Update app.py

app.py

@@ -1,6 +1,44 @@
+# Gradio Interface
+import gradio as gr
 import numpy as np
 import pandas as pd
 from sklearn.metrics.pairwise import cosine_similarity
+from sentence_transformers import SentenceTransformer
+import requests
+from PIL import Image
+from transformers import BlipProcessor, BlipForConditionalGeneration
+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(image=None, text=None, model):
+    # If an image is provided
+    if 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!="No text provided.":
+        # 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."
+    
+    vector_search(input, model)
 
 # Load embeddings and metadata
 embeddings = np.load("netflix_embeddings.npy")  #created using sentence_transformers on kaggle
@@ -17,23 +55,28 @@ def vector_search(query, model):
     # Format results for display
     result_text = "\n".join(f"Title: {row['title']}, Description: {row['description']}, Genre: {row['listed_in']}" for _, row in results.iterrows())
     return result_text
-
-# Gradio Interface
-import gradio as gr
-from sentence_transformers import SentenceTransformer
-
-model = SentenceTransformer("all-MiniLM-L6-v2")
 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.")
-    query = gr.Textbox(label="Enter your query")
-    output = gr.Textbox(label="Recommendations")
-    submit_button = gr.Button("Submit")
+    with gr.Row():
+        image_input = gr.Image(label="Upload Image", type="pil")  # Image input
+        text_input = gr.Textbox(label="Enter Text Query", placeholder="Enter a description or query here")  # Text input
     
-    submit_button.click(fn=lambda q: vector_search(q, model), inputs=query, outputs=output)
+    submit_button = gr.Button("Submit")
+    output = gr.Textbox(label="Recommendations")
+
+    submit_button.click(fn=generate_output, inputs=[image_input, text_input, sentence_model], outputs=output)
 
 demo.launch()
 
+# 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.")
+#     query = gr.Textbox(label="Enter your query")
+#     output = gr.Textbox(label="Recommendations")
+#     submit_button = gr.Button("Submit")
+    
+#     submit_button.click(fn=lambda q: vector_search(q, model), inputs=query, outputs=output)
 # import gradio as gr
 
 # # def greet(name):