initial

Departments.csv

@@ -0,0 +1,5 @@
+DepartmentID,DepartmentName
+101,Finance
+102,Marketing
+103,Human Resources
+104,Research and Development

Employees.csv

@@ -0,0 +1,6 @@
+EmployeeID,FirstName,LastName,DepartmentID,Salary
+1,John,Doe,101,50000.00
+2,Jane,Smith,102,60000.00
+3,Michael,Johnson,101,55000.00
+4,Emily,Williams,103,52000.00
+5,David,Brown,102,58000.00

README.md

@@ -0,0 +1,30 @@
+# AI SQL Query Builder
+
+## Getting Started
+
+To get started with CURE AI, follow these steps:
+
+### Clone Repository
+```
+git clone https://github.com/Shrey-patel-07/ai-sql-query-builder.git
+```
+
+### Install the dependencies from requirement.txt
+```
+pip install -r requirements.txt
+```
+
+### Run ddl_query_generator.py database_selection.py to generate SQL Query from DLL
+```
+python ddl_query_generator.py
+```
+
+### Run database_selection.py to generate outputs from database
+```
+python database_selection.py
+```
+
+### Launch it on your browser
+```
+http://localhost:5713
+```

database_selection.py

@@ -0,0 +1,54 @@
+from flask import Flask, render_template, request
+import pandas as pd
+import sqlite3
+import os
+
+app = Flask(__name__)
+
+UPLOAD_FOLDER = 'uploads'
+app.config['UPLOAD_FOLDER'] = UPLOAD_FOLDER
+
+# Create the 'uploads' directory if it doesn't exist
+if not os.path.exists(UPLOAD_FOLDER):
+    os.makedirs(UPLOAD_FOLDER)
+
+# Initialize history list to store query history
+history = []
+
+def run_sql_query(csv_files, sql_query):
+    conn = sqlite3.connect(':memory:')
+    
+    for file_path in csv_files:
+        df_name = os.path.splitext(os.path.basename(file_path))[0]  # Extract file name without extension
+        df = pd.read_csv(file_path)
+        df.to_sql(df_name, conn, index=False)
+    
+    result = pd.read_sql_query(sql_query, con=conn)
+    
+    return result.to_html()
+
+@app.route('/', methods=['GET', 'POST'])
+def index():
+    result = None
+    query = None
+    
+    if request.method == 'POST':
+        uploaded_files = request.files.getlist('file')
+        csv_files = []
+        for file in uploaded_files:
+            if file.filename != '':
+                file_path = os.path.join(app.config['UPLOAD_FOLDER'], file.filename)
+                file.save(file_path)
+                csv_files.append(file_path)
+        
+        sql_query = request.form['sql_query']
+        query = sql_query
+        
+        # Execute SQL query and store result in history
+        result = run_sql_query(csv_files, sql_query)
+        history.append({'query': sql_query, 'result': result})
+        
+    return render_template('database_selection_index.html', result=result, query=query, history=history)
+
+if __name__ == '__main__':
+    app.run(debug=True)

ddl_query_generator.py

@@ -0,0 +1,100 @@
+import os
+import sqlite3
+import warnings
+import pandas as pd
+from flask import Flask, render_template, request
+from langchain_community.llms import Ollama
+from langchain import PromptTemplate, LLMChain
+
+app = Flask(__name__)
+
+# Suppressing warnings
+warnings.filterwarnings("ignore")
+
+# Initializing the language model
+llm = Ollama(model="pxlksr/defog_sqlcoder-7b-2:Q4_K")
+
+UPLOAD_FOLDER = 'uploads'
+app.config['UPLOAD_FOLDER'] = UPLOAD_FOLDER
+
+# Prompt template for language model
+template = """
+### Task
+Generate a SQL query to answer [QUESTION]{user_question}[/QUESTION]
+
+### Instructions
+- If you cannot answer the question with the available database schema, return 'I do not know'
+
+### Database Schema
+The query will run on a database with the following schema:
+{table_metadata_string}
+
+### Answer
+Given the database schema, here is the SQL query that answers [QUESTION]{user_question}[/QUESTION]
+[SQL]
+"""
+
+prompt = PromptTemplate(template=template, input_variables=["user_question", "table_metadata_string"])
+
+# Function to get response from language model
+def get_llm_response(user_question, table_metadata_string):
+    llm_chain = LLMChain(prompt=prompt, llm=llm)
+    response = llm_chain.run({"user_question": user_question, "table_metadata_string": table_metadata_string})
+    return response
+
+def run_sql_query(csv_files, sql_query):
+    conn = sqlite3.connect(':memory:')
+    
+    for file_path in csv_files:
+        df_name = os.path.splitext(os.path.basename(file_path))[0]  # Extract file name without extension
+        df = pd.read_csv(file_path)
+        df.to_sql(df_name, conn, index=False)
+    
+    result = pd.read_sql_query(sql_query, con=conn)
+    
+    return result.to_html()
+
+
+history = []
+
+@app.route('/', methods=['GET', 'POST'])
+def ddl_query():
+    ddl = None
+    if request.method == 'POST':
+        ddl = request.form['ddl']
+        user_question = request.form.get('user_question', None)
+
+        if user_question:
+            output = get_llm_response(user_question, ddl)
+            # Insert the new history item at the beginning of the list
+            history.insert(0, {'query': user_question, 'response': output})
+
+    return render_template('index.html', history=history, ddl=ddl)
+
+
+@app.route('/dbms_query', methods=['GET', 'POST'])
+def index():
+    result = None
+    query = None
+    
+    if request.method == 'POST':
+        uploaded_files = request.files.getlist('file')
+        csv_files = []
+        for file in uploaded_files:
+            if file.filename != '':
+                file_path = os.path.join(app.config['UPLOAD_FOLDER'], file.filename)
+                file.save(file_path)
+                csv_files.append(file_path)
+        
+        sql_query = request.form['sql_query']
+        query = sql_query
+        
+        # Execute SQL query and store result in history
+        result = run_sql_query(csv_files, sql_query)
+        history.append({'query': sql_query, 'result': result})
+        
+    return render_template('database_selection_index.html', result=result, query=query, history=history)
+
+if __name__ == '__main__':
+    app.run(debug=True, port = 7860, host = '0.0.0.0')
+

demo.py

@@ -0,0 +1,41 @@
+import ollama
+import streamlit as st
+
+st.title("Ollama Python Chatbot")
+
+# initialize history
+if "messages" not in st.session_state:
+    st.session_state["messages"] = []
+
+
+# init models
+if "model" not in st.session_state:
+    st.session_state["model"] = ""
+
+models = [model["name"] for model in ollama.list()["models"]]
+st.session_state["model"] = st.selectbox("Choose your model", models)
+
+def model_res_generator():
+    stream = ollama.chat(
+        model=st.session_state["model"],
+        messages=st.session_state["messages"],
+        stream=True,
+    )
+    for chunk in stream:
+        yield chunk["message"]["content"]
+
+# Display chat messages from history on app rerun
+for message in st.session_state["messages"]:
+    with st.chat_message(message["role"]):
+        st.markdown(message["content"])
+
+if prompt := st.chat_input("What is up?"):
+    # add latest message to history in format {role, content}
+    st.session_state["messages"].append({"role": "user", "content": prompt})
+
+    with st.chat_message("user"):
+        st.markdown(prompt)
+
+    with st.chat_message("assistant"):
+        message = st.write_stream(model_res_generator())
+        st.session_state["messages"].append({"role": "assistant", "content": message})

natural-language.Dockerfile

@@ -0,0 +1,8 @@
+FROM ollama/ollama as ollama
+RUN ollama serve & sleep 5 && ollama pull pxlksr/defog_sqlcoder-7b-2:Q4_K
+ENV HOME=/home
+RUN apt-get update && apt-get install -y python3.12 python3-pip
+COPY requirements.txt ./
+RUN python3.12 -m pip install --no-cache-dir -r requirements.txt
+COPY . .
+CMD ["python3.12", "ddl_query_generator.py"]

requirements.txt

@@ -0,0 +1,51 @@
+aiohttp==3.9.5
+aiosignal==1.3.1
+annotated-types==0.6.0
+anyio==4.3.0
+attrs==23.2.0
+blinker==1.7.0
+certifi==2024.2.2
+charset-normalizer==3.3.2
+click==8.1.7
+dataclasses-json==0.6.4
+Flask==3.0.3
+frozenlist==1.4.1
+greenlet==3.0.3
+h11==0.14.0
+httpcore==1.0.5
+httpx==0.27.0
+idna==3.7
+itsdangerous==2.2.0
+Jinja2==3.1.3
+jsonpatch==1.33
+jsonpointer==2.4
+langchain==0.1.16
+langchain-community==0.0.34
+langchain-core==0.1.45
+langchain-text-splitters==0.0.1
+langsmith==0.1.49
+MarkupSafe==2.1.5
+marshmallow==3.21.1
+multidict==6.0.5
+mypy-extensions==1.0.0
+numpy==1.26.4
+ollama==0.1.8
+orjson==3.10.1
+packaging==23.2
+pandas==2.2.2
+pydantic==2.7.0
+pydantic_core==2.18.1
+python-dateutil==2.9.0.post0
+pytz==2024.1
+PyYAML==6.0.1
+requests==2.31.0
+six==1.16.0
+sniffio==1.3.1
+SQLAlchemy==2.0.29
+tenacity==8.2.3
+typing-inspect==0.9.0
+typing_extensions==4.11.0
+tzdata==2024.1
+urllib3==2.2.1
+Werkzeug==3.0.2
+yarl==1.9.4

templates/database_selection_index.html

@@ -0,0 +1,111 @@
+<!DOCTYPE html>
+<html lang="en">
+
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>CSV File Upload</title>
+    <style>
+        body {
+            font-family: Arial, sans-serif;
+            text-align: center;
+            margin: 0;
+            padding: 0;
+            background-color: #f0f0f0;
+            color: #fff;
+        }
+
+        h1 {
+            margin-top: 40px;
+            color: #fff;
+        }
+
+        form {
+            margin: 0 auto;
+            max-width: 600px;
+            padding: 20px;
+            text-align: left;
+            background-color: #444;
+            border-radius: 8px;
+        }
+
+        input[type="file"],
+        textarea,
+        input[type="submit"] {
+            width: 100%;
+            padding: 10px;
+            margin-bottom: 10px;
+            box-sizing: border-box;
+            background-color: #555;
+            border: none;
+            border-radius: 4px;
+            color: #fff;
+        }
+
+        input[type="submit"]:hover {
+            background-color: #007bff;
+        }
+
+        ul {
+            list-style-type: none;
+            padding: 0;
+            text-align: left;
+            margin: 0 auto;
+            max-width: 600px;
+        }
+
+        li {
+            margin-bottom: 10px;
+        }
+
+        div {
+            margin-bottom: 20px;
+        }
+
+        /* Dark mode compatible styles */
+        @media (prefers-color-scheme: dark) {
+            body {
+                background-color: #1a1a1a;
+                color: #fff;
+            }
+
+            form {
+                background-color: #333;
+            }
+
+            input[type="file"],
+            textarea,
+            input[type="submit"] {
+                background-color: #444;
+                color: #fff;
+            }
+
+            input[type="submit"]:hover {
+                background-color: #007bff;
+            }
+        }
+    </style>
+</head>
+
+<body>
+    <h1>CSV File Upload</h1>
+    <form action="/" method="post" enctype="multipart/form-data">
+        <input type="file" name="file" multiple>
+        <textarea name="sql_query" placeholder="Enter SQL query"></textarea>
+        <input type="submit" value="Upload and Run Query">
+    </form>
+    <h2>Query Result:</h2>
+    <div id="cnt">
+        <ul>
+            {% for entry in history %}
+            <li><strong>Query:</strong> {{ entry.query }}</li>
+            <li><strong>Result:</strong></li>
+            <center>
+                <div>{{ entry.result | safe }}</div>
+            </center>
+            {% endfor %}
+        </ul>
+    </div>
+</body>
+
+</html>

templates/index.html

@@ -0,0 +1,167 @@
+<!DOCTYPE html>
+<html lang="en">
+
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Language Model SQL Query Generator</title>
+    <style>
+        body {
+            background-color: #333;
+            color: #fff;
+            font-family: Arial, sans-serif;
+            text-align: center;
+        }
+
+        form {
+            margin: 0 auto;
+            max-width: 600px;
+            padding: 20px;
+            background-color: #444;
+            border-radius: 8px;
+        }
+
+        input[type="text"],
+        textarea {
+            width: 100%;
+            padding: 10px;
+            margin-bottom: 10px;
+            box-sizing: border-box;
+            background-color: #555;
+            border: none;
+            border-radius: 4px;
+            color: #fff;
+        }
+
+        input[type="submit"] {
+            padding: 10px 20px;
+            background-color: #007bff;
+            border: none;
+            border-radius: 4px;
+            color: #fff;
+            cursor: pointer;
+        }
+
+        input[type="submit"]:hover {
+            background-color: #0056b3;
+        }
+
+        h1,
+        h2 {
+            margin-top: 40px;
+            color: #fff;
+        }
+
+        <style>... table {
+            margin: 0 auto;
+            width: 80%;
+            border-collapse: collapse;
+            border: 1px solid #ddd;
+            /* Added border */
+            border-radius: 10px;
+            /* Rounded corners */
+            overflow: hidden;
+            /* Ensures rounded corners are visible */
+        }
+
+        th,
+        td {
+            padding: 8px;
+            border-bottom: 1px solid #ddd;
+            color: #fff;
+        }
+
+        th {
+            background-color: #555;
+        }
+
+        /* Updated styles for query and response cells */
+        .query {
+            background-color: #333;
+            /* Dark grey */
+            color: #ddd;
+            /* Light black text */
+            text-align: left;
+        }
+
+        .response {
+            background-color: #444;
+            /* Dark grey */
+            color: #ddd;
+            /* Light black text */
+        }
+
+        .history {
+            margin-top: 40px;
+            text-align: center;
+            /* Centered the History heading */
+            margin-left: auto;
+            margin-right: auto;
+            width: 80%;
+        }
+
+        .history table {
+            margin: 0 auto;
+            /* Center the table */
+            text-align: left;
+            border: 1px solid #ddd;
+            /* Added border */
+            border-radius: 10px;
+            /* Rounded corners */
+            overflow: hidden;
+        }
+
+        .history strong {
+            color: #fff;
+        }
+
+        /* Added hover effect to the entire table */
+        table:hover {
+            background-color: #666;
+        }
+    </style>
+
+    </style>
+
+</head>
+
+<body>
+    <h1>Language Model SQL Query Generator</h1>
+
+    <!-- Combined Form -->
+    <form action="/" method="post">
+        <!-- DDL Input -->
+        <label for="ddl">Enter DDL:</label><br>
+        <textarea id="ddl" name="ddl" rows="5" cols="50">{% if ddl %}{{ ddl }}{% endif %}</textarea><br><br>
+
+        <!-- Query Input -->
+        <label for="user_question">Enter Query:</label><br>
+        <input type="text" id="user_question" name="user_question"><br><br>
+
+        <!-- Submit Button -->
+        <input type="submit" value="Submit">
+    </form>
+
+    <!-- History -->
+    <div class="history">
+
+        <table>
+            <caption>
+                <h2>History</h2>
+            </caption>
+            <tbody>
+                {% for item in history %}
+                <tr>
+                    <td style="background-color: #333;"><strong>Query:</strong> {{ item.query }}</td>
+                </tr>
+                <tr>
+                    <td style="background-color: #666;"><strong>Response:</strong> {{ item.response }}</td>
+                </tr>
+                {% endfor %}
+            </tbody>
+        </table>
+    </div>
+</body>
+
+</html>
+

uploads/Departments.csv

@@ -0,0 +1,5 @@
+DepartmentID,DepartmentName
+101,Finance
+102,Marketing
+103,Human Resources
+104,Research and Development

uploads/Employees.csv

@@ -0,0 +1,6 @@
+EmployeeID,FirstName,LastName,DepartmentID,Salary
+1,John,Doe,101,50000.00
+2,Jane,Smith,102,60000.00
+3,Michael,Johnson,101,55000.00
+4,Emily,Williams,103,52000.00
+5,David,Brown,102,58000.00