test.py

import streamlit as st
import pandas as pd
import sqlite3
import tempfile
from fpdf import FPDF
import os
import re
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.")

# 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())


# Helper Function for Validation
def is_valid_suggestion(suggestion):
    chart_type = suggestion.get("chart_type", "").lower()

    if chart_type in ["bar", "line", "box", "scatter"]:
        return all(k in suggestion for k in ["chart_type", "x_axis", "y_axis"])

    elif chart_type == "pie":
        return all(k in suggestion for k in ["chart_type", "x_axis"])

    elif chart_type == "heatmap":
        return all(k in suggestion for k in ["chart_type", "x_axis", "y_axis"])

    else:
        return False
        
def ask_gpt4o_for_visualization(query, df, llm, retries=2):
    import json

    # Identify numeric and categorical columns
    numeric_columns = df.select_dtypes(include='number').columns.tolist()
    categorical_columns = df.select_dtypes(exclude='number').columns.tolist()

    # Prompt with Dataset-Specific, Query-Based Examples
    prompt = f"""
    Analyze the following query and suggest the most suitable visualization(s) using the dataset.
    **Query:** "{query}"
    **Dataset Overview:**  
    - **Numeric Columns (for Y-axis):** {', '.join(numeric_columns) if numeric_columns else 'None'}  
    - **Categorical Columns (for X-axis or grouping):** {', '.join(categorical_columns) if categorical_columns else 'None'}  
    Suggest visualizations in this exact JSON format:
    [
      {{
        "chdart_type": "bar/box/line/scatter/pie/heatmap",
        "x_axis": "categorical_or_time_column",
        "y_axis": "numeric_column",
        "group_by": "optional_column_for_grouping",
        "title": "Title of the chart",
        "description": "Why this chart is suitable"
      }}
    ]
    **Query-Based Examples:**  
    - **Query:** "What is the salary distribution across different job titles?"  
      **Suggested Visualization:**  
      {{
        "chart_type": "box",
        "x_axis": "job_title",
        "y_axis": "salary_in_usd",
        "group_by": "experience_level",
        "title": "Salary Distribution by Job Title and Experience",
        "description": "A box plot to show how salaries vary across different job titles and experience levels."
      }}
    - **Query:** "Show the average salary by company size and employment type."  
      **Suggested Visualizations:**  
      [
        {{
          "chart_type": "bar",
          "x_axis": "company_size",
          "y_axis": "salary_in_usd",
          "group_by": "employment_type",
          "title": "Average Salary by Company Size and Employment Type",
          "description": "A grouped bar chart comparing average salaries across company sizes and employment types."
        }},
        {{
          "chart_type": "heatmap",
          "x_axis": "company_size",
          "y_axis": "salary_in_usd",
          "group_by": "employment_type",
          "title": "Salary Heatmap by Company Size and Employment Type",
          "description": "A heatmap showing salary concentration across company sizes and employment types."
        }}
      ]
    - **Query:** "How has the average salary changed over the years?"  
      **Suggested Visualization:**  
      {{
        "chart_type": "line",
        "x_axis": "work_year",
        "y_axis": "salary_in_usd",
        "group_by": "experience_level",
        "title": "Average Salary Trend Over Years",
        "description": "A line chart showing how the average salary has changed across different experience levels over the years."
      }}
    - **Query:** "What is the employee distribution by company location?"  
      **Suggested Visualization:**  
      {{
        "chart_type": "pie",
        "x_axis": "company_location",
        "y_axis": null,
        "group_by": null,
        "title": "Employee Distribution by Company Location",
        "description": "A pie chart showing the distribution of employees across company locations."
      }}
    - **Query:** "Is there a relationship between remote work ratio and salary?"  
      **Suggested Visualization:**  
      {{
        "chart_type": "scatter",
        "x_axis": "remote_ratio",
        "y_axis": "salary_in_usd",
        "group_by": "experience_level",
        "title": "Remote Work Ratio vs Salary",
        "description": "A scatter plot to analyze the relationship between remote work ratio and salary."
      }}
    - **Query:** "Which job titles have the highest salaries across regions?"  
      **Suggested Visualization:**  
      {{
        "chart_type": "heatmap",
        "x_axis": "job_title",
        "y_axis": "employee_residence",
        "group_by": null,
        "title": "Salary Heatmap by Job Title and Region",
        "description": "A heatmap showing the concentration of high-paying job titles across regions."
      }}
    Only suggest visualizations that logically match the query and dataset.
    """

    for attempt in range(retries + 1):
        try:
            response = llm.generate(prompt)
            suggestions = json.loads(response)

            if isinstance(suggestions, list):
                valid_suggestions = [s for s in suggestions if is_valid_suggestion(s)]
                if valid_suggestions:
                    return valid_suggestions
                else:
                    st.warning("⚠️ GPT-4o did not suggest valid visualizations.")
                    return None

            elif isinstance(suggestions, dict):
                if is_valid_suggestion(suggestions):
                    return [suggestions]
                else:
                    st.warning("⚠️ GPT-4o's suggestion is incomplete or invalid.")
                    return None

        except json.JSONDecodeError:
            st.warning(f"⚠️ Attempt {attempt + 1}: GPT-4o returned invalid JSON.")
        except Exception as e:
            st.error(f"⚠️ Error during GPT-4o call: {e}")

        if attempt < retries:
            st.info("🔄 Retrying visualization suggestion...")

    st.error("❌ Failed to generate a valid visualization after multiple attempts.")
    return None


def add_stats_to_figure(fig, df, y_axis, chart_type):
    """
    Add relevant statistical annotations to the visualization 
    based on the chart type.
    """
    # Check if the y-axis column is numeric
    if not pd.api.types.is_numeric_dtype(df[y_axis]):
        st.warning(f"⚠️ Cannot compute statistics for non-numeric column: {y_axis}")
        return fig

    # Compute statistics for numeric data
    min_val = df[y_axis].min()
    max_val = df[y_axis].max()
    avg_val = df[y_axis].mean()
    median_val = df[y_axis].median()
    std_dev_val = df[y_axis].std()

    # Format the stats for display
    stats_text = (
        f"📊 **Statistics**\n\n"
        f"- **Min:** ${min_val:,.2f}\n"
        f"- **Max:** ${max_val:,.2f}\n"
        f"- **Average:** ${avg_val:,.2f}\n"
        f"- **Median:** ${median_val:,.2f}\n"
        f"- **Std Dev:** ${std_dev_val:,.2f}"
    )

    # Apply stats only to relevant chart types
    if chart_type in ["bar", "line"]:
        # Add annotation box for bar and line charts
        fig.add_annotation(
            text=stats_text,
            xref="paper", yref="paper",
            x=1.02, y=1,
            showarrow=False,
            align="left",
            font=dict(size=12, color="black"),
            bordercolor="gray",
            borderwidth=1,
            bgcolor="rgba(255, 255, 255, 0.85)"
        )

        # Add horizontal reference lines
        fig.add_hline(y=min_val, line_dash="dot", line_color="red", annotation_text="Min", annotation_position="bottom right")
        fig.add_hline(y=median_val, line_dash="dash", line_color="orange", annotation_text="Median", annotation_position="top right")
        fig.add_hline(y=avg_val, line_dash="dashdot", line_color="green", annotation_text="Avg", annotation_position="top right")
        fig.add_hline(y=max_val, line_dash="dot", line_color="blue", annotation_text="Max", annotation_position="top right")

    elif chart_type == "scatter":
        # Add stats annotation only, no lines for scatter plots
        fig.add_annotation(
            text=stats_text,
            xref="paper", yref="paper",
            x=1.02, y=1,
            showarrow=False,
            align="left",
            font=dict(size=12, color="black"),
            bordercolor="gray",
            borderwidth=1,
            bgcolor="rgba(255, 255, 255, 0.85)"
        )

    elif chart_type == "box":
        # Box plots inherently show distribution; no extra stats needed
        pass

    elif chart_type == "pie":
        # Pie charts represent proportions, not suitable for stats
        st.info("📊 Pie charts represent proportions. Additional stats are not applicable.")

    elif chart_type == "heatmap":
        # Heatmaps already reflect data intensity
        st.info("📊 Heatmaps inherently reflect distribution. No additional stats added.")

    else:
        st.warning(f"⚠️ No statistical overlays applied for unsupported chart type: '{chart_type}'.")

    return fig


# Dynamically generate Plotly visualizations based on GPT-4o suggestions
def generate_visualization(suggestion, df):
    """
    Generate a Plotly visualization based on GPT-4o's suggestion.
    If the Y-axis is missing, infer it intelligently.
    """
    chart_type = suggestion.get("chart_type", "bar").lower()
    x_axis = suggestion.get("x_axis")
    y_axis = suggestion.get("y_axis")
    group_by = suggestion.get("group_by")

    # Step 1: Infer Y-axis if not provided
    if not y_axis:
        numeric_columns = df.select_dtypes(include='number').columns.tolist()

        # Avoid using the same column for both axes
        if x_axis in numeric_columns:
            numeric_columns.remove(x_axis)

        # Smart guess: prioritize salary or relevant metrics if available
        priority_columns = ["salary_in_usd", "income", "earnings", "revenue"]
        for col in priority_columns:
            if col in numeric_columns:
                y_axis = col
                break

        # Fallback to the first numeric column if no priority columns exist
        if not y_axis and numeric_columns:
            y_axis = numeric_columns[0]

    # Step 2: Validate axes
    if not x_axis or not y_axis:
        st.warning("⚠️ Unable to determine appropriate columns for visualization.")
        return None

    #  Step 3: Dynamically select the Plotly function
    plotly_function = getattr(px, chart_type, None)
    if not plotly_function:
        st.warning(f"⚠️ Unsupported chart type '{chart_type}' suggested by GPT-4o.")
        return None

    #  Step 4: Prepare dynamic plot arguments
    plot_args = {"data_frame": df, "x": x_axis, "y": y_axis}
    if group_by and group_by in df.columns:
        plot_args["color"] = group_by

    try:
        # Step 5: Generate the visualization
        fig = plotly_function(**plot_args)
        fig.update_layout(
            title=f"{chart_type.title()} Plot of {y_axis.replace('_', ' ').title()} by {x_axis.replace('_', ' ').title()}",
            xaxis_title=x_axis.replace('_', ' ').title(),
            yaxis_title=y_axis.replace('_', ' ').title(),
        )

        # Step 6: Apply statistics intelligently
        fig = add_statistics_to_visualization(fig, df, y_axis, chart_type)

        return fig

    except Exception as e:
        st.error(f"⚠️ Failed to generate visualization: {e}")
        return None


def generate_multiple_visualizations(suggestions, df):
    """
    Generates one or more visualizations based on GPT-4o's suggestions.
    Handles both single and multiple suggestions.
    """
    visualizations = []

    for suggestion in suggestions:
        fig = generate_visualization(suggestion, df)
        if fig:
            # Apply chart-specific statistics
            fig = add_stats_to_figure(fig, df, suggestion["y_axis"], suggestion["chart_type"])
            visualizations.append(fig)

    if not visualizations and suggestions:
        st.warning("⚠️ No valid visualization found. Displaying the most relevant one.")
        best_suggestion = suggestions[0]
        fig = generate_visualization(best_suggestion, df)
        fig = add_stats_to_figure(fig, df, best_suggestion["y_axis"], best_suggestion["chart_type"])
        visualizations.append(fig)

    return visualizations


def handle_visualization_suggestions(suggestions, df):
    """
    Determines whether to generate a single or multiple visualizations.
    """
    visualizations = []

    # If multiple suggestions, generate multiple plots
    if isinstance(suggestions, list) and len(suggestions) > 1:
        visualizations = generate_multiple_visualizations(suggestions, df)
    
    # If only one suggestion, generate a single plot
    elif isinstance(suggestions, dict) or (isinstance(suggestions, list) and len(suggestions) == 1):
        suggestion = suggestions[0] if isinstance(suggestions, list) else suggestions
        fig = generate_visualization(suggestion, df)
        if fig:
            visualizations.append(fig)
    
    # Handle cases when no visualization could be generated
    if not visualizations:
        st.warning("⚠️ Unable to generate any visualization based on the suggestion.")

    # Display all generated visualizations
    for fig in visualizations:
        st.plotly_chart(fig, use_container_width=True)


def escape_markdown(text):
    # Ensure text is a string
    text = str(text)
    # Escape Markdown characters: *, _, `, ~
    escape_chars = r"(\*|_|`|~)"
    return re.sub(escape_chars, r"\\\1", text)

# 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})

    # Agents for SQL data extraction and analysis
    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="Write a structured report with Introduction and Key Insights. DO NOT include any Conclusion or Summary.",
        backstory="Specializes in detailed analytical reports without conclusions.",
        llm=llm,
    )

    conclusion_writer = Agent(
        role="Conclusion Specialist",
        goal="Summarize findings into a clear and concise 3-5 line Conclusion highlighting only the most important insights.",
        backstory="An expert in crafting impactful and clear conclusions.",
        llm=llm,
    )

    # Define tasks for report and conclusion
    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="Key Insights and Analysis without any Introduction or Conclusion.",
        agent=data_analyst,
        context=[extract_data],
    )

    write_report = Task(
        description="Write the analysis report with  Introduction and Key Insights. DO NOT include any Conclusion or Summary.",
        expected_output="Markdown-formatted report excluding Conclusion.",
        agent=report_writer,
        context=[analyze_data],
    )

    write_conclusion = Task(
        description="Summarize the key findings in 3-5 impactful lines, highlighting the maximum, minimum, and average salaries."
        "Emphasize significant insights on salary distribution and influential compensation trends for strategic decision-making.",
        expected_output="Markdown-formatted Conclusion section with key insights and statistics.",
        agent=conclusion_writer,
        context=[analyze_data],
    )



    # Separate Crews for report and conclusion
    crew_report = Crew(
        agents=[sql_dev, data_analyst, report_writer],
        tasks=[extract_data, analyze_data, write_report],
        process=Process.sequential,
        verbose=True,
    )

    crew_conclusion = Crew(
        agents=[data_analyst, conclusion_writer],
        tasks=[write_conclusion],
        process=Process.sequential,
        verbose=True,
    )

    # Tabs for Query Results and Visualizations
    tab1, tab2 = st.tabs(["🔍 Query Insights + Viz", "📊 Full Data Viz"])

    # 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..."):
                # Step 1: Generate the analysis report
                report_inputs = {"query": query + " Provide detailed analysis but DO NOT include Conclusion."}
                report_result = crew_report.kickoff(inputs=report_inputs)

                # Step 2: Generate only the concise conclusion
                conclusion_inputs = {"query": query + " Provide ONLY the most important insights in 3-5 concise lines."}
                conclusion_result = crew_conclusion.kickoff(inputs=conclusion_inputs)

                # Step 3: Display the report
                #st.markdown("### Analysis Report:")
                st.markdown(report_result if report_result else "⚠️ No Report Generated.")

                # Step 4: Generate Visualizations


                # Step 5: Insert Visual Insights
                st.markdown("### Visual Insights")


                # Step 6: Display Concise Conclusion
                #st.markdown("#### Conclusion")

                safe_conclusion = escape_markdown(conclusion_result if conclusion_result else "⚠️ No Conclusion Generated.")
                st.markdown(safe_conclusion)


# Sidebar Reference
with st.sidebar:
    st.header("📚 Reference:")
    st.markdown("[SQL Agents w CrewAI & Llama 3 - Plaban Nayak](https://github.com/plaban1981/Agents/blob/main/SQL_Agents_with_CrewAI_and_Llama_3.ipynb)")