Spaces:
Runtime error
Runtime error
| import time | |
| from io import BytesIO | |
| from langchain.llms import OpenAI | |
| from dotenv import load_dotenv | |
| import os | |
| import streamlit as st | |
| import pandas as pd | |
| # Set the page configuration here | |
| st.set_page_config(page_title="Insightly") | |
| def main(): | |
| load_dotenv() | |
| # Load the OpenAI API key from the environment variable | |
| api_key = os.getenv("OPENAI_API_KEY") | |
| if api_key is None or api_key == "": | |
| st.error("OPENAI_API_KEY is not set") | |
| return | |
| st.sidebar.image("https://i.ibb.co/bX6GdqG/insightly-wbg.png", use_column_width=True) | |
| st.title("Column Analysis 💬") | |
| csv_files = st.file_uploader("Upload CSV files", type="csv", accept_multiple_files=True) | |
| if csv_files: | |
| llm = OpenAI(temperature=0) | |
| user_input = st.text_input("Question here:") | |
| # Read the CSV file and get the column names | |
| for csv_file in csv_files: | |
| try: | |
| df = pd.read_csv(csv_file) | |
| except pd.errors.EmptyDataError: | |
| st.error(f"Empty CSV file uploaded: {csv_file.name}") | |
| continue | |
| if df.empty: | |
| st.error(f"Empty CSV file uploaded: {csv_file.name}") | |
| continue | |
| column_names = df.columns.tolist() | |
| # Dropdown to select the column for prompts | |
| column_for_prompt = st.selectbox("Select the column for prompts:", [None] + column_names) | |
| if column_for_prompt is not None: | |
| # Create a list to store the responses and original rows for each CSV file | |
| responses_list = [] | |
| original_rows_list = [] | |
| # Check if the specified column for prompts exists in the DataFrame | |
| if column_for_prompt not in df.columns: | |
| st.error(f"The column '{column_for_prompt}' does not exist in the CSV file: {csv_file.name}") | |
| continue | |
| # Example: Accessing columns from the DataFrame | |
| column_data = df[column_for_prompt] | |
| # Loop through each row in the specified column and pass the user input as prompt | |
| for row_value in column_data: | |
| # Convert the row value to a string to handle missing or NaN values | |
| row_value_str = str(row_value) | |
| original_rows_list.append(row_value_str) | |
| # Example: Using the preprocessed data with the OpenAI API | |
| llm_response = llm.predict(row_value_str + " " + user_input) | |
| responses_list.append(llm_response) | |
| # Introduce a delay of 1 second between API calls to reduce the rate of requests | |
| time.sleep(1) | |
| # Create a new DataFrame containing the original rows and responses | |
| response_df = pd.DataFrame({ | |
| "Original Rows": original_rows_list, | |
| "Responses": responses_list | |
| }) | |
| # Add bold formatting to the "Responses" column | |
| response_df["Responses"] = response_df["Responses"].apply(lambda x: f"**{x}**") | |
| # Offer the option to download the responses as a CSV file | |
| if st.button("Download Responses as CSV"): | |
| with BytesIO() as output_file: | |
| response_df.to_csv(output_file, index=False) | |
| st.download_button( | |
| label="Download CSV", | |
| data=output_file.getvalue(), | |
| file_name="responses.csv", | |
| mime="text/csv", | |
| ) | |
| if __name__ == "__main__": | |
| main() |