Spaces:
Running
Running
| import streamlit as st | |
| import pandas as pd | |
| import os | |
| from datetime import datetime | |
| import google.generativeai as genai | |
| # Configure Gemini | |
| GEMINI_API_KEY = os.environ.get('GEMINI_API_KEY') | |
| genai.configure(api_key=GEMINI_API_KEY) | |
| model = genai.GenerativeModel('gemini-pro') | |
| class GeminiDataChatbot: | |
| def __init__(self): | |
| if 'uploaded_df' not in st.session_state: | |
| st.session_state.uploaded_df = None | |
| if 'chat_history' not in st.session_state: | |
| st.session_state.chat_history = [] | |
| def render_interface(self): | |
| st.title("📊 Data Analysis Chatbot") | |
| st.write("Upload your CSV file and ask questions about your data") | |
| # File upload section | |
| uploaded_file = st.file_uploader("Choose a CSV file", type="csv") | |
| if uploaded_file is not None: | |
| self._process_uploaded_file(uploaded_file) | |
| # Chat interface | |
| if st.session_state.uploaded_df is not None: | |
| self._render_chat_window() | |
| def _process_uploaded_file(self, uploaded_file): | |
| try: | |
| df = pd.read_csv(uploaded_file) | |
| st.session_state.uploaded_df = df | |
| st.success("Data successfully loaded!") | |
| with st.expander("View Data Preview"): | |
| st.dataframe(df.head()) | |
| # Initial analysis prompt | |
| initial_prompt = f""" | |
| I have uploaded a dataset with {len(df)} rows and {len(df.columns)} columns. | |
| Columns: {', '.join(df.columns)}. | |
| First give a very brief (2-3 sentence) overview of what this data might contain. | |
| Then suggest 3 specific questions I could ask about this data. | |
| """ | |
| with st.spinner("Analyzing your data..."): | |
| response = self._generate_gemini_response(initial_prompt, df) | |
| st.session_state.chat_history.append({ | |
| "role": "assistant", | |
| "content": response | |
| }) | |
| except Exception as e: | |
| st.error(f"Error processing file: {str(e)}") | |
| def _render_chat_window(self): | |
| st.subheader("Chat About Your Data") | |
| # Display chat history | |
| for message in st.session_state.chat_history: | |
| with st.chat_message(message["role"]): | |
| st.markdown(message["content"]) | |
| # User input | |
| if prompt := st.chat_input("Ask about your data..."): | |
| # Add user message to chat history | |
| st.session_state.chat_history.append({"role": "user", "content": prompt}) | |
| # Display user message | |
| with st.chat_message("user"): | |
| st.markdown(prompt) | |
| # Generate and display assistant response | |
| with st.chat_message("assistant"): | |
| with st.spinner("Thinking..."): | |
| response = self._generate_gemini_response(prompt, st.session_state.uploaded_df) | |
| st.markdown(response) | |
| # Add assistant response to chat history | |
| st.session_state.chat_history.append({"role": "assistant", "content": response}) | |
| def _generate_gemini_response(self, prompt: str, df: pd.DataFrame) -> str: | |
| """Generate response using Gemini API with data context""" | |
| try: | |
| # Create data summary for context | |
| data_summary = f""" | |
| Data Summary: | |
| - Shape: {df.shape} | |
| - Columns: {', '.join(df.columns)} | |
| - First 5 rows: | |
| {df.head().to_markdown()} | |
| """ | |
| # Create prompt with context | |
| full_prompt = f""" | |
| You are a data analysis assistant. The user has uploaded a dataset with the following characteristics: | |
| {data_summary} | |
| User Question: {prompt} | |
| Provide a detailed response answering their question about the data. If appropriate, include: | |
| - Relevant statistics | |
| - Potential visualizations that would help | |
| - Any data quality issues to consider | |
| - Business insights if applicable | |
| """ | |
| response = model.generate_content(full_prompt) | |
| return response.text | |
| except Exception as e: | |
| return f"Sorry, I encountered an error processing your request: {str(e)}" | |
| # Initialize and run the chatbot | |
| if __name__ == "__main__": | |
| chatbot = GeminiDataChatbot() | |
| chatbot.render_interface() |