Update app.py

app.py

@@ -4,14 +4,14 @@ import numpy as np
 from sklearn.metrics.pairwise import cosine_similarity
 from sentence_transformers import SentenceTransformer
 
-# ✅ Correct way to load the model
-model = SentenceTransformer("all-MiniLM-L6-v2")  # Replace with your model name/path
+# ✅ Load the model
+model = SentenceTransformer("all-MiniLM-L6-v2")
 
-# Load posts dataset
-posts_df = pd.read_csv("posts_cleaned.csv")  
+# ✅ Load posts dataset
+posts_df = pd.read_csv("posts_cleaned.csv")
 post_texts = posts_df["post_text"].astype(str).tolist()
 
-# Cache embeddings
+# ✅ Cache embeddings
 post_embeddings = None
 
 def get_embeddings():
@@ -21,21 +21,25 @@ def get_embeddings():
         post_embeddings = model.encode(post_texts, convert_to_tensor=False)
     return post_embeddings
 
-def recommend_from_input(user_text):
+# ✅ Main recommender logic with JSON output
+def recommend_json(user_text):
     if not user_text.strip():
-        return []
+        return { "data": [[]] }
     
     embeddings = get_embeddings()
     user_vec = model.encode([user_text])
     sims = cosine_similarity(user_vec, embeddings)[0]
     top_idxs = sims.argsort()[-5:][::-1]
-    return posts_df.iloc[top_idxs]["post_text"].tolist()
+    recommendations = posts_df.iloc[top_idxs]["post_text"].tolist()
+    
+    return { "data": [recommendations] }
 
+# ✅ Gradio JSON interface
 interface = gr.Interface(
-    fn=recommend_from_input,
+    fn=recommend_json,
     inputs=gr.Textbox(label="What are you interested in?"),
-    outputs=gr.Dataframe(headers=["Recommended Posts"]),
-    title="🔍 AI Content Recommender"
+    outputs=gr.JSON(label="Structured Recommendations"),
+    title="🔍 AI Content Recommender (API Mode)"
 )
 
-interface.launch(share=False)
+interface.launch()