Update app.py

app.py

@@ -1,40 +1,44 @@
+
 import pandas as pd
 import numpy as np
 import faiss
 import gradio as gr
 from sentence_transformers import SentenceTransformer
 
-# Load the CSV file with embeddings
-csv_path = 'df_after_rec_embedding.csv'  # Update with your actual CSV path
-df = pd.read_csv(csv_path)
-data = df.to_numpy().astype('float32')
+# Load the embeddings from the embeddings CSV file
+embeddings_csv_path = 'df_after_rec_embedding.csv'  # Path to the embeddings CSV
+embeddings = pd.read_csv(embeddings_csv_path).to_numpy().astype('float32')
+
+# Load the content from the content CSV file
+content_csv_path = 'content.csv'  # Path to the content CSV
+content_df = pd.read_csv(content_csv_path)  # Load the entire content DataFrame
+content_column = content_df['2'].tolist()  # Extract the content from column '2'
 
 # Create a FAISS index
-dimension = data.shape[1]
+dimension = embeddings.shape[1]
 index = faiss.IndexFlatL2(dimension)  # L2 distance metric
-index.add(data)  # Add data to the index
+index.add(embeddings)  # Add embeddings to the index
 
 # Load the nomic-ai/nomic-embed-text-v1 model
-model = SentenceTransformer('nomic-ai/nomic-embed-text-v1',device='cpu', trust_remote_code=True)
-
+model = SentenceTransformer('nomic-ai/nomic-embed-text-v1', trust_remote_code=True)
 
 # Function to embed query and search using FAISS
 def search(query):
     # Embed the query using the model
     query_vector = model.encode([query])[0].astype('float32')
-
+    
     # Search the FAISS index
-    distances, indices = index.search(np.array([query_vector]), k=1)  # Search for top 5 closest vectors
-
-    # Return results with indices and distances
-    return [f"Index: {i}, Distance: {d:.4f}" for i, d in zip(indices[0], distances[0])]
-
+    distances, indices = index.search(np.array([query_vector]), k=5)  # Search for top 5 closest vectors
+    
+    # Return corresponding content for the top results using the indices
+    results = [f"Content: {content_column[i]}\nDistance: {d:.4f}" for i, d in zip(indices[0], distances[0])]
+    return "\n\n".join(results)
 
 # Create the Gradio interface
 def gradio_app():
     with gr.Blocks() as demo:
         gr.Markdown("## FAISS Search Interface with Nomic Embedder")
-
+        
         with gr.Row():
             with gr.Column():
                 query_input = gr.Textbox(
@@ -42,19 +46,18 @@ def gradio_app():
                     placeholder="Type your search query here"
                 )
                 search_button = gr.Button("Search")
-
+            
             with gr.Column():
-                search_results = gr.Textbox(label="Search Results")
-
+                search_results = gr.Textbox(label="Search Results", lines=10)
+        
         search_button.click(
             fn=search,
             inputs=[query_input],
             outputs=[search_results]
         )
-
+        
     return demo
 
-
 # Launch the Gradio app
 demo = gradio_app()
 demo.launch()