Create interim_radio.py

interim_radio.py

@@ -0,0 +1,171 @@
+import streamlit as st
+import pandas as pd
+import sqlite3
+import os
+import json
+from pathlib import Path
+from datetime import datetime, timezone
+from crewai import Agent, Crew, Process, Task
+from crewai_tools import tool
+from langchain_groq import ChatGroq
+from langchain.schema.output import LLMResult
+from langchain_core.callbacks.base import BaseCallbackHandler
+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
+
+# Environment setup
+os.environ["GROQ_API_KEY"] = st.secrets.get("GROQ_API_KEY", "")
+
+# LLM Callback Logger
+class LLMCallbackHandler(BaseCallbackHandler):
+    def __init__(self, log_path: Path):
+        self.log_path = log_path
+
+    def on_llm_start(self, serialized, prompts, **kwargs):
+        with self.log_path.open("a", encoding="utf-8") as file:
+            file.write(json.dumps({"event": "llm_start", "text": prompts[0], "timestamp": datetime.now().isoformat()}) + "\n")
+
+    def on_llm_end(self, response: LLMResult, **kwargs):
+        generation = response.generations[-1][-1].message.content
+        with self.log_path.open("a", encoding="utf-8") as file:
+            file.write(json.dumps({"event": "llm_end", "text": generation, "timestamp": datetime.now().isoformat()}) + "\n")
+
+# Initialize the LLM
+llm = ChatGroq(
+    temperature=0,
+    model_name="mixtral-8x7b-32768",
+    callbacks=[LLMCallbackHandler(Path("prompts.jsonl"))],
+)
+
+st.title("SQL-RAG Using CrewAI 🚀")
+st.write("Analyze datasets using natural language queries powered by SQL and CrewAI.")
+
+# Input Options
+input_option = st.radio("Select Dataset Input:", ["Use Hugging Face Dataset", "Upload CSV File"])
+df = None
+
+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 Hugging Face dataset..."):
+                dataset = load_dataset(dataset_name, split="train")
+                df = pd.DataFrame(dataset)
+                st.success(f"Dataset '{dataset_name}' loaded successfully!")
+                st.dataframe(df.head())
+        except Exception as e:
+            st.error(f"Error loading dataset: {e}")
+else:
+    uploaded_file = st.file_uploader("Upload CSV File:", type=["csv"])
+    if uploaded_file:
+        df = pd.read_csv(uploaded_file)
+        st.success("File uploaded successfully!")
+        st.dataframe(df.head())
+
+# SQL-RAG Analysis
+if df is not None:
+    temp_dir = tempfile.TemporaryDirectory()
+    db_path = os.path.join(temp_dir.name, "data.db")
+    connection = sqlite3.connect(db_path)
+    df.to_sql("salaries", connection, if_exists="replace", index=False)
+    db = SQLDatabase.from_uri(f"sqlite:///{db_path}")
+
+    # Tools with proper docstrings
+    @tool("list_tables")
+    def list_tables() -> str:
+        """List all tables in the SQLite database."""
+        return ListSQLDatabaseTool(db=db).invoke("")
+
+    @tool("tables_schema")
+    def tables_schema(tables: str) -> str:
+        """
+        Get the schema and sample rows for specific tables in the database.
+        Input: Comma-separated table names.
+        Example: 'salaries'
+        """
+        return InfoSQLDatabaseTool(db=db).invoke(tables)
+
+    @tool("execute_sql")
+    def execute_sql(sql_query: str) -> str:
+        """
+        Execute a valid SQL query on the database and return the results.
+        Input: A SQL query string.
+        Example: 'SELECT * FROM salaries LIMIT 5;'
+        """
+        return QuerySQLDataBaseTool(db=db).invoke(sql_query)
+
+    @tool("check_sql")
+    def check_sql(sql_query: str) -> str:
+        """
+        Check the validity of a SQL query before execution.
+        Input: A SQL query string.
+        Example: 'SELECT salary FROM salaries WHERE salary > 10000;'
+        """
+        return QuerySQLCheckerTool(db=db, llm=llm).invoke({"query": sql_query})
+
+    # Agents
+    sql_dev = Agent(
+        role="Database Developer",
+        goal="Extract relevant data by executing SQL queries.",
+        llm=llm,
+        tools=[list_tables, tables_schema, execute_sql, check_sql],
+    )
+
+    data_analyst = Agent(
+        role="Data Analyst",
+        goal="Analyze the extracted data and generate detailed insights.",
+        llm=llm,
+    )
+
+    report_writer = Agent(
+        role="Report Writer",
+        goal="Summarize the analysis into an executive report.",
+        llm=llm,
+    )
+
+    # Tasks
+    extract_data = Task(
+        description="Extract data for the query: {query}.",
+        expected_output="Database query results.",
+        agent=sql_dev,
+    )
+
+    analyze_data = Task(
+        description="Analyze the query results for: {query}.",
+        expected_output="Analysis report.",
+        agent=data_analyst,
+        context=[extract_data],
+    )
+
+    write_report = Task(
+        description="Summarize the analysis into an executive summary.",
+        expected_output="Markdown-formatted report.",
+        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=2,
+    )
+
+    query = st.text_area("Enter Query:", placeholder="e.g., 'What is the average salary by experience level?'")
+    if st.button("Submit Query"):
+        with st.spinner("Processing your query with CrewAI..."):
+            inputs = {"query": query}
+            result = crew.kickoff(inputs=inputs)
+            st.markdown("### Analysis Report:")
+            st.markdown(result)
+
+    temp_dir.cleanup()
+else:
+    st.info("Load a dataset to proceed.")