Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| import pandas as pd | |
| from pandasai import SmartDataframe | |
| from pandasai.llm import OpenAI, ChatGroq | |
| from dotenv import load_dotenv | |
| from datasets import load_dataset | |
| import os | |
| # Load environment variables | |
| load_dotenv() | |
| def initialize_llm(model_choice): | |
| """Initialize the chosen LLM based on the user's selection.""" | |
| 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.") | |
| return None | |
| return ChatGroq(groq_api_key=groq_api_key, model="groq/llama-3.3-70b-versatile") | |
| elif model_choice == "GPT-4o": | |
| if not openai_api_key: | |
| st.error("OpenAI API key is missing. Please set the OPENAI_API_KEY environment variable.") | |
| return None | |
| return OpenAI(api_token=openai_api_key) | |
| # App title and description | |
| st.title("Patent Analytics: Chat With Your Dataset") | |
| st.markdown( | |
| """ | |
| Upload a CSV file or load a dataset from Hugging Face to: | |
| - Analyze data with natural language queries. | |
| - Visualize trends and insights (e.g., "Plot the number of patents filed per year"). | |
| """ | |
| ) | |
| # Initialize session state for the dataframe | |
| if "df" not in st.session_state: | |
| st.session_state.df = None | |
| # Select the model | |
| model_choice = st.radio("Select LLM", ["GPT-4o", "llama-3.3-70b"], index=0, horizontal=True) | |
| llm = initialize_llm(model_choice) | |
| if not llm: | |
| st.stop() | |
| def load_dataset_into_session(): | |
| """Load dataset based on user input.""" | |
| input_option = st.radio("Choose Dataset Input Method", ["Use Hugging Face Dataset", "Upload CSV File"], index=0) | |
| if input_option == "Use Hugging Face Dataset": | |
| dataset_name = st.text_input("Enter Hugging Face Dataset Name:", value="HUPD/hupd") | |
| if st.button("Load Dataset"): | |
| try: | |
| dataset = load_dataset(dataset_name, split="train", trust_remote_code=True) | |
| st.session_state.df = pd.DataFrame(dataset) | |
| st.success(f"Dataset '{dataset_name}' loaded successfully!") | |
| except Exception as e: | |
| st.error(f"Error loading dataset: {e}") | |
| elif input_option == "Upload CSV File": | |
| uploaded_file = st.file_uploader("Upload CSV File:", type=["csv"]) | |
| if uploaded_file: | |
| try: | |
| st.session_state.df = pd.read_csv(uploaded_file) | |
| st.success("File uploaded successfully!") | |
| except Exception as e: | |
| st.error(f"Error loading file: {e}") | |
| # Load dataset | |
| load_dataset_into_session() | |
| # Show the loaded dataframe preview | |
| if st.session_state.df is not None: | |
| st.subheader("Dataset Preview") | |
| st.dataframe(st.session_state.df.head(10)) | |
| # Create a SmartDataFrame for PandasAI | |
| chat_df = SmartDataframe(st.session_state.df, config={"llm": llm}) | |
| # Input box for user questions | |
| question = st.text_input( | |
| "Ask a question about your data or request a visualization", | |
| placeholder="E.g., 'Which assignee has the most patents?' or 'Plot patent filings per year'", | |
| ) | |
| if question: | |
| with st.spinner("Processing your request..."): | |
| try: | |
| # Chat with the dataframe | |
| response = chat_df.chat(question) | |
| # Display response | |
| if isinstance(response, pd.DataFrame): | |
| st.write("### Response") | |
| st.dataframe(response) | |
| else: | |
| st.write("### Response") | |
| st.write(response) | |
| st.success("Request processed successfully!") | |
| except Exception as e: | |
| st.error(f"An error occurred: {e}") | |
| else: | |
| st.write("Upload a CSV file or load a dataset to get started.") |