -> ChatCompletionResponse:
         params = self._get_params(request)
         r = client.completions.create(**params)
-        return process_chat_completion_response(request, r, self.formatter)
+        return process_chat_completion_response(r, self.formatter)
 
     async def _stream_chat_completion(
         self, request: ChatCompletionRequest, client: OpenAI
@@ -105,7 +105,7 @@ class DatabricksInferenceAdapter(ModelRegistryHelper, Inference):
 
         stream = _to_async_generator()
         async for chunk in process_chat_completion_stream_response(
-            request, stream, self.formatter
+            stream, self.formatter
         ):
             yield chunk
 

llama_stack/providers/adapters/inference/fireworks/fireworks.py

@@ -94,7 +94,7 @@ class FireworksInferenceAdapter(ModelRegistryHelper, Inference):
     ) -> ChatCompletionResponse:
         params = self._get_params(request)
         r = await client.completion.acreate(**params)
-        return process_chat_completion_response(request, r, self.formatter)
+        return process_chat_completion_response(r, self.formatter)
 
     async def _stream_chat_completion(
         self, request: ChatCompletionRequest, client: Fireworks
@@ -103,7 +103,7 @@ class FireworksInferenceAdapter(ModelRegistryHelper, Inference):
 
         stream = client.completion.acreate(**params)
         async for chunk in process_chat_completion_stream_response(
-            request, stream, self.formatter
+            stream, self.formatter
         ):
             yield chunk
 

llama_stack/providers/adapters/inference/ollama/ollama.py

@@ -143,7 +143,7 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
         response = OpenAICompatCompletionResponse(
             choices=[choice],
         )
-        return process_chat_completion_response(request, response, self.formatter)
+        return process_chat_completion_response(response, self.formatter)
 
     async def _stream_chat_completion(
         self, request: ChatCompletionRequest
@@ -163,7 +163,7 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
 
         stream = _generate_and_convert_to_openai_compat()
         async for chunk in process_chat_completion_stream_response(
-            request, stream, self.formatter
+            stream, self.formatter
         ):
             yield chunk
 

llama_stack/providers/adapters/inference/tgi/tgi.py

@@ -116,7 +116,7 @@ class _HfAdapter(Inference, ModelsProtocolPrivate):
         response = OpenAICompatCompletionResponse(
             choices=[choice],
         )
-        return process_chat_completion_response(request, response, self.formatter)
+        return process_chat_completion_response(response, self.formatter)
 
     async def _stream_chat_completion(
         self, request: ChatCompletionRequest
@@ -135,7 +135,7 @@ class _HfAdapter(Inference, ModelsProtocolPrivate):
 
         stream = _generate_and_convert_to_openai_compat()
         async for chunk in process_chat_completion_stream_response(
-            request, stream, self.formatter
+            stream, self.formatter
         ):
             yield chunk
 

llama_stack/providers/adapters/inference/together/together.py

@@ -108,7 +108,7 @@ class TogetherInferenceAdapter(
     ) -> ChatCompletionResponse:
         params = self._get_params(request)
         r = client.completions.create(**params)
-        return process_chat_completion_response(request, r, self.formatter)
+        return process_chat_completion_response(r, self.formatter)
 
     async def _stream_chat_completion(
         self, request: ChatCompletionRequest, client: Together
@@ -123,7 +123,7 @@ class TogetherInferenceAdapter(
 
         stream = _to_async_generator()
         async for chunk in process_chat_completion_stream_response(
-            request, stream, self.formatter
+            stream, self.formatter
         ):
             yield chunk
 

llama_stack/providers/impls/vllm/vllm.py

@@ -207,7 +207,7 @@ class VLLMInferenceImpl(ModelRegistryHelper, Inference):
         response = OpenAICompatCompletionResponse(
             choices=[choice],
         )
-        return process_chat_completion_response(request, response, self.formatter)
+        return process_chat_completion_response(response, self.formatter)
 
     async def _stream_chat_completion(
         self, request: ChatCompletionRequest, results_generator: AsyncGenerator
@@ -229,7 +229,7 @@ class VLLMInferenceImpl(ModelRegistryHelper, Inference):
 
         stream = _generate_and_convert_to_openai_compat()
         async for chunk in process_chat_completion_stream_response(
-            request, stream, self.formatter
+            stream, self.formatter
         ):
             yield chunk
 

llama_stack/providers/utils/inference/openai_compat.py

@@ -50,9 +50,7 @@ def text_from_choice(choice) -> str:
 
 
 def process_chat_completion_response(
-    request: ChatCompletionRequest,
+    response: OpenAICompatCompletionResponse, formatter: ChatFormat
-    response: OpenAICompatCompletionResponse,
-    formatter: ChatFormat,
 ) -> ChatCompletionResponse:
     choice = response.choices[0]
 
@@ -78,9 +76,7 @@ def process_chat_completion_response(
 
 
 async def process_chat_completion_stream_response(
-    request: ChatCompletionRequest,
+    stream: AsyncGenerator[OpenAICompatCompletionResponse, None], formatter: ChatFormat
-    stream: AsyncGenerator[OpenAICompatCompletionResponse, None],
-    formatter: ChatFormat,
 ) -> AsyncGenerator:
     yield ChatCompletionResponseStreamChunk(
         event=ChatCompletionResponseEvent(