Update app.py

app.py

@@ -3,10 +3,31 @@ import numpy as np
 import gradio as gr
 import chromadb
 
-from transformers import AutoModel, AutoTokenizer, AutoModelForCausalLMpipeline
+from transformers import AutoModel, AutoTokenizer, pipeline
 import torch
 import chromadb
 
+import os
+
+# Ensure the token is set
+hf_token = os.getenv("HF_Token")
+
+if not hf_token:
+    raise ValueError("HF_Token is not set. Please check your Hugging Face Secrets.")
+
+# Load LLaMA-2 model with authentication
+llama_pipe = pipeline(
+    "text-generation",
+    model="meta-llama/Llama-2-7b-chat-hf",
+    token=hf_token  # Pass the token explicitly
+)
+
+# Test LLaMA-2 inference
+output = llama_pipe("What is machine learning?", max_length=100)
+print(output)
+
+
+'''
 # Initialize ChromaDB client
 chroma_client = chromadb.PersistentClient(path="./chroma_db")  # Stores data persistently
 collection = chroma_client.get_or_create_collection(name="wikipedia_docs")
@@ -85,4 +106,5 @@ iface = gr.Interface(
     description="Enter a query and retrieve relevant Wikipedia passages."
 )
 
-iface.launch()
+iface.launch()
+'''