Update app.py

app.py

@@ -6,22 +6,15 @@ from pandasai.llm import OpenAI
 import tempfile
 import matplotlib.pyplot as plt
 from datasets import load_dataset
+from langchain_groq import ChatGroq
+from langchain_openai import ChatOpenAI
 
 # Load environment variables
 openai_api_key = os.getenv("OPENAI_API_KEY")
+groq_api_key = os.getenv("GROQ_API_KEY")
 
-# Ensure OpenAI API key is provided
-if not openai_api_key:
-    st.error("OpenAI API key is not set. Please add it to a .env file.")
-    st.stop()
-
-# Initialize the LLM
-#llm = OpenAI(api_token=openai_api_key)
-
+# Initialize the LLM based on user selection
 def initialize_llm(model_choice):
-    groq_api_key = os.getenv("GROQ_API_KEY")
-    openai_api_key = os.getenv("OPENAI_API_KEY")
-
     if model_choice == "llama-3.3-70b":
         if not groq_api_key:
             st.error("Groq API key is missing. Please set the GROQ_API_KEY environment variable.")
@@ -33,9 +26,9 @@ def initialize_llm(model_choice):
             return None
         return ChatOpenAI(api_key=openai_api_key, model="gpt-4o")
 
-model_choice = st.radio("Select LLM", ["GPT-4o", "llama-3.3-70b"], index=0, horizontal=True)
-llm = initialize_llm(model_choice)
-
+def validate_and_clean_dataset(dataframe):
+    # Placeholder for dataset validation and cleaning logic
+    return dataframe
 
 def load_dataset_into_session():
     input_option = st.radio(
@@ -49,6 +42,7 @@ def load_dataset_into_session():
         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}")
@@ -83,23 +77,27 @@ def load_dataset_into_session():
 
 st.title("Chat with Patent Dataset Using PandasAI")
 
-# Instructions
+# Push instructions to the sidebar
 with st.sidebar:
-    st.header("Instructions:")
+    st.header("Instructions")
     st.markdown(
         "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"
+        "3. Choose an LLM (Groq-based or OpenAI-based) to interact with the 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"
     )
 
+# Select LLM model
+model_choice = st.radio("Select LLM", ["GPT-4o", "llama-3.3-70b"], index=0, horizontal=True)
+llm = initialize_llm(model_choice)
+
 # Load dataset into session
 load_dataset_into_session()
 
-if "df" in st.session_state:
+if "df" in st.session_state and llm:
     df = st.session_state.df
     st.write("### Data Preview")
     st.dataframe(df.head(10))