Upload 6 files

employee.csv

@@ -0,0 +1,51 @@
+EMPLOYEE_ID,FIRST_NAME,LAST_NAME,EMAIL,PHONE_NUMBER,HIRE_DATE,JOB_ID,SALARY,COMMISSION_PCT,MANAGER_ID,DEPARTMENT_ID
+198,Donald,OConnell,DOCONNEL,650.507.9833,21-JUN-07,SH_CLERK,2600, - ,124,50
+199,Douglas,Grant,DGRANT,650.507.9844,13-JAN-08,SH_CLERK,2600, - ,124,50
+200,Jennifer,Whalen,JWHALEN,515.123.4444,17-SEP-03,AD_ASST,4400, - ,101,10
+201,Michael,Hartstein,MHARTSTE,515.123.5555,17-FEB-04,MK_MAN,13000, - ,100,20
+202,Pat,Fay,PFAY,603.123.6666,17-AUG-05,MK_REP,6000, - ,201,20
+203,Susan,Mavris,SMAVRIS,515.123.7777,07-JUN-02,HR_REP,6500, - ,101,40
+204,Hermann,Baer,HBAER,515.123.8888,07-JUN-02,PR_REP,10000, - ,101,70
+205,Shelley,Higgins,SHIGGINS,515.123.8080,07-JUN-02,AC_MGR,12008, - ,101,110
+206,William,Gietz,WGIETZ,515.123.8181,07-JUN-02,AC_ACCOUNT,8300, - ,205,110
+100,Steven,King,SKING,515.123.4567,17-JUN-03,AD_PRES,24000, - , - ,90
+101,Neena,Kochhar,NKOCHHAR,515.123.4568,21-SEP-05,AD_VP,17000, - ,100,90
+102,Lex,De Haan,LDEHAAN,515.123.4569,13-JAN-01,AD_VP,17000, - ,100,90
+103,Alexander,Hunold,AHUNOLD,590.423.4567,03-JAN-06,IT_PROG,9000, - ,102,60
+104,Bruce,Ernst,BERNST,590.423.4568,21-MAY-07,IT_PROG,6000, - ,103,60
+105,David,Austin,DAUSTIN,590.423.4569,25-JUN-05,IT_PROG,4800, - ,103,60
+106,Valli,Pataballa,VPATABAL,590.423.4560,05-FEB-06,IT_PROG,4800, - ,103,60
+107,Diana,Lorentz,DLORENTZ,590.423.5567,07-FEB-07,IT_PROG,4200, - ,103,60
+108,Nancy,Greenberg,NGREENBE,515.124.4569,17-AUG-02,FI_MGR,12008, - ,101,100
+109,Daniel,Faviet,DFAVIET,515.124.4169,16-AUG-02,FI_ACCOUNT,9000, - ,108,100
+110,John,Chen,JCHEN,515.124.4269,28-SEP-05,FI_ACCOUNT,8200, - ,108,100
+111,Ismael,Sciarra,ISCIARRA,515.124.4369,30-SEP-05,FI_ACCOUNT,7700, - ,108,100
+112,Jose Manuel,Urman,JMURMAN,515.124.4469,07-MAR-06,FI_ACCOUNT,7800, - ,108,100
+113,Luis,Popp,LPOPP,515.124.4567,07-DEC-07,FI_ACCOUNT,6900, - ,108,100
+114,Den,Raphaely,DRAPHEAL,515.127.4561,07-DEC-02,PU_MAN,11000, - ,100,30
+115,Alexander,Khoo,AKHOO,515.127.4562,18-MAY-03,PU_CLERK,3100, - ,114,30
+116,Shelli,Baida,SBAIDA,515.127.4563,24-DEC-05,PU_CLERK,2900, - ,114,30
+117,Sigal,Tobias,STOBIAS,515.127.4564,24-JUL-05,PU_CLERK,2800, - ,114,30
+118,Guy,Himuro,GHIMURO,515.127.4565,15-NOV-06,PU_CLERK,2600, - ,114,30
+119,Karen,Colmenares,KCOLMENA,515.127.4566,10-AUG-07,PU_CLERK,2500, - ,114,30
+120,Matthew,Weiss,MWEISS,650.123.1234,18-JUL-04,ST_MAN,8000, - ,100,50
+121,Adam,Fripp,AFRIPP,650.123.2234,10-APR-05,ST_MAN,8200, - ,100,50
+122,Payam,Kaufling,PKAUFLIN,650.123.3234,01-MAY-03,ST_MAN,7900, - ,100,50
+123,Shanta,Vollman,SVOLLMAN,650.123.4234,10-OCT-05,ST_MAN,6500, - ,100,50
+124,Kevin,Mourgos,KMOURGOS,650.123.5234,16-NOV-07,ST_MAN,5800, - ,100,50
+125,Julia,Nayer,JNAYER,650.124.1214,16-JUL-05,ST_CLERK,3200, - ,120,50
+126,Irene,Mikkilineni,IMIKKILI,650.124.1224,28-SEP-06,ST_CLERK,2700, - ,120,50
+127,James,Landry,JLANDRY,650.124.1334,14-JAN-07,ST_CLERK,2400, - ,120,50
+128,Steven,Markle,SMARKLE,650.124.1434,08-MAR-08,ST_CLERK,2200, - ,120,50
+129,Laura,Bissot,LBISSOT,650.124.5234,20-AUG-05,ST_CLERK,3300, - ,121,50
+130,Mozhe,Atkinson,MATKINSO,650.124.6234,30-OCT-05,ST_CLERK,2800, - ,121,50
+131,James,Marlow,JAMRLOW,650.124.7234,16-FEB-05,ST_CLERK,2500, - ,121,50
+132,TJ,Olson,TJOLSON,650.124.8234,10-APR-07,ST_CLERK,2100, - ,121,50
+133,Jason,Mallin,JMALLIN,650.127.1934,14-JUN-04,ST_CLERK,3300, - ,122,50
+134,Michael,Rogers,MROGERS,650.127.1834,26-AUG-06,ST_CLERK,2900, - ,122,50
+135,Ki,Gee,KGEE,650.127.1734,12-DEC-07,ST_CLERK,2400, - ,122,50
+136,Hazel,Philtanker,HPHILTAN,650.127.1634,06-FEB-08,ST_CLERK,2200, - ,122,50
+137,Renske,Ladwig,RLADWIG,650.121.1234,14-JUL-03,ST_CLERK,3600, - ,123,50
+138,Stephen,Stiles,SSTILES,650.121.2034,26-OCT-05,ST_CLERK,3200, - ,123,50
+139,John,Seo,JSEO,650.121.2019,12-FEB-06,ST_CLERK,2700, - ,123,50
+140,Joshua,Patel,JPATEL,650.121.1834,06-APR-06,ST_CLERK,2500, - ,123,50

main.py

@@ -0,0 +1,98 @@
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+import sqlite3
+import pandas as pd
+import os
+from dotenv import load_dotenv
+import google.generativeai as genai
+
+app = FastAPI()
+
+# Load environment variables and configure Genai
+load_dotenv()
+genai.configure(api_key=os.getenv('GOOGLE_API_KEY'))
+
+class Query(BaseModel):
+    question: str
+    data_source: str
+
+def get_gemini_response(question, prompt):
+    model = genai.GenerativeModel('gemini-pro')
+    response = model.generate_content([prompt, question])
+    return response.text
+
+def get_csv_columns():
+    df = pd.read_csv('employee.csv')
+    return df.columns.tolist()
+
+csv_columns = get_csv_columns()
+
+sql_prompt = """
+You are an expert in converting English questions to SQL code!
+The SQL database has the name STUDENT and has the following Columns - NAME, CLASS, SECTION
+
+For example:
+- How many entries of records are present? SQL command: SELECT COUNT(*) FROM STUDENT;
+- Tell me all the students studying in Data Science class? SQL command: SELECT * FROM STUDENT where CLASS="Data Science";
+
+Also, the SQL code should not have ''' in the beginning or at the end, and SQL word in output.
+Ensure that you only generate valid SQL queries, not pandas or Python code.
+"""
+
+csv_prompt = f"""
+You are an expert in analyzing CSV data and converting English questions to pandas query syntax.
+The CSV file is named 'employee.csv' and contains employee information.
+The available columns in the CSV file are: {', '.join(csv_columns)}
+
+For example:
+- How many employees are there? Pandas query: len(df)
+- List all employees in the Sales department. Pandas query: df[df['Department'] == 'Sales']
+- Show employees with a specific ID. Pandas query: df[df['ID'] == specific_id]
+
+Provide only the pandas query syntax without any additional explanation or markdown formatting.
+Do not include 'df = ' or any variable assignment in your response.
+Make sure to use only the columns that are available in the CSV file.
+Ensure that you only generate valid pandas queries, not SQL or other types of code.
+"""
+
+def execute_sql_query(query):
+    conn = sqlite3.connect('student.db')
+    try:
+        cursor = conn.cursor()
+        cursor.execute(query)
+        result = cursor.fetchall()
+        return result
+    except sqlite3.Error as e:
+        raise HTTPException(status_code=400, detail=f"SQL Error: {str(e)}")
+    finally:
+        conn.close()
+
+def execute_pandas_query(query):
+    df = pd.read_csv('employee.csv')
+    try:
+        result = eval(query, {'df': df, 'pd': pd})
+        if isinstance(result, pd.DataFrame):
+            return result.to_dict(orient='records')
+        elif isinstance(result, pd.Series):
+            return result.to_dict()
+        else:
+            return result
+    except Exception as e:
+        raise HTTPException(status_code=400, detail=f"Pandas Error: {str(e)}")
+
+@app.post("/query")
+async def process_query(query: Query):
+    if query.data_source == "SQL Database":
+        ai_response = get_gemini_response(query.question, sql_prompt)
+        try:
+            result = execute_sql_query(ai_response)
+            return {"query": ai_response, "result": result}
+        except HTTPException as e:
+            raise HTTPException(status_code=400, detail=f"Error in SQL query: {e.detail}")
+    else:  # CSV Data
+        ai_response = get_gemini_response(query.question, csv_prompt)
+        try:
+            result = execute_pandas_query(ai_response)
+            return {"query": ai_response, "result": result, "columns": csv_columns}
+        except HTTPException as e:
+            raise HTTPException(status_code=400, detail=f"Error in pandas query: {e.detail}")

requirements.txt

@@ -0,0 +1,7 @@
+fastapi
+uvicorn
+streamlit
+pandas
+python-dotenv
+google-generativeai
+requests

run_app.py

@@ -0,0 +1,11 @@
+import subprocess
+
+# Start Streamlit
+streamlit_process = subprocess.Popen(["streamlit", "run", "streamlit_app.py"])
+
+# Start Uvicorn
+uvicorn_process = subprocess.Popen(["uvicorn", "main:app", "--reload"])
+
+# Wait for the processes to finish
+streamlit_process.wait()
+uvicorn_process.wait()

streamlit_app.py

@@ -0,0 +1,204 @@
+# import streamlit as st
+# import requests
+# import json
+
+# st.set_page_config(page_title="QueryMate: Text to SQL & CSV")
+
+# st.markdown("# QueryMate: Text to SQL & CSV 💬🌐🗄️")
+# st.description('''Welcome to QueryMate, your friendly assistant for converting natural language queries into SQL statements and CSV outputs!
+#                Let's get started with your data queries!''')
+# # Load chat history
+# def load_chat_history():
+#     try:
+#         with open('chat_history.json', 'r') as f:
+#             return json.load(f)
+#     except FileNotFoundError:
+#         return []
+
+# def save_chat_history(history):
+#     with open('chat_history.json', 'w') as f:
+#         json.dump(history, f)
+
+# chat_history = load_chat_history()
+
+# # Data source selection
+# data_source = st.radio("Select Data Source:", ('SQL Database', 'Employee CSV'))
+
+# # Predefined queries
+# predefined_queries = {
+#     'SQL Database': [
+#         'Print all students',
+#         'Count total number of students',
+#         'List students in Data Science class'
+#     ],
+#     'Employee CSV': [
+#         'Print employees having the department id equal to 100',
+#         'Count total number of employees',
+#         'List Top 5 employees according to salary in descending order'
+#     ]
+# }
+
+# st.markdown(f"### Predefined Queries for {data_source}")
+
+# # Create buttons for predefined queries
+# for query in predefined_queries[data_source]:
+#     if st.button(query):
+#         st.session_state.predefined_query = query
+
+# st.markdown("### Enter Your Question")
+# question = st.text_input("Input: ", key="input", value=st.session_state.get('predefined_query', ''))
+
+# # Submit button
+# submit = st.button("Submit")
+
+# if submit:
+#     # Send request to FastAPI backend
+#     response = requests.post("http://localhost:8000/query", 
+#                              json={"question": question, "data_source": data_source})
+#     if response.status_code == 200:
+#         data = response.json()
+#         st.markdown(f"## Generated {'SQL' if data_source == 'SQL Database' else 'Pandas'} Query")
+#         st.code(data['query'])
+        
+#         st.markdown("## Query Results")
+#         st.write(data['result'])
+
+#         if data_source == 'Employee CSV':
+#             st.markdown("## Available CSV Columns")
+#             st.write(data['columns'])
+
+#         # Update chat history
+#         chat_history.append(f"User ({data_source}): {question}")
+#         chat_history.append(f"AI: {data['query']}")
+#         save_chat_history(chat_history)
+#     else:
+#         st.error(f"Error processing your request: {response.text}")
+
+#     # Clear the predefined query from session state
+#     st.session_state.pop('predefined_query', None)
+
+# # Display chat history
+# st.markdown("## Chat History")
+# for message in chat_history:
+#     st.text(message)
+
+# # Option to clear chat history
+# if st.button("Clear Chat History"):
+#     chat_history.clear()
+#     save_chat_history(chat_history)
+#     st.success("Chat history cleared!")
+
+
+
+
+
+import streamlit as st
+import requests
+import json
+import pandas as pd
+
+st.set_page_config(page_title="QueryMate: Text to SQL & CSV")
+
+st.markdown("# QueryMate: Text to SQL & CSV 💬🗄️")
+st.markdown('''Welcome to QueryMate, your friendly assistant for converting natural language queries into SQL statements and CSV outputs!
+               Let's get started with your data queries!''')
+
+# Load chat history
+def load_chat_history():
+    try:
+        with open('chat_history.json', 'r') as f:
+            return json.load(f)
+    except FileNotFoundError:
+        return []
+
+def save_chat_history(history):
+    with open('chat_history.json', 'w') as f:
+        json.dump(history, f)
+
+chat_history = load_chat_history()
+
+# Data source selection
+data_source = st.radio("Select Data Source:", ('SQL Database', 'Employee CSV'))
+
+# Predefined queries
+predefined_queries = {
+    'SQL Database': [
+        'Print all students',
+        'Count total number of students',
+        'List students in Data Science class'
+    ],
+    'Employee CSV': [
+        'Print employees having the department id equal to 100',
+        'Count total number of employees',
+        'List Top 5 employees according to salary in descending order'
+    ]
+}
+
+st.markdown(f"### Predefined Queries for {data_source}")
+
+# Create buttons for predefined queries
+for query in predefined_queries[data_source]:
+    if st.button(query):
+        st.session_state.predefined_query = query
+
+st.markdown("### Enter Your Question")
+question = st.text_input("Input: ", key="input", value=st.session_state.get('predefined_query', ''))
+
+# Submit button
+submit = st.button("Submit")
+
+if submit:
+    # Send request to FastAPI backend
+    response = requests.post("http://localhost:8000/query", 
+                             json={"question": question, "data_source": data_source})
+    if response.status_code == 200:
+        data = response.json()
+        st.markdown(f"## Generated {'SQL' if data_source == 'SQL Database' else 'Pandas'} Query")
+        st.code(data['query'])
+        
+        st.markdown("## Query Results")
+        result = data['result']
+        
+        if isinstance(result, list) and len(result) > 0:
+            if isinstance(result[0], dict):
+                # For CSV queries that return a list of dictionaries
+                df = pd.DataFrame(result)
+                st.dataframe(df)
+            elif isinstance(result[0], list):
+                # For SQL queries that return a list of lists
+                df = pd.DataFrame(result)
+                st.dataframe(df)
+            else:
+                # For single column results
+                st.dataframe(pd.DataFrame(result, columns=['Result']))
+        elif isinstance(result, dict):
+            # For single row results
+            st.table(result)
+        else:
+            # For scalar results or empty results
+            st.write(result)
+
+        if data_source == 'Employee CSV':
+            st.markdown("## Available CSV Columns")
+            st.write(data['columns'])
+
+        # Update chat history
+        chat_history.append(f"👨‍💻({data_source}): {question}")
+        chat_history.append(f"🤖: {data['query']}")
+        save_chat_history(chat_history)
+    else:
+        st.error(f"Error processing your request: {response.text}")
+
+    # Clear the predefined query from session state
+    st.session_state.pop('predefined_query', None)
+
+# Display chat history
+st.markdown("## Chat History")
+for message in chat_history:
+    st.text(message)
+
+# Option to clear chat history
+if st.button("Clear Chat History"):
+    chat_history.clear()
+    save_chat_history(chat_history)
+    st.success("Chat history cleared!")