app3.py

import streamlit as st
import pandas as pd
import plotly.express as px
from pandasai import Agent
from langchain_community.embeddings.openai import OpenAIEmbeddings
from langchain_community.vectorstores import FAISS
from langchain_openai import ChatOpenAI
from langchain.chains import RetrievalQA
from langchain.schema import Document
import os

# Set the title of the app
st.title("Data Analyzer")

# Fetch API keys from environment variables
api_key = os.getenv("OPENAI_API_KEY")
pandasai_api_key = os.getenv("PANDASAI_API_KEY")

if not api_key or not pandasai_api_key:
    st.error(
        "API keys not found in the environment. Please set the 'OPENAI_API_KEY' and 'PANDASAI_API_KEY' environment variables."
    )
else:
    # File uploader
    uploaded_file = st.file_uploader("Upload an Excel or CSV file", type=["xlsx", "csv"])

    if uploaded_file is not None:
        # Load the data
        if uploaded_file.name.endswith('.xlsx'):
            df = pd.read_excel(uploaded_file)
        else:
            df = pd.read_csv(uploaded_file)

        st.write("Data Preview:")
        st.write(df.head())

        # Set up PandasAI Agent
        agent = Agent(df)

        # Convert the DataFrame into documents
        documents = [
            Document(
                page_content=", ".join([f"{col}: {row[col]}" for col in df.columns]),
                metadata={"index": index}
            )
            for index, row in df.iterrows()
        ]

        # Set up RAG
        embeddings = OpenAIEmbeddings()
        vectorstore = FAISS.from_documents(documents, embeddings)
        retriever = vectorstore.as_retriever()
        qa_chain = RetrievalQA.from_chain_type(
            llm=ChatOpenAI(),
            chain_type="stuff",
            retriever=retriever
        )

        # Create tabs
        tab1, tab2, tab3 = st.tabs(["PandasAI Analysis", "RAG Q&A", "Data Visualization"])

        with tab1:
            st.header("Data Analysis using PandasAI")
            pandas_question = st.text_input("Ask a question about the data (PandasAI):")
            if pandas_question:
                result = agent.chat(pandas_question)
                st.write("PandasAI Answer:", result)

        with tab2:
            st.header("Question Answering using RAG")
            rag_question = st.text_input("Ask a question about the data (RAG):")
            if rag_question:
                result = qa_chain.run(rag_question)
                st.write("RAG Answer:", result)

        with tab3:
            st.header("Data Visualization")
            viz_question = st.text_input("What kind of graph would you like to create? (e.g., 'Show a scatter plot of salary vs experience')")
            
            if viz_question:
                try:
                    result = agent.chat(viz_question)
                    
                    # Since PandasAI output is text, extract executable code
                    import re
                    code_pattern = r'```python\n(.*?)\n```'
                    code_match = re.search(code_pattern, result, re.DOTALL)
                    
                    if code_match:
                        viz_code = code_match.group(1)
                        # Modify code to use Plotly (px) instead of matplotlib (plt)
                        viz_code = viz_code.replace('plt.', 'px.')
                        viz_code = viz_code.replace('plt.show()', 'fig = px.scatter(df, x=x, y=y)')
                        
                        # Execute the code and display the chart
                        exec(viz_code)
                        st.plotly_chart(fig)
                    else:
                        st.write("Unable to generate a graph. Please try a different query.")
                except Exception as e:
                    st.write(f"An error occurred: {str(e)}")
                    st.write("Please try phrasing your query differently.")
    else:
        st.info("Please upload a file to begin analysis.")