fix: adjust naming and tests and rebase typo

Author: drbh

clients/python/text_generation/types.py

@@ -115,7 +115,7 @@ class ChatComplete(BaseModel):
     usage: Any
 
 
-class CompletionComplete(BaseModel):
+class Completion(BaseModel):
     # Completion details
     id: str
     object: str

integration-tests/conftest.py

@@ -27,7 +27,7 @@
     ChatComplete,
     ChatCompletionChunk,
     ChatCompletionComplete,
-    CompletionComplete,
+    Completion,
 )
 
 DOCKER_IMAGE = os.getenv("DOCKER_IMAGE", None)
@@ -71,17 +71,22 @@ def convert_data(data):
             data = json.loads(data)
             if isinstance(data, Dict) and "choices" in data:
                 choices = data["choices"]
-                print(choices)
                 if isinstance(choices, List) and len(choices) >= 1:
                     if "delta" in choices[0]:
                         return ChatCompletionChunk(**data)
                     if "text" in choices[0]:
-                        return CompletionComplete(**data)
+                        return Completion(**data)
                 return ChatComplete(**data)
 
             if isinstance(data, Dict):
                 return Response(**data)
             if isinstance(data, List):
+                if (
+                    len(data) > 0
+                    and "object" in data[0]
+                    and data[0]["object"] == "text_completion"
+                ):
+                    return [Completion(**d) for d in data]
                 return [Response(**d) for d in data]
             raise NotImplementedError
 
@@ -163,7 +168,7 @@ def eq_details(details: Details, other: Details) -> bool:
                 )
             )
 
-        def eq_completion(response: ChatComplete, other: ChatComplete) -> bool:
+        def eq_completion(response: Completion, other: Completion) -> bool:
             return response.choices[0].text == other.choices[0].text
 
         def eq_chat_complete(response: ChatComplete, other: ChatComplete) -> bool:
@@ -189,7 +194,7 @@ def eq_response(response: Response, other: Response) -> bool:
         if not isinstance(snapshot_data, List):
             snapshot_data = [snapshot_data]
 
-        if isinstance(serialized_data[0], CompletionComplete):
+        if isinstance(serialized_data[0], Completion):
             return len(snapshot_data) == len(serialized_data) and all(
                 [eq_completion(r, o) for r, o in zip(serialized_data, snapshot_data)]
             )

integration-tests/models/__snapshots__/test_completion_prompts/test_flash_llama_completion_many_prompts.json

@@ -6,12 +6,6 @@
       "logprobs": null,
       "text": " PR for more information?"
     },
-    {
-      "finish_reason": "length",
-      "index": 3,
-      "logprobs": null,
-      "text": "hd20220811-"
-    },
     {
       "finish_reason": "length",
       "index": 0,
@@ -23,13 +17,19 @@
       "index": 2,
       "logprobs": null,
       "text": " severely flawed and often has a substandard"
+    },
+    {
+      "finish_reason": "length",
+      "index": 3,
+      "logprobs": null,
+      "text": "hd20220811-"
     }
   ],
-  "created": 1712875413,
+  "created": 1713284455,
   "id": "",
   "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
   "object": "text_completion",
-  "system_fingerprint": "1.4.5-native",
+  "system_fingerprint": "2.0.0-native",
   "usage": {
     "completion_tokens": 36,
     "prompt_tokens": 8,