Update app.py

app.py

@@ -12,14 +12,26 @@ from langchain.llms import HuggingFacePipeline
 
 # Initialize conversation history
 if 'history' not in st.session_state:
-    st.session_state.history = []
+    st.session_state['history'] = []
 
 # Set up the Llama-2-7b-chat-hf model
 model_id = "meta-llama/Llama-2-7b-chat-hf"
 
-# Load the tokenizer and model
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id, device_map='auto', torch_dtype='auto')  # Adjust device_map and torch_dtype as needed
+# Get your Hugging Face token (it's stored as a secret in your Space)
+hf_token = os.environ.get("HUGGINGFACEHUB_API_TOKEN")
+
+if hf_token is None:
+    st.error("Hugging Face API token is not set. Please set the HUGGINGFACEHUB_API_TOKEN secret in your Space.")
+    st.stop()
+
+# Load the tokenizer and model with the token
+tokenizer = AutoTokenizer.from_pretrained(model_id, use_auth_token=hf_token)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    use_auth_token=hf_token,
+    device_map='auto',
+    torch_dtype='auto'  # Adjust based on your environment
+)
 
 # Create the text-generation pipeline with appropriate parameters
 pipe = pipeline(
@@ -37,6 +49,9 @@ pipe = pipeline(
 # Wrap the pipeline with HuggingFacePipeline for use in LangChain
 llm = HuggingFacePipeline(pipeline=pipe)
 
+# ... rest of your code ...
+
+
 # Step 1: Upload CSV data file (or use default)
 st.title("Natural Language to SQL Query App with Enhanced Insights")
 st.write("Upload a CSV file to get started, or use the default dataset.")