Update interim.py

interim.py

@@ -20,9 +20,10 @@ 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 Logging
+# LLM Callback Logger
 class LLMCallbackHandler(BaseCallbackHandler):
     def __init__(self, log_path: Path):
         self.log_path = log_path
@@ -36,6 +37,7 @@ class LLMCallbackHandler(BaseCallbackHandler):
         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",
@@ -45,7 +47,7 @@ llm = ChatGroq(
 st.title("SQL-RAG Using CrewAI 🚀")
 st.write("Analyze datasets using natural language queries powered by SQL and CrewAI.")
 
-# Data Input Options
+# Input Options
 input_option = st.radio("Select Dataset Input:", ["Use Hugging Face Dataset", "Upload CSV File"])
 df = None
 
@@ -67,7 +69,7 @@ else:
         st.success("File uploaded successfully!")
         st.dataframe(df.head())
 
-# SQL-RAG and Query Workflow
+# SQL-RAG Analysis
 if df is not None:
     temp_dir = tempfile.TemporaryDirectory()
     db_path = os.path.join(temp_dir.name, "data.db")
@@ -75,45 +77,60 @@ if df is not None:
     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 database."""
+        """List all tables in the SQLite database."""
         return ListSQLDatabaseTool(db=db).invoke("")
 
     @tool("tables_schema")
     def tables_schema(tables: str) -> str:
-        """Return schema and example rows for given tables."""
+        """
+        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 SQL query and return results."""
+        """
+        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 SQL query validity."""
+        """
+        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="Senior Database Developer",
-        goal="Construct and execute SQL queries.",
+        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="Senior Data Analyst",
-        goal="Analyze the data returned from SQL queries.",
+        role="Data Analyst",
+        goal="Analyze the extracted data and generate detailed insights.",
         llm=llm,
     )
 
     report_writer = Agent(
-        role="Senior Report Editor",
-        goal="Summarize the analysis into a short report.",
+        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.",
@@ -122,14 +139,14 @@ if df is not None:
 
     analyze_data = Task(
         description="Analyze the query results for: {query}.",
-        expected_output="Detailed analysis report.",
+        expected_output="Analysis report.",
         agent=data_analyst,
         context=[extract_data],
     )
 
     write_report = Task(
-        description="Summarize the analysis into a brief executive summary.",
-        expected_output="Markdown report.",
+        description="Summarize the analysis into an executive summary.",
+        expected_output="Markdown-formatted report.",
         agent=report_writer,
         context=[analyze_data],
     )
@@ -138,7 +155,7 @@ if df is not None:
         agents=[sql_dev, data_analyst, report_writer],
         tasks=[extract_data, analyze_data, write_report],
         process=Process.sequential,
-        verbose=2,
+        verbose=True,
     )
 
     query = st.text_area("Enter Query:", placeholder="e.g., 'What is the average salary by experience level?'")