Spaces:
Sleeping
Sleeping
| import os | |
| import streamlit as st | |
| import pandas as pd | |
| from datasets import load_dataset | |
| import time | |
| from langchain.agents.agent_types import AgentType | |
| from langchain_experimental.agents.agent_toolkits import create_csv_agent | |
| from langchain_openai import ChatOpenAI | |
| import ast | |
| # Streamlit App Title and Description | |
| st.title("Patent Data Analysis with LangChain") | |
| st.write("""This app allows you to analyze patent-related datasets interactively using LangChain agents. You can upload datasets, load from Hugging Face, or use a repository directory dataset.""") | |
| # Dataset loading without caching to support progress bar | |
| def load_huggingface_dataset(dataset_name): | |
| # Initialize progress bar | |
| progress_bar = st.progress(0) | |
| try: | |
| # Incrementally update progress | |
| progress_bar.progress(10) | |
| dataset = load_dataset(dataset_name, name="sample", split="train", trust_remote_code=True, uniform_split=True) | |
| progress_bar.progress(50) | |
| if hasattr(dataset, "to_pandas"): | |
| df = dataset.to_pandas() | |
| else: | |
| df = pd.DataFrame(dataset) | |
| progress_bar.progress(100) # Final update to 100% | |
| return df | |
| except Exception as e: | |
| progress_bar.progress(0) # Reset progress bar on failure | |
| raise e | |
| def load_uploaded_csv(uploaded_file): | |
| # Initialize progress bar | |
| progress_bar = st.progress(0) | |
| try: | |
| # Simulate progress | |
| progress_bar.progress(10) | |
| time.sleep(1) # Simulate file processing delay | |
| progress_bar.progress(50) | |
| df = pd.read_csv(uploaded_file) | |
| progress_bar.progress(100) # Final update | |
| return df | |
| except Exception as e: | |
| progress_bar.progress(0) # Reset progress bar on failure | |
| raise e | |
| # Dataset selection logic | |
| def load_dataset_into_session(): | |
| input_option = st.radio( | |
| "Select Dataset Input:", | |
| ["Use Repo Directory Dataset", "Use Hugging Face Dataset", "Upload CSV File"], index=1, horizontal=True | |
| ) | |
| # Option 1: Load dataset from the repo directory | |
| if input_option == "Use Repo Directory Dataset": | |
| file_path = "./source/test.csv" | |
| if st.button("Load Dataset"): | |
| try: | |
| with st.spinner("Loading dataset from the repo directory..."): | |
| st.session_state.df = pd.read_csv(file_path) | |
| st.success(f"File loaded successfully from '{file_path}'!") | |
| except Exception as e: | |
| st.error(f"Error loading dataset from the repo directory: {e}") | |
| # Option 2: Load dataset from Hugging Face | |
| elif 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: | |
| st.session_state.df = load_huggingface_dataset(dataset_name) | |
| st.success(f"Hugging Face Dataset '{dataset_name}' loaded successfully!") | |
| except Exception as e: | |
| st.error(f"Error loading Hugging Face dataset: {e}") | |
| # Option 3: Upload CSV File | |
| elif input_option == "Upload CSV File": | |
| uploaded_file = st.file_uploader("Upload a CSV File:", type=["csv"]) | |
| if uploaded_file: | |
| try: | |
| st.session_state.df = load_uploaded_csv(uploaded_file) | |
| st.success("File uploaded successfully!") | |
| except Exception as e: | |
| st.error(f"Error reading uploaded file: {e}") | |
| # Load dataset into session | |
| load_dataset_into_session() | |
| if "df" in st.session_state: | |
| df = st.session_state.df | |
| # Display dataset metadata | |
| st.write("### Dataset Metadata") | |
| st.text(f"Number of Rows: {df.shape[0]}") | |
| st.text(f"Number of Columns: {df.shape[1]}") | |
| st.text(f"Column Names: {', '.join(df.columns)}") | |
| # Display dataset preview | |
| st.write("### Dataset Preview") | |
| num_rows = st.slider("Select number of rows to display:", min_value=5, max_value=50, value=10) | |
| st.dataframe(df.head(num_rows)) | |
| # Define LangChain CSV Agent | |
| st.header("Run Queries on Patent Data") | |
| with st.spinner("Setting up LangChain CSV Agent..."): | |
| df.to_csv("patent_data.csv", index=False) | |
| csv_agent = create_csv_agent( | |
| ChatOpenAI(temperature=0, model="gpt-4", api_key=os.getenv("OPENAI_API_KEY")), | |
| path=["patent_data.csv"], | |
| verbose=True, | |
| agent_type=AgentType.OPENAI_FUNCTIONS, | |
| allow_dangerous_code=True | |
| ) | |
| # Query Input and Execution | |
| query = st.text_area("Enter your natural language query:", "How many patents are related to AI?") | |
| if st.button("Run Query"): | |
| with st.spinner("Running query..."): | |
| try: | |
| # Check if the dataset is too large and split if needed | |
| max_rows = 1000 # Limit chunk size to manage token limits | |
| total_rows = len(df) | |
| if total_rows > max_rows: | |
| results = [] | |
| for start in range(0, total_rows, max_rows): | |
| chunk = df.iloc[start:start + max_rows] | |
| chunk.to_csv("chunk_data.csv", index=False) | |
| partial_agent = create_csv_agent( | |
| ChatOpenAI(temperature=0, model="gpt-4", api_key=os.getenv("OPENAI_API_KEY")), | |
| path=["chunk_data.csv"], | |
| verbose=True, | |
| agent_type=AgentType.OPENAI_FUNCTIONS, | |
| allow_dangerous_code=True | |
| ) | |
| result = partial_agent.invoke(query) | |
| results.append(result) | |
| st.success("Query executed successfully!") | |
| st.write("### Combined Query Results:") | |
| st.write("\n".join(results)) | |
| else: | |
| result = csv_agent.invoke(query) | |
| st.success("Query executed successfully!") | |
| st.write("### Query Result:") | |
| st.write(result) | |
| except Exception as e: | |
| st.error(f"Error executing query: {e}") | |