Update app.py

made an update to fix runtime error

app.py

@@ -1,31 +1,25 @@
 import gradio as gr
-import pickle
 import pandas as pd
+from sentence_transformers import SentenceTransformer
 from sklearn.metrics.pairwise import cosine_similarity
 
-# Load model and dataset
-with open("recommender_model.pkl", "rb") as f:
-    model = pickle.load(f)
+# Load your trained SentenceTransformer model
+model = SentenceTransformer("all-MiniLM-L6-v2")  # Or use your custom model path if you trained a new one
 
-posts_df = pd.read_csv("posts_cleaned.csv")  # your full dataset with post content
-post_embeddings = model["embeddings"]  # precomputed post embeddings
-vectorizer = model["vectorizer"]      # for transforming user input
+# Load the posts
+posts = pd.read_csv("posts.csv")
 
-# Predict function
-def recommend_from_input(user_text):
-    user_vec = vectorizer.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)
+# Precompute embeddings for all posts
+post_texts = posts["post_text"].astype(str).tolist()
+post_embeddings = model.encode(post_texts, convert_to_tensor=False)
 
-# Gradio UI
-interface = gr.Interface(
-    fn=recommend_from_input,
-    inputs="text",
-    outputs="text",
-    title="AI Content Recommender",
-    description="Enter a sample interest or post to receive recommendations"
-)
+# Recommendation function
+def recommend(user_input):
+    user_embedding = model.encode([user_input], convert_to_tensor=False)
+    similarities = cosine_similarity(user_embedding, post_embeddings)[0]
+    top_indices = similarities.argsort()[-5:][::-1]
+    recommended = posts.iloc[top_indices]["post_text"].tolist()
+    return "\n\n".join(recommended)
 
-interface.launch()
+# Launch Gradio app
+gr.Interface(fn=recommend, inputs="text", outputs="text", title="AI Post Recommender").launch()