Update app.py

app.py

@@ -12,33 +12,33 @@ sentence_model = SentenceTransformer("all-MiniLM-L6-v2")
 processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
 image_model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")
 
-def generate_input(model, image=None, text=None):
-    # If an image is provided
-    if image:
+def generate_input(input_type, image=None, text=None):
+    # Initialize the input variable
+    combined_input = ""
+
+    # Handle image input if chosen
+    if input_type == "Image" and image:
         inputs = processor(images=image, return_tensors="pt")
         out = image_model.generate(**inputs)
         image_caption = processor.decode(out[0], skip_special_tokens=True)
-    else:
-        image_caption = None
-
-    # If text is provided, you can process it accordingly
-    if text:
-        text_input = text
-    else:
-        text_input = "No text provided."
-
-    # Combine image caption and text output
-    if image_caption and text:
-        # input = f"Image Caption: {image_caption}\nText Query: {text_output}"
-        input = image_caption+" "+text_input
-    elif image_caption:
-        input = image_caption
-    elif text:
-        input = text_input
-    else:
-        input = "No input provided."
+        combined_input += image_caption  # Add the image caption to input
+
+    # Handle text input if chosen
+    elif input_type == "Text" and text:
+        combined_input += text  # Add the text to input
+
+    # Handle both text and image input if chosen
+    elif input_type == "Both" and image and text:
+        inputs = processor(images=image, return_tensors="pt")
+        out = image_model.generate(**inputs)
+        image_caption = processor.decode(out[0], skip_special_tokens=True)
+        combined_input += image_caption + " " + text  # Combine image caption and text
     
-    return vector_search(input)
+    # If no input, fallback
+    if not combined_input:
+        combined_input = "No input provided."
+
+    return vector_search(combined_input)
 
 # Load embeddings and metadata
 embeddings = np.load("netflix_embeddings.npy")  #created using sentence_transformers on kaggle
@@ -59,13 +59,14 @@ with gr.Blocks() as demo:
     gr.Markdown("# Netflix Recommendation System")
     gr.Markdown("Enter a query to receive Netflix show recommendations based on title, description, and genre.")
     with gr.Row():
+        input_choice = gr.Radio(choices=["Image", "Text", "Both"], label="Select Input Type", value="Both")
         image_input = gr.Image(label="Upload Image", type="pil", optional=True)  # Image input
         text_input = gr.Textbox(label="Enter Text Query", placeholder="Enter a description or query here", optional=True)  # Text input
     
     submit_button = gr.Button("Submit")
     output = gr.Textbox(label="Recommendations")
 
-    submit_button.click(fn=generate_input, inputs=[image_input, text_input], outputs=output)
+    submit_button.click(fn=generate_input, inputs=[input_choice,image_input, text_input], outputs=output)
 
 demo.launch()