NO LOGGING]

servers/cogvlm/cogvlm.py

@@ -159,33 +159,33 @@ async def create_chat_completion(
         content=response["text"],
     )
 
-    # Log the entry to supabase
-    entry = ModelAPILogEntry(
-        user_id=await fetch_api_key_info(token),
-        model_id="41a2869c-5f8d-403f-83bb-1f06c56bad47",
-        input_tokens=await count_tokens(request.messages, tokenizer, request.model),
-        output_tokens=await count_tokens(response["text"], tokenizer, request.model),
-        all_cost=await calculate_pricing(
-            texts=[message.content], tokenizer=tokenizer, rate_per_million=15.0
-        ),
-        input_cost=await calculate_pricing(
-            texts=[message.content], tokenizer=tokenizer, rate_per_million=15.0
-        ),
-        output_cost=await calculate_pricing(
-            texts=response["text"], tokenizer=tokenizer, rate_per_million=15.0
-        )
-        * 5,
-        messages=request.messages,
-        # temperature=request.temperature,
-        top_p=request.top_p,
-        # echo=request.echo,
-        stream=request.stream,
-        repetition_penalty=request.repetition_penalty,
-        max_tokens=request.max_tokens,
-    )
-
-    # Log the entry to supabase
-    await log_to_supabase(entry=entry)
+    # # Log the entry to supabase
+    # entry = ModelAPILogEntry(
+    #     user_id=await fetch_api_key_info(token),
+    #     model_id="41a2869c-5f8d-403f-83bb-1f06c56bad47",
+    #     input_tokens=await count_tokens(request.messages, tokenizer, request.model),
+    #     output_tokens=await count_tokens(response["text"], tokenizer, request.model),
+    #     all_cost=await calculate_pricing(
+    #         texts=[message.content], tokenizer=tokenizer, rate_per_million=15.0
+    #     ),
+    #     input_cost=await calculate_pricing(
+    #         texts=[message.content], tokenizer=tokenizer, rate_per_million=15.0
+    #     ),
+    #     output_cost=await calculate_pricing(
+    #         texts=response["text"], tokenizer=tokenizer, rate_per_million=15.0
+    #     )
+    #     * 5,
+    #     messages=request.messages,
+    #     # temperature=request.temperature,
+    #     top_p=request.top_p,
+    #     # echo=request.echo,
+    #     stream=request.stream,
+    #     repetition_penalty=request.repetition_penalty,
+    #     max_tokens=request.max_tokens,
+    # )
+
+    # # Log the entry to supabase
+    # await log_to_supabase(entry=entry)
 
     # ChatCompletionResponseChoice
     logger.debug(f"==== message ====\n{message}")