Update app.py

app.py

@@ -1,55 +1,50 @@
 import gradio as gr
-from transformers import pipeline
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+import torch
 
-# 🔹 Load Qwen2.5-14B-Instruct-1M with a pipeline
-pipe = pipeline("text-generation", model="Qwen/Qwen2.5-14B-Instruct-1M")
+# 🔹 Load Llama 3 - 7B model
+model_name = "meta-llama/Meta-Llama-3-7B-Instruct"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
 
-# 🎯 Function to extract interests from user input
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, max_new_tokens=100)
+
+# 🎯 Extract interests from user input
 def extract_interests(text):
-    prompt = f"Extract 3-5 relevant interests from this request: '{text}'. Focus on hobbies and product preferences."
-    
-    response = pipe(prompt, max_length=50, num_return_sequences=1)
+    prompt = f"Extract 3-5 keywords from this: '{text}' (focus on hobbies & products)."
+    response = pipe(prompt)
     interests = response[0]["generated_text"].replace(prompt, "").strip()
-
     return interests.split(", ")
 
 # 🎁 Web search for gift suggestions
 def search_gifts(interests):
     query = "+".join(interests)
-    amazon_url = f"https://www.amazon.in/s?k={query}"
-    flipkart_url = f"https://www.flipkart.com/search?q={query}"
-    igp_url = f"https://www.igp.com/search?q={query}"
-    indiamart_url = f"https://dir.indiamart.com/search.mp?ss={query}"
-
     return {
-        "Amazon": amazon_url,
-        "Flipkart": flipkart_url,
-        "IGP": igp_url,
-        "IndiaMart": indiamart_url
+        "Amazon": f"https://www.amazon.in/s?k={query}",
+        "Flipkart": f"https://www.flipkart.com/search?q={query}",
+        "IGP": f"https://www.igp.com/search?q={query}",
+        "IndiaMart": f"https://dir.indiamart.com/search.mp?ss={query}",
     }
 
 # 🎯 Main function for gift recommendation
 def recommend_gifts(text):
     if not text:
         return "Please enter a description."
-
+    
     interests = extract_interests(text)
     links = search_gifts(interests)
 
-    return {
-        "Predicted Interests": interests,
-        "Gift Suggestions": links
-    }
+    return {"Predicted Interests": interests, "Gift Suggestions": links}
 
-# 🎨 Gradio UI for easy interaction
+# 🎨 Gradio UI
 demo = gr.Interface(
     fn=recommend_gifts, 
     inputs="text", 
     outputs="json",
-    title="🎁 AI Gift Recommender",
-    description="Enter details about the person you are buying a gift for, and get personalized suggestions with shopping links!",
+    title="🎁 AI Gift Recommender (Llama 3 - 7B)",
+    description="Enter details about the person and get personalized gift suggestions with shopping links!",
 )
 
 # 🚀 Launch Gradio App
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()