import streamlit as st import pandas as pd import sqlite3 import os import json from pathlib import Path import plotly.express as px from datetime import datetime, timezone from crewai import Agent, Crew, Process, Task from crewai.tools import tool from langchain_groq import ChatGroq from langchain_openai import ChatOpenAI from langchain.schema.output import LLMResult from langchain_community.tools.sql_database.tool import ( InfoSQLDatabaseTool, ListSQLDatabaseTool, QuerySQLCheckerTool, QuerySQLDataBaseTool, ) from langchain_community.utilities.sql_database import SQLDatabase from datasets import load_dataset import tempfile st.title("SQL-RAG Using CrewAI 🚀") st.write("Analyze datasets using natural language queries powered by SQL and CrewAI.") # Initialize LLM llm = None # Model Selection model_choice = st.radio("Select LLM", ["GPT-4o", "llama-3.3-70b"], index=0, horizontal=True) # API Key Validation and LLM Initialization 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.") llm = None else: llm = 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.") llm = None else: llm = ChatOpenAI(api_key=openai_api_key, model="gpt-4o") # Initialize session state for data persistence if "df" not in st.session_state: st.session_state.df = None if "show_preview" not in st.session_state: st.session_state.show_preview = False # Dataset Input input_option = st.radio("Select Dataset Input:", ["Use Hugging Face Dataset", "Upload CSV File"]) if input_option == "Use Hugging Face Dataset": dataset_name = st.text_input("Enter Hugging Face Dataset Name:", value="Einstellung/demo-salaries") if st.button("Load Dataset"): try: with st.spinner("Loading dataset..."): dataset = load_dataset(dataset_name, split="train") st.session_state.df = pd.DataFrame(dataset) st.session_state.show_preview = True # Show preview after loading st.success(f"Dataset '{dataset_name}' loaded successfully!") except Exception as e: st.error(f"Error: {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.session_state.show_preview = True # Show preview after loading st.success("File uploaded successfully!") except Exception as e: st.error(f"Error loading file: {e}") # Show Dataset Preview Only After Loading if st.session_state.df is not None and st.session_state.show_preview: st.subheader("📂 Dataset Preview") st.dataframe(st.session_state.df.head()) # SQL-RAG Analysis if st.session_state.df is not None: temp_dir = tempfile.TemporaryDirectory() db_path = os.path.join(temp_dir.name, "data.db") connection = sqlite3.connect(db_path) st.session_state.df.to_sql("salaries", connection, if_exists="replace", index=False) db = SQLDatabase.from_uri(f"sqlite:///{db_path}") @tool("list_tables") def list_tables() -> str: """List all tables in the database.""" return ListSQLDatabaseTool(db=db).invoke("") @tool("tables_schema") def tables_schema(tables: str) -> str: """Get the schema and sample rows for the specified tables.""" return InfoSQLDatabaseTool(db=db).invoke(tables) @tool("execute_sql") def execute_sql(sql_query: str) -> str: """Execute a SQL query against the database and return the results.""" return QuerySQLDataBaseTool(db=db).invoke(sql_query) @tool("check_sql") def check_sql(sql_query: str) -> str: """Validate the SQL query syntax and structure before execution.""" return QuerySQLCheckerTool(db=db, llm=llm).invoke({"query": sql_query}) sql_dev = Agent( role="Senior Database Developer", goal="Extract data using optimized SQL queries.", backstory="An expert in writing optimized SQL queries for complex databases.", llm=llm, tools=[list_tables, tables_schema, execute_sql, check_sql], ) data_analyst = Agent( role="Senior Data Analyst", goal="Analyze the data and produce insights.", backstory="A seasoned analyst who identifies trends and patterns in datasets.", llm=llm, ) report_writer = Agent( role="Technical Report Writer", goal="Summarize the insights into a clear report.", backstory="An expert in summarizing data insights into readable reports.", llm=llm, ) extract_data = Task( description="Extract data based on the query: {query}.", expected_output="Database results matching the query.", agent=sql_dev, ) analyze_data = Task( description="Analyze the extracted data for query: {query}.", expected_output="Analysis text summarizing findings.", agent=data_analyst, context=[extract_data], ) write_report = Task( description="Summarize the analysis into an executive report.", expected_output="Markdown report of insights.", agent=report_writer, context=[analyze_data], ) crew = Crew( agents=[sql_dev, data_analyst, report_writer], tasks=[extract_data, analyze_data, write_report], process=Process.sequential, verbose=True, ) # UI: Tabs for Query Results and General Insights tab1, tab2 = st.tabs(["🔍 Query Insights + Viz", "📊 Full Data Viz"]) # Tab 1: Query Insights + Visualization with tab1: query = st.text_area("Enter Query:", value="Provide insights into the salary of a Principal Data Scientist.") if st.button("Submit Query"): with st.spinner("Processing query..."): inputs = {"query": query} result = crew.kickoff(inputs=inputs) st.markdown("### Analysis Report:") # Create visualization if the query is about salary if "salary" in query.lower(): fig = px.box(st.session_state.df, x="job_title", y="salary_in_usd", title="Salary Distribution by Job Title") # Insert visualization after "5. Company Size" insert_section = "5. Company Size" if insert_section in result: # Split the report at the "Company Size" section parts = result.split(insert_section) st.markdown(parts[0]) # Display everything before "Company Size" st.markdown(f"## {insert_section}{parts[1].split('6.')[0]}") # Show the "Company Size" content # Insert the visualization here st.plotly_chart(fig, use_container_width=True) # Continue with the rest of the report st.markdown("## 6." + parts[1].split("6.")[1]) # Display everything after "Company Size" else: # If "Company Size" not found, show full report and plot at the end st.markdown(result) st.plotly_chart(fig, use_container_width=True) else: st.markdown(result) # Tab 2: Full Data Visualization with tab2: st.subheader("📊 Comprehensive Data Visualizations") fig1 = px.histogram(st.session_state.df, x="job_title", title="Job Title Frequency") st.plotly_chart(fig1) fig2 = px.bar( st.session_state.df.groupby("experience_level")["salary_in_usd"].mean().reset_index(), x="experience_level", y="salary_in_usd", title="Average Salary by Experience Level" ) st.plotly_chart(fig2) temp_dir.cleanup() else: st.info("Please load a dataset to proceed.")