Update app.py

app.py

@@ -25,8 +25,8 @@ except Exception as e:
 @spaces.GPU()
 def analyze_symptoms(symptom_image: Image.Image, symptoms_text: str):
     """
-    Analyzes user's symptoms using the recommended chat format and correct
-    parameter passing for the MedGemma multimodal model.
+    Analyzes user's symptoms using the definitive correct calling convention for
+    multimodal chat models in Hugging Face pipelines.
     """
     if not model_loaded:
         return "Error: The AI model could not be loaded. Please check the Space logs."
@@ -36,7 +36,7 @@ def analyze_symptoms(symptom_image: Image.Image, symptoms_text: str):
         return "Please describe your symptoms or upload an image for analysis."
 
     try:
-        # --- CHAT-BASED PROMPT LOGIC (Unchanged) ---
+        # --- DEFINITIVE CHAT-BASED PROMPT LOGIC ---
         system_instruction = (
             "You are an expert, empathetic AI medical assistant. "
             "Analyze the potential medical condition based on the user's input. "
@@ -45,42 +45,53 @@ def analyze_symptoms(symptom_image: Image.Image, symptoms_text: str):
             "the user provided."
         )
 
+        # The user's content is a list of dictionaries describing the multimodal input.
         user_content = []
-        text_to_send = symptoms_text if symptoms_text else "Please analyze this medical image."
-        user_content.append({"type": "text", "text": text_to_send})
+        
+        # The text part of the prompt.
+        user_content.append({"type": "text", "text": symptoms_text})
 
+        # The images to be passed to the pipeline.
+        images_to_pass = []
         if symptom_image:
-            user_content.append({"type": "image", "image": symptom_image})
+            # 1. Add a placeholder to the content list.
+            user_content.append({"type": "image"})
+            # 2. Add the actual PIL image object to a separate list.
+            images_to_pass.append(symptom_image)
 
+        # Construct the final messages list for the chat template.
         messages = [
             {"role": "system", "content": system_instruction},
             {"role": "user", "content": user_content},
         ]
         
-        print("Generating pipeline output with chat format...")
+        print("Generating pipeline output with separate image argument...")
 
-        # --- DEFINITIVE PIPELINE CALL ---
-        # All text-generation parameters must be nested within a 'generate_kwargs' dictionary.
+        # Generation parameters must be in a `generate_kwargs` dictionary.
         generate_kwargs = {
             "max_new_tokens": 512,
             "do_sample": True,
             "temperature": 0.7,
         }
-
-        # The `messages` list is the primary argument.
-        # `generate_kwargs` is a dedicated keyword argument for generation options.
-        output = pipe(messages, generate_kwargs=generate_kwargs)
+        
+        # --- THE DEFINITIVE PIPELINE CALL ---
+        # The pipeline call requires three distinct things:
+        # 1. The `messages` list describing the chat structure.
+        # 2. The `images` list containing the actual PIL image data.
+        # 3. The `generate_kwargs` dictionary for generation parameters.
+        output = pipe(
+            messages,
+            images=images_to_pass,
+            generate_kwargs=generate_kwargs
+        )
 
         print("Pipeline Output:", output)
 
-        # --- OUTPUT PROCESSING (Unchanged) ---
-        if output and isinstance(output, list) and output[0].get('generated_text'):
-            full_conversation = output[0]['generated_text']
-            assistant_message = full_conversation[-1]
-            if assistant_message['role'] == 'assistant':
-                result = assistant_message['content']
-            else:
-                result = str(assistant_message)
+        # --- SIMPLIFIED OUTPUT PROCESSING ---
+        # For this pipeline, the output is a list with one dictionary.
+        # The 'generated_text' key contains the AI's response string directly.
+        if output and isinstance(output, list) and 'generated_text' in output[0]:
+            result = output[0]['generated_text']
         else:
             result = "The model did not return a valid response. Please try again."