Feature/vllm/input embedding completion api (#17590)

Signed-off-by: Andrew Sansom <andrew@protopia.ai>
Signed-off-by: Nan2018 <nan@protopia.ai>
Co-authored-by: 临景 <linjing.yx@alibaba-inc.com>
Co-authored-by: Bryce1010 <bryceyx@gmail.com>
Co-authored-by: Andrew Sansom <andrew@protopia.ai>
Co-authored-by: Andrew Sansom <qthequartermasterman@gmail.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>

vllm/entrypoints/openai/protocol.py

@@ -745,7 +745,8 @@ class CompletionRequest(OpenAIBaseModel):
     # Ordered by official OpenAI API documentation
     # https://platform.openai.com/docs/api-reference/completions/create
     model: Optional[str] = None
-    prompt: Union[list[int], list[list[int]], str, list[str]]
+    prompt: Optional[Union[list[int], list[list[int]], str, list[str]]] = None
+    prompt_embeds: Optional[Union[bytes, list[bytes]]] = None
     best_of: Optional[int] = None
     echo: Optional[bool] = False
     frequency_penalty: Optional[float] = 0.0
@@ -1025,6 +1026,14 @@ class CompletionRequest(OpenAIBaseModel):
 
         return data
 
+    @model_validator(mode="before")
+    @classmethod
+    def validate_prompt_and_prompt_embeds(cls, data):
+        if data.get("prompt") is None and data.get("prompt_embeds") is None:
+            raise ValueError(
+                "At least one of `prompt` or `prompt_embeds` must be set.")
+        return data
+
 
 class EmbeddingCompletionRequest(OpenAIBaseModel):
     # Ordered by official OpenAI API documentation