Merge pull request #93 from Aleph-Alpha/add-raw-completion-parameter

Add raw_completion to completion request

aleph_alpha_client/aleph_alpha_client.py

@@ -268,6 +268,7 @@ def complete(
         contextual_control_threshold: Optional[float] = None,
         control_log_additive: Optional[bool] = True,
         repetition_penalties_include_completion: bool = True,
+        raw_completion: bool = False,
     ):
         """Generates samples from a prompt.
 
@@ -425,6 +426,12 @@ def complete(
 
             repetition_penalties_include_completion (bool, optional, default True)
                 Flag deciding whether presence penalty or frequency penalty are updated from the completion
+
+            raw_completion (bool, default False)
+                Setting this parameter to true forces the raw completion of the model to be returned.
+                For some models, we may optimize the completion that was generated by the model and
+                return the optimized completion in the completion field of the CompletionResponse.
+                The raw completion, if returned, will contain the un-optimized completion.
         """
 
         payload = {
@@ -461,6 +468,7 @@ def complete(
             "contextual_control_threshold": contextual_control_threshold,
             "control_log_additive": control_log_additive,
             "repetition_penalties_include_completion": repetition_penalties_include_completion,
+            "raw_completion": raw_completion,
         }
 
         if hosting is not None:

aleph_alpha_client/completion.py

@@ -167,6 +167,12 @@ class CompletionRequest(NamedTuple):
         repetition_penalties_include_completion (bool, optional, default True)
             Flag deciding whether presence penalty or frequency penalty are updated from the completion
 
+        raw_completion (bool, default False)
+            Setting this parameter to true forces the raw completion of the model to be returned.
+            For some models, we may optimize the completion that was generated by the model and
+            return the optimized completion in the completion field of the CompletionResponse.
+            The raw completion, if returned, will contain the un-optimized completion.
+
     Examples:
         >>> prompt = Prompt.from_text("Provide a short description of AI:")
         >>> request = CompletionRequest(prompt=prompt, maximum_tokens=20)
@@ -204,6 +210,7 @@ class CompletionRequest(NamedTuple):
     contextual_control_threshold: Optional[float] = None
     control_log_additive: Optional[bool] = True
     repetition_penalties_include_completion: bool = True
+    raw_completion: bool = False
 
     def to_json(self) -> Dict[str, Any]:
         payload = {k: v for k, v in self._asdict().items() if v is not None}