Update app.py

app.py

@@ -38,12 +38,21 @@ class StopOnTokens(StoppingCriteria):
                 return True
         return False
 
+def format_prompt(self, message, history):
+        prompt = ""
+        if history:
+            for user_prompt, bot_response in history:
+                prompt += f"<start_of_turn>user{user_prompt}<end_of_turn>"
+                prompt += f"<start_of_turn>model{bot_response}"
+        prompt += f"<start_of_turn>user{message}<end_of_turn><start_of_turn>modelo"
+        return prompt
+
 def getProductDetails(history, image):
     product_description=getImageDescription(image)
     clients = InferenceClient("google/gemma-7b")
     rand_val = random.randint(1, 1111111111111111)
     if not history:
-        history = [[{"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "hello"}]]
+        history = []
     generate_kwargs = dict(
         temperature=0.67,
         max_new_tokens=1024,
@@ -54,9 +63,9 @@ def getProductDetails(history, image):
     )
     system_prompt="you're a helpful e-commerce marketting assitant"
     prompt="Write me a poem"
-    formatted_prompt = self.format_prompt(f"{system_prompt}, {prompt}", history)
+    formatted_prompt = format_prompt(f"{system_prompt}, {prompt}", history)
     stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=stream_output, details=True, return_full_text=False)
-    # output = ""
+    output = ""
     
     # for response in stream:
     #     output += response.token.text