Update app.py

app.py

@@ -0,0 +1,50 @@
+import pandas as pd
+import gradio as gr
+from datetime import datetime
+from sentence_transformers import SentenceTransformer
+from sklearn.metrics.pairwise import cosine_similarity
+
+# Load dataset (ensure the file is in the same directory)
+df = pd.read_csv("analytics_vidhya_articles.csv", parse_dates=["Date"])
+
+# Combine Title and Description for similarity search
+df["combined_text"] = df["Title"].astype(str) + " " + df["Description"].astype(str)
+
+# Load sentence transformer model
+model = SentenceTransformer("all-MiniLM-L6-v2")
+
+# Function to retrieve top-N records
+def retrieve_records(query, min_date, top_n):
+    # Filter by date
+    filtered_df = df[df["Date"] >= pd.to_datetime(min_date)]
+
+    if filtered_df.empty or not query.strip():
+        return pd.DataFrame(columns=["Title", "Description", "Date", "Link"])
+
+    # Compute embeddings
+    text_embeddings = model.encode(filtered_df["combined_text"].tolist(), convert_to_tensor=False)
+    query_embedding = model.encode([query], convert_to_tensor=False)
+
+    # Compute cosine similarity
+    scores = cosine_similarity([query_embedding], text_embeddings)[0]
+    filtered_df = filtered_df.copy()
+    filtered_df["similarity"] = scores
+
+    # Return top-N results
+    top_results = filtered_df.sort_values(by="similarity", ascending=False).head(top_n)
+    return top_results[["Title", "Description", "Date", "Link"]]
+
+# Gradio interface
+iface = gr.Interface(
+    fn=retrieve_records,
+    inputs=[
+        gr.Textbox(label="Enter your query"),
+        gr.Textbox(label="Minimum date (YYYY-MM-DD)", value=str(datetime.today().date())),
+        gr.Slider(5, 15, value=5, step=5, label="Top N results")
+    ],
+    outputs=gr.Dataframe(label="Top Similar Records"),
+    title="Top-N Article Retriever",
+    description="Search articles using Title and Description similarity, filtered by a minimum date."
+)
+
+iface.launch()