Update app.py

app.py

@@ -836,9 +836,10 @@ def classify(platform, UserInput, Images, Textbox2, Textbox3):
                     print("Error: Image data is not available.")
                     return None
 
-            if "vision" in UserInput.lower():
-                vision()
-                return "yesssss"
+            if UserInput.lower() is not None:
+                caption = UserInput.lower()
+            else:
+                caption = ""
 
             image = cv.imdecode(np.frombuffer(image_data, np.uint8), cv.IMREAD_COLOR)
             image = cv.resize(image, (224, 224))
@@ -884,7 +885,10 @@ def classify(platform, UserInput, Images, Textbox2, Textbox3):
 
                 if max_rounded_prediction > 0.5:
                     print("\nWays to dispose of this waste: " + max_label)
-                    messages.append({"role": "user", "content": content + " " + max_label})
+                    if caption == None:
+                        messages.append({"role": "user", "content": content + " " + max_label})
+                    else:
+                        messages.append({"role": "user", "content": caption})
                     print("IMAGE messages after appending:", messages)
 
                     print("Message list of image:", messages)
@@ -913,13 +917,18 @@ def classify(platform, UserInput, Images, Textbox2, Textbox3):
                         # reply = response.choices[0].message['content']
                         print("RESPONSE TRY", completion)
 
-
-                        output.append({"Mode": "Image", "type": max_label, "prediction_value": max_rounded_prediction, "content": reply})
+                        if caption == None:
+                            output.append({"Mode": "Image", "type": max_label, "prediction_value": max_rounded_prediction, "content": reply})
+                        else:
+                            output.append({"Mode": "Image with Caption", "content": reply})
                     except:
                         print("DOESN'T WORK")
                         
                 elif max_rounded_prediction < 0.5:
-                    output.append({"Mode": "Image", "type": "Not predictable", "prediction_value": max_rounded_prediction, "content": "Seems like the prediction rate is too low due to that won't be able to predict the type of material. Try again with a cropped image or different one"})
+                    if caption == None:
+                        output.append({"Mode": "Image", "type": "Not predictable", "prediction_value": max_rounded_prediction, "content": "Seems like the prediction rate is too low due to that won't be able to predict the type of material. Try again with a cropped image or different one"})
+                    else:
+                        pass
 
             return output