Update app.py

app.py

@@ -3,12 +3,16 @@ import pandas as pd
 import json
 import os
 import plotly.express as px
-from transformers import pipeline
-from datasets import Dataset
 from transformers import RagTokenizer, RagRetriever, RagSequenceForGeneration
+from datasets import Dataset
 
-# Load the LLaMA-based model with RAG
-@st.cache(allow_output_mutation=True)
+# Set paths to the default files
+DEFAULT_PROMPT_PATH = "default_prompt.json"
+DEFAULT_METADATA_PATH = "default_metadata.csv"
+DEFAULT_DATA_PATH = "default_data.csv"
+
+# Load the RAG model with LLaMA-based retrieval-augmented generation
+@st.cache_resource(allow_output_mutation=True)
 def load_rag_model():
     retriever = RagRetriever.from_pretrained("facebook/rag-token-base", index_name="custom")
     tokenizer = RagTokenizer.from_pretrained("facebook/rag-token-base")
@@ -17,30 +21,47 @@ def load_rag_model():
 
 model, tokenizer, retriever = load_rag_model()
 
-# Title of the app
+# Title for the app
 st.title("Interactive Insights Chatbot with LLaMA + RAG")
 
-# Step 1: Upload prompt.json file
+# Step 1: Upload prompt.json file (or use default)
 prompt_file = st.file_uploader("Upload your prompt.json file", type=["json"])
-if prompt_file:
+if prompt_file is None:
+    with open(DEFAULT_PROMPT_PATH) as f:
+        prompt_data = json.load(f)
+        st.write("Using default prompt.json file.")
+else:
     prompt_data = json.load(prompt_file)
     st.write("Prompt JSON loaded successfully!")
 
-# Step 2: Upload CSV file
+# Step 2: Upload metadata.csv file (or use default)
+metadata_file = st.file_uploader("Upload your metadata.csv file", type=["csv"])
+if metadata_file is None:
+    metadata = pd.read_csv(DEFAULT_METADATA_PATH)
+    st.write("Using default metadata.csv file.")
+else:
+    metadata = pd.read_csv(metadata_file)
+    st.write("Metadata loaded successfully!")
+    st.dataframe(metadata)
+
+# Step 3: Upload CSV data file (or use default)
 csv_file = st.file_uploader("Upload your CSV file", type=["csv"])
-if csv_file:
+if csv_file is None:
+    data = pd.read_csv(DEFAULT_DATA_PATH)
+    st.write("Using default data.csv file.")
+else:
     data = pd.read_csv(csv_file)
     st.write("Data Preview:")
     st.dataframe(data.head())
 
-    # Convert the CSV data to a Hugging Face Dataset for retrieval
-    dataset = Dataset.from_pandas(data)
+# Convert the CSV data to a Hugging Face Dataset for retrieval
+dataset = Dataset.from_pandas(data)
 
-# Step 3: Natural language prompt input
+# Step 4: Natural language prompt input
 user_prompt = st.text_input("Enter your natural language prompt:")
 
-# Step 4: Process the user prompt and generate insights using LLaMA + RAG
-if user_prompt and csv_file:
+# Step 5: Process the prompt and generate insights using LLaMA + RAG
+if user_prompt and data is not None:
     st.write(f"Processing your prompt: '{user_prompt}'")
 
     # Tokenize the prompt for LLaMA + RAG
@@ -56,7 +77,7 @@ if user_prompt and csv_file:
 
     # Example: if the prompt asks for a plot (like "show sales over time")
     if "plot sales" in user_prompt.lower():
-        # Create a bar chart (you can customize based on the prompt)
+        # Create an interactive bar chart
         fig = px.bar(data, x='Date', y='Sales', title="Sales Over Time")
         st.plotly_chart(fig)
     else: