Deployment

Dockerfile

@@ -0,0 +1,17 @@
+# Stage 1: Build the Python environment and install dependencies
+FROM python:3.11-slim-bullseye AS builder
+
+WORKDIR /app
+
+# Copy only the requirements file first to leverage Docker layer caching
+COPY requirements.txt .
+COPY setup.py .
+RUN pip install --upgrade pip && pip install --no-cache-dir -r requirements.txt
+
+COPY . .
+
+# Clean up after install (if necessary)
+RUN rm -rf /root/.cache
+
+# Run the app
+CMD ["python", "app.py"]

Generative_AI_Project.egg-info/PKG-INFO

@@ -0,0 +1,6 @@
+Metadata-Version: 2.1
+Name: Generative-AI-Project
+Version: 0.0.0
+Author: Yaswanth
+Author-email: yashmanic96@gmail.com
+License-File: LICENSE

Generative_AI_Project.egg-info/SOURCES.txt

@@ -0,0 +1,10 @@
+LICENSE
+README.md
+setup.py
+Generative_AI_Project.egg-info/PKG-INFO
+Generative_AI_Project.egg-info/SOURCES.txt
+Generative_AI_Project.egg-info/dependency_links.txt
+Generative_AI_Project.egg-info/top_level.txt
+src/__init__.py
+src/helper.py
+src/prompt.py

Generative_AI_Project.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

Generative_AI_Project.egg-info/top_level.txt

@@ -0,0 +1 @@
+src

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 yaswanth
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

app.py

@@ -0,0 +1,71 @@
+from flask import Flask, render_template, jsonify, request
+from src.helper import download_hugging_face_embeddings
+from langchain_pinecone import PineconeVectorStore
+from langchain_groq import ChatGroq
+from langchain_core.prompts import ChatPromptTemplate
+from langchain_core.output_parsers import JsonOutputParser
+import json
+from langchain.chains import create_retrieval_chain
+from langchain.chains.combine_documents import create_stuff_documents_chain
+from langchain_core.prompts import ChatPromptTemplate
+from dotenv import load_dotenv
+from src.prompt import *
+import os
+
+app = Flask(__name__)
+
+load_dotenv()
+
+PINECONE_API_KEY=os.environ.get('PINECONE_API_KEY')
+GROQ_API_KEY=os.environ.get('GROQ_API_KEY')
+
+os.environ["PINECONE_API_KEY"] = PINECONE_API_KEY
+os.environ["GROQ_API_KEY"] = GROQ_API_KEY
+
+embeddings = download_hugging_face_embeddings()
+
+
+index_name = "medicalbot"
+
+# Embed each chunk and upsert the embeddings into your Pinecone index.
+docsearch = PineconeVectorStore.from_existing_index(
+    index_name=index_name,
+    embedding=embeddings
+)
+
+retriever = docsearch.as_retriever(search_type="similarity", search_kwargs={"k":3})
+
+llm = ChatGroq(
+    model_name="llama-3.3-70b-versatile",
+    temperature=0.7
+)
+prompt = ChatPromptTemplate.from_messages(
+    [
+        ("system", system_prompt),
+        ("human", "{input}"),
+    ]
+)
+
+question_answer_chain = create_stuff_documents_chain(llm, prompt)
+rag_chain = create_retrieval_chain(retriever, question_answer_chain)
+
+
+@app.route("/")
+def index():
+    return render_template('chat.html')
+
+
+@app.route("/get", methods=["GET", "POST"])
+def chat():
+    msg = request.form["msg"]
+    input = msg
+    print(input)
+    response = rag_chain.invoke({"input": msg})
+    print("Response : ", response["answer"])
+    return str(response["answer"])
+
+
+
+ 
+if __name__ == '__main__':
+    app.run(host="0.0.0.0", port= 8080)

requirements.txt

@@ -0,0 +1,12 @@
+sentence-transformers == 3.3.1
+gunicorn>=20.0.4
+langchain
+flask
+pypdf
+python-dotenv
+pinecone[grpc]
+langchain-pinecone
+langchain_community
+langchain_experimental
+langchain-groq
+-e .

setup.py

@@ -0,0 +1,11 @@
+from setuptools import find_packages, setup
+
+setup(
+    name = 'Generative AI Project',
+    version= '0.0.0',
+    author= 'Yaswanth',
+    author_email= 'yashmanic96@gmail.com',
+    packages= find_packages(),
+    install_requires = []
+
+)

src/helper.py

@@ -0,0 +1,29 @@
+from langchain_community.document_loaders import PyPDFLoader,DirectoryLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_community.embeddings import HuggingFaceEmbeddings
+
+
+#Extract Data From the PDF File
+def load_pdf_file(data):
+    loader= DirectoryLoader(data,
+                            glob="*.pdf",
+                            loader_cls=PyPDFLoader)
+
+    documents=loader.load()
+
+    return documents
+
+
+
+#Split the Data into Text Chunks
+def text_split(extracted_data):
+    text_splitter=RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=20)
+    text_chunks=text_splitter.split_documents(extracted_data)
+    return text_chunks
+
+
+
+#Download the Embeddings from HuggingFace 
+def download_hugging_face_embeddings():
+    embeddings=HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L6-v2')  #this model return 384 dimensions
+    return embeddings

src/prompt.py

@@ -0,0 +1,9 @@
+system_prompt = (
+    "You are an assistant for question-answering tasks. "
+    "Use the following pieces of retrieved context to answer "
+    "the question. If you don't know the answer, say that you "
+    "don't know. Use three sentences maximum and keep the "
+    "answer concise."
+    "\n\n"
+    "{context}"
+)

static/style.css

@@ -0,0 +1,223 @@
+body,html{
+	height: 100%;
+	margin: 0;
+	background: rgb(44, 47, 59);
+   background: -webkit-linear-gradient(to right, rgb(40, 59, 34), rgb(54, 60, 70), rgb(32, 32, 43));
+	background: linear-gradient(to right, rgb(38, 51, 61), rgb(50, 55, 65), rgb(33, 33, 78));
+}
+
+.chat{
+	margin-top: auto;
+	margin-bottom: auto;
+}
+.card{
+	height: 500px;
+	border-radius: 15px !important;
+	background-color: rgba(0,0,0,0.4) !important;
+}
+.contacts_body{
+	padding:  0.75rem 0 !important;
+	overflow-y: auto;
+	white-space: nowrap;
+}
+.msg_card_body{
+	overflow-y: auto;
+}
+.card-header{
+	border-radius: 15px 15px 0 0 !important;
+	border-bottom: 0 !important;
+}
+.card-footer{
+border-radius: 0 0 15px 15px !important;
+	border-top: 0 !important;
+}
+.container{
+	align-content: center;
+}
+.search{
+	border-radius: 15px 0 0 15px !important;
+	background-color: rgba(0,0,0,0.3) !important;
+	border:0 !important;
+	color:white !important;
+}
+.search:focus{
+	 box-shadow:none !important;
+   outline:0px !important;
+}
+.type_msg{
+	background-color: rgba(0,0,0,0.3) !important;
+	border:0 !important;
+	color:white !important;
+	height: 60px !important;
+	overflow-y: auto;
+}
+	.type_msg:focus{
+	 box-shadow:none !important;
+   outline:0px !important;
+}
+.attach_btn{
+	border-radius: 15px 0 0 15px !important;
+	background-color: rgba(0,0,0,0.3) !important;
+	border:0 !important;
+	color: white !important;
+	cursor: pointer;
+}
+.send_btn{
+	border-radius: 0 15px 15px 0 !important;
+	background-color: rgba(0,0,0,0.3) !important;
+	border:0 !important;
+	color: white !important;
+	cursor: pointer;
+}
+.search_btn{
+	border-radius: 0 15px 15px 0 !important;
+	background-color: rgba(0,0,0,0.3) !important;
+	border:0 !important;
+	color: white !important;
+	cursor: pointer;
+}
+.contacts{
+	list-style: none;
+	padding: 0;
+}
+.contacts li{
+	width: 100% !important;
+	padding: 5px 10px;
+	margin-bottom: 15px !important;
+}
+.active{
+	background-color: rgba(0,0,0,0.3);
+}
+.user_img{
+	height: 70px;
+	width: 70px;
+	border:1.5px solid #f5f6fa;
+
+}
+.user_img_msg{
+	height: 40px;
+	width: 40px;
+	border:1.5px solid #f5f6fa;
+
+}
+.img_cont{
+	position: relative;
+	height: 70px;
+	width: 70px;
+}
+.img_cont_msg{
+	height: 40px;
+	width: 40px;
+}
+.online_icon{
+	position: absolute;
+	height: 15px;
+	width:15px;
+	background-color: #4cd137;
+	border-radius: 50%;
+	bottom: 0.2em;
+	right: 0.4em;
+	border:1.5px solid white;
+}
+.offline{
+	background-color: #c23616 !important;
+}
+.user_info{
+	margin-top: auto;
+	margin-bottom: auto;
+	margin-left: 15px;
+}
+.user_info span{
+	font-size: 20px;
+	color: white;
+}
+.user_info p{
+	font-size: 10px;
+	color: rgba(255,255,255,0.6);
+}
+.video_cam{
+	margin-left: 50px;
+	margin-top: 5px;
+}
+.video_cam span{
+	color: white;
+	font-size: 20px;
+	cursor: pointer;
+	margin-right: 20px;
+}
+.msg_cotainer{
+	margin-top: auto;
+	margin-bottom: auto;
+	margin-left: 10px;
+	border-radius: 25px;
+	background-color: rgb(82, 172, 255);
+	padding: 10px;
+	position: relative;
+}
+.msg_cotainer_send{
+	margin-top: auto;
+	margin-bottom: auto;
+	margin-right: 10px;
+	border-radius: 25px;
+	background-color: #58cc71;
+	padding: 10px;
+	position: relative;
+}
+.msg_time{
+	position: absolute;
+	left: 0;
+	bottom: -15px;
+	color: rgba(255,255,255,0.5);
+	font-size: 10px;
+}
+.msg_time_send{
+	position: absolute;
+	right:0;
+	bottom: -15px;
+	color: rgba(255,255,255,0.5);
+	font-size: 10px;
+}
+.msg_head{
+	position: relative;
+}
+#action_menu_btn{
+	position: absolute;
+	right: 10px;
+	top: 10px;
+	color: white;
+	cursor: pointer;
+	font-size: 20px;
+}
+.action_menu{
+	z-index: 1;
+	position: absolute;
+	padding: 15px 0;
+	background-color: rgba(0,0,0,0.5);
+	color: white;
+	border-radius: 15px;
+	top: 30px;
+	right: 15px;
+	display: none;
+}
+.action_menu ul{
+	list-style: none;
+	padding: 0;
+	margin: 0;
+}
+.action_menu ul li{
+	width: 100%;
+	padding: 10px 15px;
+	margin-bottom: 5px;
+}
+.action_menu ul li i{
+	padding-right: 10px;
+}
+.action_menu ul li:hover{
+	cursor: pointer;
+	background-color: rgba(0,0,0,0.2);
+}
+@media(max-width: 576px){
+	.contacts_card{
+	margin-bottom: 15px !important;
+}
+}

store_index.py

@@ -0,0 +1,40 @@
+from src.helper import load_pdf_file, text_split, download_hugging_face_embeddings
+from pinecone.grpc import PineconeGRPC as Pinecone
+from pinecone import ServerlessSpec
+from langchain_pinecone import PineconeVectorStore
+from dotenv import load_dotenv
+import os
+
+
+load_dotenv()
+
+PINECONE_API_KEY=os.environ.get('PINECONE_API_KEY')
+os.environ["PINECONE_API_KEY"] = PINECONE_API_KEY
+
+
+extracted_data=load_pdf_file(data='Data/')
+text_chunks=text_split(extracted_data)
+embeddings = download_hugging_face_embeddings()
+
+
+pc = Pinecone(api_key=PINECONE_API_KEY)
+
+index_name = "medicalbot"
+
+
+pc.create_index(
+    name=index_name,
+    dimension=384, 
+    metric="cosine", 
+    spec=ServerlessSpec(
+        cloud="aws", 
+        region="us-east-1"
+    ) 
+) 
+
+# Embed each chunk and upsert the embeddings into your Pinecone index.
+docsearch = PineconeVectorStore.from_documents(
+    documents=text_chunks,
+    index_name=index_name,
+    embedding=embeddings, 
+)

template.py

@@ -0,0 +1,36 @@
+import os
+from pathlib import Path
+import logging
+
+logging.basicConfig(level=logging.INFO, format='[%(asctime)s]: %(message)s:')
+
+
+list_of_files = [
+    "src/__init__.py",
+    "src/helper.py",
+    "src/prompt.py",
+    ".env",
+    "setup.py",
+    "app.py",
+    "research/trials.ipynb",
+   " test.py"
+]
+
+
+for filepath in list_of_files:
+    filepath = Path(filepath)
+    filedir, filename = os.path.split(filepath)
+
+
+    if filedir !="":
+        os.makedirs(filedir, exist_ok=True)
+        logging.info(f"Creating directory; {filedir} for the file: {filename}")
+
+    if (not os.path.exists(filepath)) or (os.path.getsize(filepath) == 0):
+        with open(filepath, "w") as f:
+            pass
+            logging.info(f"Creating empty file: {filepath}")
+
+
+    else:
+        logging.info(f"{filename} is already exists")

templates/chat.html

@@ -0,0 +1,81 @@
+<link href="//maxcdn.bootstrapcdn.com/bootstrap/4.1.1/css/bootstrap.min.css" rel="stylesheet" id="bootstrap-css">
+<script src="//maxcdn.bootstrapcdn.com/bootstrap/4.1.1/js/bootstrap.min.js"></script>
+<script src="//cdnjs.cloudflare.com/ajax/libs/jquery/3.2.1/jquery.min.js"></script>
+
+<!DOCTYPE html>
+<html>
+	<head>
+		<title>Chatbot</title>
+		<link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/css/bootstrap.min.css" integrity="sha384-MCw98/SFnGE8fJT3GXwEOngsV7Zt27NXFoaoApmYm81iuXoPkFOJwJ8ERdknLPMO" crossorigin="anonymous">
+		<link rel="stylesheet" href="https://use.fontawesome.com/releases/v5.5.0/css/all.css" integrity="sha384-B4dIYHKNBt8Bc12p+WXckhzcICo0wtJAoU8YZTY5qE0Id1GSseTk6S+L3BlXeVIU" crossorigin="anonymous">
+		<script src="https://ajax.googleapis.com/ajax/libs/jquery/3.3.1/jquery.min.js"></script>
+		<link rel="stylesheet" type="text/css" href="{{ url_for('static', filename='style.css')}}"/>
+	</head>
+	
+	
+	<body>
+		<div class="container-fluid h-100">
+			<div class="row justify-content-center h-100">		
+				<div class="col-md-8 col-xl-6 chat">
+					<div class="card">
+						<div class="card-header msg_head">
+							<div class="d-flex bd-highlight">
+								<div class="img_cont">
+									<img src="https://cdn-icons-png.flaticon.com/512/387/387569.png" class="rounded-circle user_img">
+									<!-- <img src="https://www.prdistribution.com/spirit/uploads/pressreleases/2019/newsreleases/d83341deb75c4c4f6b113f27b1e42cd8-chatbot-florence-already-helps-thousands-of-patients-to-remember-their-medication.png" class="rounded-circle user_img"> -->
+									<span class="online_icon"></span>
+								</div>
+								<div class="user_info">
+									<span>Medical Chatbot</span>
+									<p>Ask me anything!</p>
+								</div>
+							</div>
+						</div>
+						<div id="messageFormeight" class="card-body msg_card_body">
+							
+							
+						</div>
+						<div class="card-footer">
+							<form id="messageArea" class="input-group">
+                                <input type="text" id="text" name="msg" placeholder="Type your message..." autocomplete="off" class="form-control type_msg" required/>
+								<div class="input-group-append">
+									<button type="submit" id="send" class="input-group-text send_btn"><i class="fas fa-location-arrow"></i></button>
+								</div>
+							</form>
+						</div>
+					</div>
+				</div>
+			</div>
+		</div>
+		
+		<script>
+			$(document).ready(function() {
+				$("#messageArea").on("submit", function(event) {
+					const date = new Date();
+					const hour = date.getHours();
+					const minute = date.getMinutes();
+					const str_time = hour+":"+minute;
+					var rawText = $("#text").val();
+
+					var userHtml = '<div class="d-flex justify-content-end mb-4"><div class="msg_cotainer_send">' + rawText + '<span class="msg_time_send">'+ str_time + '</span></div><div class="img_cont_msg"><img src="https://i.ibb.co/d5b84Xw/Untitled-design.png" class="rounded-circle user_img_msg"></div></div>';
+					
+					$("#text").val("");
+					$("#messageFormeight").append(userHtml);
+
+					$.ajax({
+						data: {
+							msg: rawText,	
+						},
+						type: "POST",
+						url: "/get",
+					}).done(function(data) {
+						var botHtml = '<div class="d-flex justify-content-start mb-4"><div class="img_cont_msg"><img src="https://cdn-icons-png.flaticon.com/512/387/387569.png" class="rounded-circle user_img_msg"></div><div class="msg_cotainer">' + data + '<span class="msg_time">' + str_time + '</span></div></div>';
+						$("#messageFormeight").append($.parseHTML(botHtml));
+					});
+					event.preventDefault();
+				});
+			});
+		</script>
+        
+    </body>
+</html>