Update app.py

app.py

@@ -3,9 +3,9 @@ import pandas as pd
 import os
 from pandasai import SmartDataframe
 from pandasai.llm import OpenAI
-from dotenv import load_dotenv
 import tempfile
 import matplotlib.pyplot as plt
+from datasets import load_dataset
 
 # Load environment variables
 openai_api_key = os.getenv("OPENAI_API_KEY")
@@ -18,30 +18,83 @@ if not openai_api_key:
 # Initialize the LLM
 llm = OpenAI(api_token=openai_api_key)
 
-st.title("Chat with CSV File Using PandasAI")
+def validate_and_clean_dataset(dataframe):
+    # Placeholder for dataset validation and cleaning logic
+    return dataframe
+
+def load_dataset_into_session():
+    input_option = st.radio(
+        "Select Dataset Input:",
+        ["Use Repo Directory Dataset", "Use Hugging Face Dataset", "Upload CSV File"],
+    )
+
+    # Option 1: Load dataset from the repo directory
+    if input_option == "Use Repo Directory Dataset":
+        file_path = "./source/test.csv"
+        if st.button("Load Dataset"):
+            try:
+                st.session_state.df = pd.read_csv(file_path)
+                st.session_state.df = validate_and_clean_dataset(st.session_state.df)
+                st.success(f"File loaded successfully from '{file_path}'!")
+            except Exception as e:
+                st.error(f"Error loading dataset from the repo directory: {e}")
+
+    # Option 2: Load dataset from Hugging Face
+    elif input_option == "Use Hugging Face Dataset":
+        dataset_name = st.text_input(
+            "Enter Hugging Face Dataset Name:", value="HUPD/hupd"
+        )
+        if st.button("Load Hugging Face Dataset"):
+            try:
+                dataset = load_dataset(dataset_name, split="train", trust_remote_code=True)
+                if hasattr(dataset, "to_pandas"):
+                    st.session_state.df = dataset.to_pandas()
+                else:
+                    st.session_state.df = pd.DataFrame(dataset)
+                st.session_state.df = validate_and_clean_dataset(st.session_state.df)
+                st.success(f"Hugging Face Dataset '{dataset_name}' loaded successfully!")
+            except Exception as e:
+                st.error(f"Error loading Hugging Face dataset: {e}")
+
+    # Option 3: Upload CSV File
+    elif input_option == "Upload CSV File":
+        uploaded_file = st.file_uploader("Upload a CSV File:", type=["csv"])
+        if uploaded_file:
+            try:
+                st.session_state.df = pd.read_csv(uploaded_file)
+                st.session_state.df = validate_and_clean_dataset(st.session_state.df)
+                st.success("File uploaded successfully!")
+            except Exception as e:
+                st.error(f"Error reading uploaded file: {e}")
+
+st.title("Chat with Patent Dataset Using PandasAI")
 
 # Instructions
 with st.sidebar:
-    st.header("Instructions")
+    st.header("Instructions:")
     st.markdown(
-        "1. Upload a CSV file to get started.\n"
-        "2. Enter a question to interact with the data.\n"
-        "3. Enter a query to generate and view graphs.\n"
+        "1. Select how you want to input the dataset.\n"
+        "2. Upload, select, or fetch the dataset using the provided options.\n"
+        "3. Enter a question to interact with the patent data.\n"
+        "   - Example: 'Predict if the patent will be accepted.'\n"
+        "   - Example: 'What is the primary classification of this patent?'\n"
+        "   - Example: 'Summarize the abstract of this patent.'\n"
+        "4. Enter a query to generate and view graphs based on patent attributes.\n"
     )
 
-uploaded_file = st.file_uploader("Upload a CSV file", type="csv")
+# Load dataset into session
+load_dataset_into_session()
 
-if uploaded_file:
-    # Read the CSV file
-    df = pd.read_csv(uploaded_file)
+if "df" in st.session_state:
+    df = st.session_state.df
     st.write("### Data Preview")
     st.dataframe(df.head(10))
 
     # Create SmartDataFrame
     chat_df = SmartDataframe(df, config={"llm": llm})
 
-    st.write("### Chat with Your Data")
-    user_query = st.text_input("Enter your question about the data:")
+    st.write("### Chat with Your Patent Data")
+    user_query = st.text_input("Enter your question about the patent data (e.g., 'Predict if the patent will be accepted.'):")
 
     if user_query:
         try:
@@ -51,7 +104,7 @@ if uploaded_file:
             st.error(f"Error: {e}")
 
     st.write("### Generate and View Graphs")
-    plot_query = st.text_input("Enter a query to generate a graph (e.g., 'Can you plot me a bar graph of total weekly sales for each store?'):")
+    plot_query = st.text_input("Enter a query to generate a graph (e.g., 'Plot the number of patents by filing year.'):")
 
     if plot_query:
         try: