Add application file

Dockerfile

@@ -0,0 +1,14 @@
+FROM python:3.9
+
+RUN useradd -m -u 1000 user
+
+WORKDIR /app
+
+COPY --chown=user ./requirements.txt requirements.txt
+
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+COPY --chown=user . /app
+
+CMD ["flask", "run", "--host", "0.0.0.0:7860"]
+# CMD ["gunicorn", "-b", "--host", "0.0.0.0:7860", "main:app"]

app.py

@@ -0,0 +1,75 @@
+from flask import Flask,render_template,jsonify,request
+from src.helper import *
+from src.prompt import *
+
+from langchain_groq import ChatGroq
+from langchain_community.document_loaders import WebBaseLoader
+from langchain_community.embeddings import OllamaEmbeddings
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.chains.combine_documents import create_stuff_documents_chain
+from langchain_core.prompts import ChatPromptTemplate
+from langchain.chains import create_retrieval_chain
+from langchain_community.vectorstores import FAISS
+from langchain_community.document_loaders import PyPDFLoader
+from langchain_community.document_loaders import PyPDFDirectoryLoader
+from langchain_community.embeddings import HuggingFaceBgeEmbeddings
+# from langchain.vectorstores.cassandra import Cassandra
+from langchain_community.vectorstores import Cassandra
+from langchain.prompts import PromptTemplate
+from langchain_community.llms import Ollama
+from cassandra.auth import PlainTextAuthProvider
+import tempfile
+import cassio
+from PyPDF2 import PdfReader
+from cassandra.cluster import Cluster
+import warnings
+warnings.filterwarnings("ignore")
+import os
+from dotenv import load_dotenv
+import time
+load_dotenv()
+app = Flask(__name__)
+
+groq_api_key=os.environ['GROQ_API_KEY']
+LANGCHAIN_TRACING_V2="true"
+LANGCHAIN_API_KEY=os.getenv('LANGCHAIN_API_KEY')
+LANGCHAIN_PROJECT="medical_bot"
+LANGCHAIN_ENDPOINT="https://api.smith.langchain.com"
+
+prompt=PromptTemplate(template=prompt_template, input_variables=["context", "question"])
+# print(PROMPT)
+llm=ChatGroq(groq_api_key=groq_api_key,model_name="mixtral-8x7b-32768")
+file_path="data/Medical_book.pdf"
+pinecone_vector_store=doc_loader(file_path)
+
+print(type(pinecone_vector_store))
+def generate_response(llm,prompt,pinecone_vector_store,question):
+
+    # print('HELLO!Im from gen reponse fn')
+    document_chain=create_stuff_documents_chain(llm,prompt)
+    # print('document chain:',prompt)
+    retriever=pinecone_vector_store.as_retriever(search_type="similarity",search_kwargs={"k":5})
+    # print('HELLO!Im  after retriever')
+    retrieval_chain=create_retrieval_chain(retriever,document_chain)
+    # print('HELLO!Im  after retrieval chain')
+    response=retrieval_chain.invoke({"input":question})
+    # print('im response from fn',response)
+    return response
+
+@app.route("/")
+def index():
+    return render_template('chat.html')
+
+@app.route("/get", methods=["GET", "POST"])
+def chat():
+    msg = request.form["msg"]
+    question = msg
+    print(question)
+    result=generate_response(llm,prompt,pinecone_vector_store,question)
+    # print("Response : ", result['answer'])
+    return result['answer']
+
+    
+if __name__ == '__main__':
+    app.run(host="0.0.0.0", port= 8080, debug= True)
+    

requirements.txt

@@ -0,0 +1,35 @@
+ctransformers==0.2.5
+sentence-transformers==2.2.2
+langchain
+pinecone-client
+# langchain==0.0.225
+flask
+streamlit
+google-generativeai
+python-dotenv
+langchain
+PyPDF2
+chromadb
+faiss-cpu
+langchain_google_genai
+langchain-community
+pdf2image
+langsmith
+ollama
+langserve
+fastapi
+uvicorn
+sse_starlette
+bs4
+wikipedia
+arxiv
+langchainhub
+cassio
+beautifulsoup4
+langchain-groq
+sentence_transformers
+astrapy
+langchain_pinecone
+flask
+huggingface_hub[cli]
+-e .

src/helper.py

@@ -0,0 +1,149 @@
+import streamlit as st
+import os
+from langchain_groq import ChatGroq
+from langchain_community.document_loaders import WebBaseLoader
+from langchain_community.embeddings import OllamaEmbeddings
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.chains.combine_documents import create_stuff_documents_chain
+from langchain_core.prompts import ChatPromptTemplate
+from langchain.chains import create_retrieval_chain
+from langchain_community.vectorstores import FAISS
+from langchain_community.document_loaders import PyPDFLoader
+from langchain_community.document_loaders import PyPDFDirectoryLoader
+from langchain_community.embeddings import HuggingFaceBgeEmbeddings
+# from langchain.vectorstores.cassandra import Cassandra
+from langchain_community.vectorstores import Cassandra
+from langchain_community.llms import Ollama
+from cassandra.auth import PlainTextAuthProvider
+import tempfile
+import cassio
+from PyPDF2 import PdfReader
+from cassandra.cluster import Cluster
+import warnings
+from langchain.vectorstores import Pinecone
+import pinecone
+from pinecone import Pinecone, ServerlessSpec
+from langchain_pinecone import PineconeVectorStore
+warnings.filterwarnings("ignore")
+
+from dotenv import load_dotenv
+import time
+load_dotenv()
+
+ASTRA_DB_SECURE_BUNDLE_PATH ="G:/GENAI/Medical_chat_bot/src/secure-connect-medical-bot.zip"
+LANGCHAIN_TRACING_V2"]="true"
+LANGCHAIN_API_KEY=os.getenv('LANGCHAIN_API_KEY')
+LANGCHAIN_PROJECT="Medical_chatbot"
+LANGCHAIN_ENDPOINT="https://api.smith.langchain.com"
+
+def doc_loader(pdf_reader):
+    # print('im from doc_loc fn')
+    encode_kwargs = {'normalize_embeddings': True}
+    huggigface_embeddings=HuggingFaceBgeEmbeddings(
+    model_name='BAAI/bge-small-en-v1.5',
+    # model_name='sentence-transformers/all-MiniLM-16-v2',
+    model_kwargs={'device':'cpu'},
+    encode_kwargs=encode_kwargs)
+
+
+    loader=PyPDFLoader(pdf_reader)
+    documents=loader.load_and_split()
+    # print('iam after documents loader called')
+   
+    text_splitter=RecursiveCharacterTextSplitter(chunk_size=1000,chunk_overlap=200)
+    final_documents=text_splitter.split_documents(documents)
+    # print('iam after final_documents  called',final_documents)
+   
+    os.environ['PINECONE_API_KEY'] =  os.environ['pinecone']
+    os.environ['PINECONE_API_ENV'] =  "pdf_query_db"
+    pc = Pinecone(api_key=os.getenv('PINECONE_API_KEY'))
+    
+    index = pc.Index("pdf-query-index")
+    namespace = "pdf_query_medical"
+    
+    def namespace_exists(index, namespace):
+        try:
+            stats = index.describe_index_stats()
+            return namespace in stats['namespaces']
+        except pinecone.core.client.exceptions.NotFoundException:
+            return False
+    if namespace_exists(index, namespace):
+        print(f"Namespace '{namespace}' exist.")
+        pinecone_vector_store = PineconeVectorStore(embedding=huggigface_embeddings,index_name="pdf-query-index", namespace=namespace)
+        # pinecone_vector_store = index.query(f"SELECT * FROM {namespace}")
+        # return pinecone_vector_store
+    else:
+        print(f"Namespace '{namespace}' does not exist. It will be created upon upsertion.")
+
+
+        pinecone_vector_store=PineconeVectorStore(embedding=huggigface_embeddings,index_name="pdf-query-index",namespace=namespace)
+
+        pinecone_vector_store.add_documents(final_documents)
+
+    return pinecone_vector_store
+   
+    
+    
+
+# def doc_loader(pdf_reader):
+#     # print('im from doc_loc fn')
+#     encode_kwargs = {'normalize_embeddings': True}
+#     huggigface_embeddings=HuggingFaceBgeEmbeddings(
+#     model_name='BAAI/bge-small-en-v1.5',
+#     # model_name='sentence-transformers/all-MiniLM-16-v2',
+#     model_kwargs={'device':'cpu'},
+#     encode_kwargs=encode_kwargs)
+
+
+#     loader=PyPDFLoader(pdf_reader)
+#     documents=loader.load_and_split()
+#     # print('iam after documents loader called')
+   
+#     text_splitter=RecursiveCharacterTextSplitter(chunk_size=1000,chunk_overlap=200)
+#     final_documents=text_splitter.split_documents(documents)
+#     # print('iam after final_documents  called',final_documents)
+   
+#     astrasession = Cluster(
+#     cloud={"secure_connect_bundle": ASTRA_DB_SECURE_BUNDLE_PATH},
+#     auth_provider=PlainTextAuthProvider("token", ASTRA_DB_APPLICATION_TOKEN),
+#     ).connect()
+   
+   
+    
+#     check_table_query = f"""
+#     SELECT table_name FROM system_schema.tables 
+#     WHERE keyspace_name='{ASTRA_DB_KEYSPACE}' AND table_name='{ASTRA_DB_TABLE}';
+#     """
+
+  
+#     try:
+
+#         result = astrasession.execute(check_table_query)
+       
+#         if result.one():
+#             return_query=f""" select * from '{ASTRA_DB_KEYSPACE}'.'{ASTRA_DB_TABLE}'; """
+#             astra_vector_store=astrasession.execute(return_query)
+#             return astra_vector_store
+       
+       
+#         else:
+            
+#             print(f"Table {ASTRA_DB_KEYSPACE}.{ASTRA_DB_TABLE} does not exist. Try to create table.")
+    
+    
+#             astra_vector_store=Cassandra(
+#             embedding=huggigface_embeddings,
+#             table_name='medical_bot_demo',
+#             session=astrasession,
+#             keyspace=ASTRA_DB_KEYSPACE
+#             )
+
+        
+#             astra_vector_store.add_documents(final_documents)
+#             if astra_vector_store:
+#                 print("Vector store created successfully")
+
+#             return astra_vector_store
+#     except Exception as e:
+#         print(f"Error checking/creating keyspace: {e}")
+

src/prompt.py

@@ -0,0 +1,10 @@
+prompt_template="""
+Use the following pieces of information to answer the user's question.
+If you don't know the answer, just say that you don't know, don't try to make up an answer.
+
+Context: {context}
+Question: {input}
+
+Only return the helpful answer below and nothing else.
+Helpful answer:
+"""

src/secure-connect-medical-bot.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9976f3d6ec4a0d9459267c3bea8c2990695fff6b83b62cba92e5e5991c4c9dc
+size 12244

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;
+}
+}

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://i.ibb.co/fSNP7Rz/icons8-chatgpt-512.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://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_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>