Create app.py

app.py

@@ -0,0 +1,80 @@
+from transformers import pipeline
+import streamlit as st
+from PIL import Image
+import requests
+from io import BytesIO
+from sentence_transformers import SentenceTransformer
+import numpy as np
+import faiss
+import pandas as pd
+
+# Initialize the image-to-text pipeline
+image_to_text = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning")
+
+# Initialize the sentence transformer model for embeddings
+sentence_model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')
+
+# Function to load images from URL
+def load_image_from_url(url):
+    try:
+        response = requests.get(url)
+        img = Image.open(BytesIO(response.content))
+        return img
+    except Exception as e:
+        st.error(f"Error loading image from URL: {e}")
+        return None
+
+# Load the dataset and create FAISS index
+def load_dataset_and_create_index():
+    df = pd.read_csv('/path/to/your/amazon_reviews.csv')
+    review_texts = df['reviewText'].dropna().tolist()
+    review_embeddings = sentence_model.encode(review_texts)
+    dimension = review_embeddings.shape[1]
+    faiss_index = faiss.IndexFlatL2(dimension)
+    faiss_index.add(np.array(review_embeddings))
+    return faiss_index, review_texts
+
+faiss_index, review_texts = load_dataset_and_create_index()
+
+# Find top N similar reviews
+def find_top_n_similar_reviews(query, faiss_index, review_texts, top_n=3):
+    query_embedding = sentence_model.encode([query])
+    _, indices = faiss_index.search(query_embedding, top_n)
+    return [review_texts[i] for i in indices[0]]
+
+st.title('Image Captioning and Review Visualization Application')
+
+input_type = st.radio("Select input type:", ("Upload Image", "Image URL", "Text"))
+
+image = None
+text_input = ""
+
+if input_type == "Upload Image":
+    uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
+    if uploaded_file is not None:
+        image = Image.open(uploaded_file)
+        st.image(image, caption='Uploaded Image', use_column_width=True)
+elif input_type == "Image URL":
+    image_url = st.text_input("Enter the image URL here:", "")
+    if image_url:
+        image = load_image_from_url(image_url)
+elif input_type == "Text":
+    text_input = st.text_area("Enter text here:", "")
+
+if st.button('Generate Caption'):
+    result_text = ""
+    if input_type in ["Upload Image", "Image URL"] and image:
+        with st.spinner("Generating caption..."):
+            result = image_to_text(image_url if input_type == "Image URL" else uploaded_file)
+            result_text = result[0]['generated_text'] if result else "Failed to generate caption."
+    elif input_type == "Text" and text_input:
+        result_text = text_input
+
+    if result_text:
+        st.success(f'Generated Caption: {result_text}')
+        similar_reviews = find_top_n_similar_reviews(result_text, faiss_index, review_texts)
+        st.write("Similar Reviews Based on the Caption:")
+        for review in similar_reviews:
+            st.write(review)
+    else:
+        st.error("Please provide input.")