initial commit

.gitignore

@@ -0,0 +1,2 @@
+.venv
+**/__pycache__/

Dockerfile

@@ -0,0 +1,21 @@
+FROM python:3.11
+
+WORKDIR /code
+
+COPY ./requirements.txt /code/requirements.txt
+
+RUN pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
+RUN pip install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+	PATH=/home/user/.local/bin:$PATH
+
+WORKDIR $HOME/app
+
+
+COPY --chown=user . $HOME/app
+
+CMD ["python", "app.py"]

app.py

@@ -0,0 +1,14 @@
+from chatBot import create_app
+from threading import Thread
+from flask import render_template
+app = create_app()
+
+@app.route('/home')
+def index():
+    return render_template('layout.html')
+
+
+def run():
+    app.run(host='0.0.0.0', port=7860, debug=False)
+
+run()

chatBot/__init__.py

@@ -0,0 +1,29 @@
+from flask import Flask
+from flask_cors import CORS
+from chatBot.config import Config
+from flask_login import LoginManager
+from flask_bcrypt import Bcrypt
+from flask_sqlalchemy import SQLAlchemy
+
+db = SQLAlchemy()
+
+bcrypt = Bcrypt()
+
+login_manager = LoginManager()
+login_manager.login_view = 'update.login'
+login_manager.login_message_category = 'info'
+
+
+def create_app(config_class=Config):
+    app = Flask(__name__)
+    app.config.from_object(Config)
+    CORS(app)
+
+    db.init_app(app)
+    bcrypt.init_app(app)
+    login_manager.init_app(app)
+    from chatBot.resources.routes import resources
+    app.register_blueprint(resources)
+    from chatBot.update.routes import update
+    app.register_blueprint(update)
+    return app

chatBot/common/chatgpt.py

@@ -0,0 +1,43 @@
+import os
+from chatBot.common.pdfToText import loadLatestPdf
+os.environ["OPENAI_API_KEY"] = "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"
+from langchain.document_loaders import PyPDFLoader
+from langchain.text_splitter import CharacterTextSplitter
+import pickle
+import faiss
+from langchain.vectorstores import FAISS
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.chains import RetrievalQAWithSourcesChain
+from langchain.chains.question_answering import load_qa_chain
+from langchain import OpenAI
+
+urls = [
+    'http://en.espn.co.uk/f1/motorsport/story/3836.html', 'https://www.mercedes-amg-hpp.com/formula-1-engine-facts/#' , 'https://www.redbullracing.com/int-en/five-things-about-yas-marina' , 'https://www.redbull.com/gb-en/history-of-formula-1'
+, 'https://www.formula1.com/en/information.abu-dhabi-yas-marina-circuit-yas-island.4YtOtpaWvaxWvDBTItP7s6.html']
+
+
+data = loadLatestPdf()
+
+
+text_splitter = CharacterTextSplitter(separator='\n',
+                                      chunk_size=1000,
+                                      chunk_overlap=200)
+
+
+docs = text_splitter.split_documents(data)
+
+
+embeddings = OpenAIEmbeddings()
+
+vectorStore1_openAI = FAISS.from_documents(docs, embeddings)
+
+with open("faiss_store_openai.pkl", "wb") as f:
+    pickle.dump(vectorStore1_openAI, f)
+
+with open("faiss_store_openai.pkl", "rb") as f:
+    VectorStore = pickle.load(f)
+
+
+llm=OpenAI(temperature=0.8, verbose = True)
+
+gptModel = RetrievalQAWithSourcesChain.from_llm(llm=llm, retriever=VectorStore.as_retriever())

chatBot/common/llama.py

@@ -0,0 +1,99 @@
+import torch
+from auto_gptq import AutoGPTQForCausalLM
+from langchain import HuggingFacePipeline, PromptTemplate
+from langchain.chains import RetrievalQA
+from langchain.document_loaders import PyPDFDirectoryLoader
+from langchain.embeddings import HuggingFaceInstructEmbeddings
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.vectorstores import Chroma
+from pdf2image import convert_from_path
+from transformers import AutoTokenizer, TextStreamer, pipeline
+from chatBot.common.pdfToText import loadLatestPdf
+from transformers import LlamaTokenizer
+from langchain.document_loaders import PyPDFLoader
+
+# DEVICE = "cuda:0" if torch.cuda.is_available() else "cpu"
+DEVICE = "cpu"
+print(DEVICE)
+
+
+data = loadLatestPdf()
+
+embeddings = HuggingFaceInstructEmbeddings(
+    model_name="hkunlp/instructor-large", model_kwargs={"device": DEVICE}
+)
+
+text_splitter = RecursiveCharacterTextSplitter(chunk_size=1024, chunk_overlap=64)
+texts = text_splitter.split_documents(data)
+
+db = Chroma.from_documents(texts, embeddings, persist_directory="db")
+
+model_name_or_path = "TheBloke/Llama-2-13B-chat-GPTQ"
+model_basename = "model"
+
+tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
+
+model = AutoGPTQForCausalLM.from_quantized(
+    model_name_or_path,
+    device_map="auto",
+    revision="gptq-4bit-128g-actorder_True",
+    model_basename=model_basename,
+    use_safetensors=True,
+    trust_remote_code=True,
+    inject_fused_attention=False,
+    device=DEVICE,
+    quantize_config=None,
+)
+
+
+DEFAULT_SYSTEM_PROMPT = """
+You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
+
+If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
+""".strip()
+
+
+def generate_prompt(prompt: str, system_prompt: str = DEFAULT_SYSTEM_PROMPT) -> str:
+    return f"""
+[INST] <<SYS>>
+{system_prompt}
+<</SYS>>
+
+{prompt} [/INST]
+""".strip()
+
+streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
+
+text_pipeline = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    max_new_tokens=1024,
+    temperature=0,
+    top_p=0.95,
+    repetition_penalty=1.15,
+    streamer=streamer,
+)
+
+llm = HuggingFacePipeline(pipeline=text_pipeline, model_kwargs={"temperature": 0})
+
+SYSTEM_PROMPT = "Use the following pieces of context to answer the question at the end. If you don't know the answer, just say that you don't know, don't try to make up an answer."
+
+template = generate_prompt(
+    """
+{context}
+
+Question: {question}
+""",
+    system_prompt=SYSTEM_PROMPT,
+)
+
+prompt = PromptTemplate(template=template, input_variables=["context", "question"])
+
+llamaModel = RetrievalQA.from_chain_type(
+    llm=llm,
+    chain_type="stuff",
+    retriever=db.as_retriever(search_kwargs={"k": 2}),
+    return_source_documents=True,
+    chain_type_kwargs={"prompt": prompt},
+)

chatBot/common/pdfToText.py

@@ -0,0 +1,12 @@
+from langchain.document_loaders import PyPDFLoader
+import os
+
+pdfLocation = 'chatBot/static/pdfs/'
+
+def loadLatestPdf():
+    pdfCount = len(os.listdir(pdfLocation))
+    loader = PyPDFLoader(f"{pdfLocation}/{pdfCount}.pdf")
+    pages = loader.load_and_split()
+    data=pages
+
+    return data

chatBot/common/utils.py

@@ -0,0 +1,9 @@
+from chatBot.common.chatgpt import gptModel
+from chatBot.common.llama import llamaModel
+
+
+def getAnswerLlama(question):
+    return llamaModel(question) 
+
+def getAnswerGpt(question):
+    return gptModel({'question' : question}, return_only_outputs = True)['answer']

chatBot/config.py

@@ -0,0 +1,6 @@
+class Config:
+    SECRET_KEY = '5791628bb0b13ce0c676dfde280ba245'
+    PASSWORD = 'saaddiditallonhisown'
+    PDF_PATH = 'chatBot/static/pdfs/'
+    SQLALCHEMY_DATABASE_URI = 'sqlite:///site.db'
+    

chatBot/models.py

@@ -0,0 +1,20 @@
+from flask import current_app
+from flask_sqlalchemy import SQLAlchemy
+from chatBot import login_manager, db
+from flask_login import UserMixin
+
+
+@login_manager.user_loader
+def load_user(user_id):
+    return User.query.get(int(user_id))
+
+
+class User(db.Model, UserMixin):
+    id = db.Column(db.Integer, primary_key = True)
+    username = db.Column(db.String(20), unique = True, nullable = False)
+    password = db.Column(db.String(60), nullable = False)
+
+    def __repr__(self):
+        return f"User('{self.username}')"
+    
+    

chatBot/resources/routes.py

@@ -0,0 +1,20 @@
+from flask import Blueprint, request 
+from flask_restful import Api, Resource
+from chatBot.common.utils import getAnswerLlama, getAnswerGpt
+
+resources = Blueprint('resources', __name__)
+api = Api(resources)
+
+class Gpt(Resource):
+    def get(self):
+        question = request.json['question']
+
+        return {'answer': getAnswerGpt(question)}
+api.add_resource(Gpt, '/gpt')
+
+
+class Llama(Resource):
+    def get(self):
+        question = request.json['question']
+        return {'answer': getAnswerLlama(question)}
+api.add_resource(Llama, '/llama')

chatBot/static/main.css

@@ -0,0 +1,38 @@
+* {
+    box-sizing: border-box;
+    color : white;
+}
+body {
+    padding : 100px;
+    margin : 100px;
+    background-color: #222;
+    padding: 0px;
+    margin: 0px;
+    font-family: Arial, Helvetica, sans-serif;
+    display : flex;
+    flex-direction: column;
+    justify-content: center;
+    align-items: center;
+    height : 100dvh;
+    gap : 1rem;
+    overflow-y : scroll;
+
+}
+
+.img {
+    border-radius: 50%;     
+}
+
+
+.container {
+    width : 50%;
+    padding : 2rem;
+    border-radius: 0.8rem;
+    background-color: #333;
+}
+
+main > form > fieldset {
+    display : flex;
+    flex-direction: column;
+    gap : 1rem;
+}

chatBot/templates/layout.html

@@ -0,0 +1,29 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <link href="https://cdn.jsdelivr.net/npm/bootstrap@5.3.2/dist/css/bootstrap.min.css" rel="stylesheet" integrity="sha384-T3c6CoIi6uLrA9TneNEoa7RxnatzjcDSCmG1MXxSR1GAsXEV/Dwwykc2MPK8M2HN" crossorigin="anonymous">  
+    <script defersrc="https://cdn.jsdelivr.net/npm/bootstrap@5.3.2/dist/js/bootstrap.bundle.min.js" integrity="sha384-C6RzsynM9kWDrMNeT87bh95OGNyZPhcTNXj1NW7RuBCsyN/o0jlpcV8Qyq46cDfL" crossorigin="anonymous"></script>
+    <link rel="stylesheet" type="text/css" href="{{ url_for('static', filename='main.css') }}">
+    <title>Document</title>
+</head>
+<body>
+    <div class="image">
+        <img src="{{ url_for('static', filename='logo.jpg') }}" alt="logo" class="img">
+    </div>
+    <div class="container">
+        {% with messages = get_flashed_messages(with_categories = true) %}
+            {% if messages %}
+                {% for category, message in messages %}
+                    <div class="alert alert-{{ category }}">
+                        {{ message }}
+                    </div>
+                {% endfor %}
+            {% endif %}
+        {% endwith %}
+        {% block content %}
+        {% endblock %}
+    </div>
+</body>
+</html>

chatBot/templates/login.html

@@ -0,0 +1,44 @@
+{% extends 'layout.html' %}
+{% block content %}
+
+<main class="login">
+    <form method="POST" action="">
+        {{form.hidden_tag()}}
+        <fieldset class="form-group">
+            <legend class="border-bottom mb-4">Login</legend>
+            <div class="form-group">
+                {{form.username.label(class="form-control-label")}}
+                {% if form.username.errors %}
+                    {{form.username(class="form-control form-control-lg is-invalid")}}
+                    <div class="invalid-feedback">
+                        {% for error in form.username.errors %}
+                            <span> {{ error }} </span>
+                        {% endfor %}
+                    </div>
+                {% else %}
+                    {{form.username(class="form-control form-control-lg")}}
+                {% endif %}
+            </div>
+
+            <div class="form-group">
+                {{form.password.label(class="form-control-label")}}
+                {% if form.password.errors %}
+                    {{form.password(class="form-control form-control-lg is-invalid")}}
+                    <div class="invalid-feedback">
+                        {% for error in form.password.errors %}
+                            <span> {{ error }} </span>
+                        {% endfor %}
+                    </div>
+                {% else %}
+                    {{form.password(class="form-control form-control-lg")}}
+                {% endif %}
+            </div>
+
+            <div class="form-group">
+                {{form.submit(class="btn btn-info")}}
+            </div>
+        </fieldset> 
+    </form>
+</main>
+
+{% endblock %}

chatBot/templates/update.html

@@ -0,0 +1,26 @@
+{% extends 'layout.html' %}
+{% block content %}
+
+<main class="update">
+    <form method="POST" action="" enctype="multipart/form-data">
+        {{form.hidden_tag()}}
+        <fieldset class="form-group">
+            <legend class="border-bottom mb-4"> Upload new dataset </legend>
+            <div class="form-group">
+                {{ form.file.label(class="form-control-label", for="formFile") }}
+                {{ form.file(class="form-control", id="formFile", type="file") }}
+                {% if form.file.errors %}
+                    {% for error in form.file.errors %}
+                        <span> {{ error }} </span>
+                    {% endfor %}
+                {% endif %}
+            </div>
+
+            <div class="form-group">
+                {{form.submit(class="btn btn-info")}}
+            </div>
+        </fieldset> 
+    </form>
+</main>
+
+{% endblock %}

chatBot/update/forms.py

@@ -0,0 +1,17 @@
+from flask_wtf import FlaskForm
+from wtforms import StringField, SubmitField, PasswordField
+from flask_wtf.file import FileAllowed, FileField
+from wtforms.validators import DataRequired
+
+
+class LoginForm(FlaskForm):
+    username = StringField('Username',validators=[DataRequired()])
+    password = PasswordField('Password',validators=[DataRequired()])
+    submit = SubmitField('Login')
+
+
+class UpdateForm(FlaskForm):
+    file = FileField('Update File', validators=[DataRequired(), FileAllowed(['pdf'])])
+    submit = SubmitField('Update')
+
+

chatBot/update/routes.py

@@ -0,0 +1,50 @@
+from flask import Blueprint, render_template, url_for, flash, redirect, request, current_app
+from chatBot.update.forms import LoginForm, UpdateForm
+from flask_login import login_user, current_user, logout_user, login_required
+import os
+from chatBot import bcrypt, db
+from chatBot.models import User
+update = Blueprint('update', __name__)
+
+@update.route("/register", methods=['GET', 'POST'])
+def register():
+    if current_user.is_authenticated:
+        return redirect(url_for('update.upload'))
+    form = LoginForm()
+
+    if form.validate_on_submit():
+        hashed_password = bcrypt.generate_password_hash(form.password.data).decode('utf-8')
+        user = User(username = form.username.data, password = hashed_password)
+        db.session.add(user)
+        db.session.commit()
+        flash(message = "Account created", category = "success")
+        return redirect(url_for('update.login'))
+    return render_template('login.html', title='login', form=form)
+
+@update.route("/login", methods=['GET', 'POST'])
+def login():
+    if current_user.is_authenticated:
+        return redirect(url_for('update.upload'))
+    form = LoginForm()
+
+    if form.validate_on_submit():
+        user = User.query.filter_by(username=form.username.data).first()
+        if user and form.username.data == 'TechTeam' and bcrypt.check_password_hash(pw_hash = user.password, password = form.password.data):
+            login_user(user)
+            next_page = request.args.get('next')
+            flash(message = "Login successful", category = "success")
+            return redirect(next_page) if next_page else redirect(url_for('update.upload'))
+        flash(message = "Login unsuccessful", category = "danger")
+    return render_template('login.html', title='Login', form=form)
+
+@update.route("/upload", methods=['GET', 'POST'])
+@login_required
+def upload():
+    form = UpdateForm()
+    if form.validate_on_submit():
+        if form.file.data:
+            file = form.file.data
+            fileCount = len(os.listdir(current_app.config['PDF_PATH']))
+            file.save(current_app.config['PDF_PATH'] + str(fileCount + 1) + '.pdf')
+            flash('Your file has been updated!', 'success')
+    return render_template('update.html', title='Update', form=form)