create chatbot app

app.py

@@ -0,0 +1,158 @@
+from dotenv import load_dotenv
+load_dotenv() ## load all the environemnt variables
+from extract_word import suggest_words
+import streamlit as st
+import os
+import sqlite3
+import pandas as pd
+import re
+import numpy as np
+import Levenshtein
+
+import google.generativeai as genai
+## Configure Genai Key
+
+genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
+
+## Function To Load Google Gemini Model and provide queries as response
+
+def get_gemini_response(question,prompt):
+    model=genai.GenerativeModel('gemini-pro')
+    response=model.generate_content([prompt,question])
+    return response.text
+
+
+def string_similarity(input_string, string_list):
+    similarities = []
+
+    for string in string_list:
+        distance = Levenshtein.distance(input_string, string)
+        similarity = 1 - distance / max(len(input_string), len(string))
+        similarities.append((string, similarity))
+
+    return similarities
+
+def suggest_words(input_string, string_list, max_suggestions=5):
+    similarities = string_similarity(input_string, string_list)
+
+    # Sort the list of similarities by similarity score (descending order)
+    sorted_similarities = sorted(similarities, key=lambda x: x[1], reverse=True)
+
+    # Get the top N suggestions
+    suggestions = [string for string, _ in sorted_similarities[:max_suggestions]]
+
+    return suggestions
+
+
+
+
+
+
+
+
+
+
+## Fucntion To retrieve query from the database
+
+def read_sql_query(sql,db):
+    conn=sqlite3.connect(db)
+    cur=conn.cursor()
+    cur.execute(sql)
+    rows=cur.fetchall()
+    conn.commit()
+    conn.close()
+    for row in rows:
+        print(row)
+    return rows
+
+## Streamlit App
+df= pd.DataFrame()
+string_of_csv = []
+st.set_page_config(page_title="I can Retrieve Any SQL query")
+st.header("Data analysis by Chatbot")
+
+uploaded_file = st.file_uploader("Upload a CSV file", type=["csv"], key="uploaded_file")
+
+if uploaded_file is not None:
+    # Display the uploaded file
+    # st.write("Uploaded CSV file:", uploaded_file.name)
+
+    # Read the CSV file
+    df = pd.read_csv(uploaded_file)
+    df = df.dropna(axis=1, how="all")
+    df = df.dropna(axis=0, how="all")
+    df = df.fillna('nan')
+    object_columns = df.select_dtypes(include='object')
+    print(object_columns)
+    # Convert each object-type column to a Python list
+    lists_of_columns = [df[column].tolist() for column in object_columns.columns]
+    string_of_csv = [element for sublist in lists_of_columns for element in sublist]
+    
+    
+    df = df.applymap(lambda x: x.lower() if isinstance(x, str) else x)
+    df.columns = df.columns.str.replace(' ', '_')
+    df.columns = df.columns.str.replace('.', '')
+    # pattern = re.compile('[^a-zA-Z0-9]')
+    # # Use the sub() function to replace matched characters with an empty string
+    # df.columns = df.columns.map(lambda x: re.sub(pattern, '', x))
+    df.columns = df.columns.astype(str)
+    df.columns = df.columns.str.strip()
+
+question = st.text_input("Enter a word prefix:", key="user_input")
+# Display suggestions dynamically
+suggestions = suggest_words(question.strip(), string_of_csv)
+st.subheader("Suggestions:")
+if suggestions:
+    for suggestion in suggestions:
+        st.write(suggestion)
+else:
+    st.write("No suggestions found.")
+
+question = question.lower()
+
+
+# User input for the starting string
+
+
+
+
+submit=st.button("Ask the question")
+
+connection  = sqlite3.connect('student.db')
+
+df.to_sql('student', connection,if_exists='replace')
+connection.commit()
+connection.close()
+
+## Define Your Prompt
+column_names = df.columns.tolist()
+# print(column_names)
+column = ', '.join(column_names) 
+prompt = f"""You are an expert in converting English questions to SQL query!
+    The SQL database has the name STUDENT and has the following columns - {column} 
+    \n\n\nFor example: \n Example 1: Retrieve all the information about student ?, the sql query will be like 
+    SELECT * FROM student;
+    \n Example 2: how many row in the student table ?, the sql query will be like 
+    SELECT COUNT(*) as row_count FROM student;
+    \n Example 3:  what is the unique name ?, the sql query will be like 
+    SELECT DISTINCT name  FROM student; 
+    also the sql code should not have ``` in beginning or end and sql word in output
+    return only sql query
+    """
+# if submit is clicked
+if submit:
+    response=get_gemini_response(question,prompt)
+    print(response)
+    response=read_sql_query(response,"student.db")
+    print(response)
+    st.subheader("The REsponse is")
+    for row in response:
+        st.text(row)
+    # st.text(response)
+
+
+
+
+
+
+