Update app.py

app.py

@@ -1,34 +1,36 @@
 import gradio as gr
 import pickle
 import pandas as pd
+import numpy as np
 from sklearn.metrics.pairwise import cosine_similarity
-from sklearn.metrics.pairwise import cosine_similarity
-
-# Load model and dataset
-with open("recommender_model.pkl", "rb") as f:
-    model = pickle.load(f)
 
-posts_df = pd.read_csv("posts_cleaned.csv")  # your full dataset with post content
-post_texts = posts["post_text"].astype(str).tolist()
-post_embeddings = model.encode(post_texts, convert_to_tensor=False)
-  # precomputed post embeddings
-vectorizer = model["vectorizer"]      # for transforming user input
+# Load model and data with error handling
+try:
+    with open("recommender_model.pkl", "rb") as f:
+        model = pickle.load(f)
+    posts_df = pd.read_csv("posts_cleaned.csv")
+    post_texts = posts_df["post_text"].astype(str).tolist()
+    post_embeddings = np.load("post_embeddings.npy")  # Precomputed
+except Exception as e:
+    raise gr.Error(f"Error loading files: {str(e)}")
 
 # Predict function
 def recommend_from_input(user_text):
-    user_vec = vectorizer.encode([user_text])
+    if not user_text.strip():
+        return "Please enter valid text."
+    user_vec = model.encode([user_text])
     sims = cosine_similarity(user_vec, post_embeddings)[0]
-    top_idxs = sims.argsort()[-5:][::-1]
-    top_posts = posts_df.iloc[top_idxs]["post_text"].tolist()
-    return "\n\n".join(top_posts)
+    top_idxs = sims.argsort()[-5:][::-1]  # Top 5 posts
+    return posts_df.iloc[top_idxs]["post_text"].tolist()
 
 # Gradio UI
 interface = gr.Interface(
     fn=recommend_from_input,
-    inputs="text",
-    outputs="text",
+    inputs=gr.Textbox(label="Describe your interests"),
+    outputs=gr.Dataframe(headers=["Recommended Posts"]),
     title="AI Content Recommender",
-    description="Enter a sample interest or post to receive recommendations"
+    description="Enter a topic or post to get recommendations",
+    examples=[["Web3 security"], ["Machine learning trends"]]
 )
 
-interface.launch()
+interface.launch()