commit

.gitignore

@@ -0,0 +1 @@
+.env

Career_Chatbot.egg-info/PKG-INFO

@@ -0,0 +1,5 @@
+Metadata-Version: 2.1
+Name: Career-Chatbot
+Version: 0.0.0
+Author: Shirlyn and Earvin
+Author-email: shirlynngure@gmail.com

Career_Chatbot.egg-info/SOURCES.txt

@@ -0,0 +1,8 @@
+setup.py
+Career_Chatbot.egg-info/PKG-INFO
+Career_Chatbot.egg-info/SOURCES.txt
+Career_Chatbot.egg-info/dependency_links.txt
+Career_Chatbot.egg-info/top_level.txt
+src/__init__.py
+src/helper.py
+src/prompt.py

Career_Chatbot.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

Career_Chatbot.egg-info/top_level.txt

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

Dockerfile

@@ -0,0 +1,17 @@
+FROM python:3.9
+
+RUN useradd -m -u 1000 user
+
+WORKDIR /app
+
+COPY --chown=user ./requirements.txt requirements.txt
+
+RUN pip install -r requirements.txt
+
+RUN pip install --upgrade sentence_transformers
+
+RUN pip install --upgrade langchain
+
+COPY --chown=user . /app
+
+CMD ["gunicorn", "app:app","-b","0.0.0.0:7860"]

Medical_Chatbot.egg-info/PKG-INFO

@@ -0,0 +1,5 @@
+Metadata-Version: 2.1
+Name: Medical-Chatbot
+Version: 0.0.0
+Author: Boktiar Ahmed Bappy
+Author-email: entbappy73@gmail.com

Medical_Chatbot.egg-info/SOURCES.txt

@@ -0,0 +1,8 @@
+setup.py
+Medical_Chatbot.egg-info/PKG-INFO
+Medical_Chatbot.egg-info/SOURCES.txt
+Medical_Chatbot.egg-info/dependency_links.txt
+Medical_Chatbot.egg-info/top_level.txt
+src/__init__.py
+src/helper.py
+src/prompt.py

Medical_Chatbot.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

Medical_Chatbot.egg-info/top_level.txt

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

app.py

@@ -0,0 +1,66 @@
+from flask import Flask, render_template, jsonify, request
+from src.helper import download_hugging_face_embeddings
+from langchain.vectorstores import Pinecone
+import pinecone
+from langchain.prompts import PromptTemplate
+from langchain.llms import CTransformers
+from langchain.chains import RetrievalQA
+from dotenv import load_dotenv
+from src.prompt import *
+import os
+from pinecone import Pinecone
+from langchain_pinecone import PineconeVectorStore
+from langchain.llms import Replicate
+app = Flask(__name__)
+
+load_dotenv()
+
+PINECONE_API_KEY = os.environ.get('PINECONE_API_KEY')
+PINECONE_API_ENV = os.environ.get('PINECONE_API_ENV')
+
+
+embeddings = download_hugging_face_embeddings()
+
+#Initializing the Pinecone
+index_name="clare"
+pc=Pinecone(api_key=PINECONE_API_KEY)
+index=pc.Index("clare")
+
+#Loading the index
+docsearch = PineconeVectorStore.from_existing_index(index_name, embeddings)
+
+
+PROMPT=PromptTemplate(template=prompt_template, input_variables=["context", "question"])
+
+chain_type_kwargs={"prompt": PROMPT}
+
+llm=Replicate(model="meta/meta-llama-3-8b")
+
+qa=RetrievalQA.from_chain_type(
+    llm=llm, 
+    chain_type="stuff", 
+    retriever=docsearch.as_retriever(search_kwargs={'k': 2}),
+    return_source_documents=True, 
+    chain_type_kwargs=chain_type_kwargs)
+
+
+
+@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)
+    result=qa({"query": input})
+    print("Response : ", result["result"])
+    return str(result["result"])
+
+
+
+if __name__ == '__main__':
+    app.run(host="0.0.0.0", port= 8080, debug= True)

medical-chatbot/trials.ipynb

@@ -0,0 +1,405 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "c:\\Users\\Admin\\AppData\\Local\\conda\\conda\\envs\\med\\lib\\site-packages\\pinecone\\data\\index.py:1: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from tqdm.autonotebook import tqdm\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain import PromptTemplate\n",
+    "from langchain.chains import RetrievalQA\n",
+    "from langchain.embeddings import HuggingFaceEmbeddings\n",
+    "import pinecone\n",
+    "from langchain.vectorstores import pinecone\n",
+    "from langchain.document_loaders import PyPDFLoader, DirectoryLoader\n",
+    "from langchain.prompts import PromptTemplate\n",
+    "from langchain.llms import CTransformers\n",
+    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
+    "from tqdm.autonotebook import tqdm"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Name: langchain\n",
+      "Version: 0.0.225\n",
+      "Summary: Building applications with LLMs through composability\n",
+      "Home-page: https://www.github.com/hwchase17/langchain\n",
+      "Author: \n",
+      "Author-email: \n",
+      "License: MIT\n",
+      "Location: c:\\users\\admin\\appdata\\local\\conda\\conda\\envs\\med\\lib\\site-packages\n",
+      "Requires: aiohttp, async-timeout, dataclasses-json, langchainplus-sdk, numexpr, numpy, openapi-schema-pydantic, pydantic, PyYAML, requests, SQLAlchemy, tenacity\n",
+      "Required-by: langchain-community\n",
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
+   "source": [
+    "pip show langchain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "PINECONE_API_KEY = \"4b6b83c2-dc68-4bad-ae31-9642bc3be58e\"\n",
+    "PINECONE_API_ENV = \"us-east-1\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Extract the data from the pdf book\n",
+    "def load_data(data):\n",
+    "    loader = DirectoryLoader(data,\n",
+    "    glob=\"*.pdf\",\n",
+    "    loader_cls=PyPDFLoader)\n",
+    "\n",
+    "    documents = loader.load()\n",
+    "    return documents\n",
+    "    "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Requirement already satisfied: pyPDF in c:\\users\\admin\\appdata\\local\\conda\\conda\\envs\\med\\lib\\site-packages (4.2.0)\n",
+      "Requirement already satisfied: typing_extensions>=4.0 in c:\\users\\admin\\appdata\\local\\conda\\conda\\envs\\med\\lib\\site-packages (from pyPDF) (4.11.0)\n",
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
+   "source": [
+    "pip install pyPDF"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Name: pypdf\n",
+      "Version: 4.2.0\n",
+      "Summary: A pure-python PDF library capable of splitting, merging, cropping, and transforming PDF files\n",
+      "Home-page: \n",
+      "Author: \n",
+      "Author-email: Mathieu Fenniak <biziqe@mathieu.fenniak.net>\n",
+      "License: \n",
+      "Location: c:\\users\\admin\\appdata\\local\\conda\\conda\\envs\\med\\lib\\site-packages\n",
+      "Requires: typing_extensions\n",
+      "Required-by: \n",
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
+   "source": [
+    "pip show pyPDF"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Data Extracted\n"
+     ]
+    }
+   ],
+   "source": [
+    "extracted_pdf = load_data(\"data/\")\n",
+    "print(\"Data Extracted\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#extracted_data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#create text Chunks\n",
+    "def text_split(extracted_pdf):\n",
+    "    text_splitter = RecursiveCharacterTextSplitter(chunk_size=500,\n",
+    "                                   chunk_overlap=20)\n",
+    "    text_chunks=text_splitter.split_documents(extracted_pdf)\n",
+    "    return text_chunks "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "chunks created\n",
+      "The number of chunks is: 10484\n"
+     ]
+    }
+   ],
+   "source": [
+    "text_chunks = text_split(extracted_pdf)\n",
+    "print(\"chunks created\")\n",
+    "print(\"The number of chunks is:\",len(text_chunks))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#download embedding model\n",
+    "def download_huggingfaceembedding():\n",
+    "    embedding = HuggingFaceEmbeddings(model_name=\"TheBloke/Llama-2-7B-Chat-GGML\")\n",
+    "    return embedding"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "KeyboardInterrupt",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[17], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m embedding \u001b[38;5;241m=\u001b[39m \u001b[43mdownload_huggingfaceembedding\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n",
+      "Cell \u001b[1;32mIn[14], line 3\u001b[0m, in \u001b[0;36mdownload_huggingfaceembedding\u001b[1;34m()\u001b[0m\n\u001b[0;32m      2\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mdownload_huggingfaceembedding\u001b[39m():\n\u001b[1;32m----> 3\u001b[0m     embedding \u001b[38;5;241m=\u001b[39m \u001b[43mHuggingFaceEmbeddings\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmodel_name\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mTheBloke/Llama-2-7B-Chat-GGML\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[0;32m      4\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m embedding\n",
+      "File \u001b[1;32mc:\\Users\\Admin\\AppData\\Local\\conda\\conda\\envs\\med\\lib\\site-packages\\langchain\\embeddings\\huggingface.py:59\u001b[0m, in \u001b[0;36mHuggingFaceEmbeddings.__init__\u001b[1;34m(self, **kwargs)\u001b[0m\n\u001b[0;32m     53\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mImportError\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m exc:\n\u001b[0;32m     54\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mImportError\u001b[39;00m(\n\u001b[0;32m     55\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mCould not import sentence_transformers python package. \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m     56\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mPlease install it with `pip install sentence_transformers`.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m     57\u001b[0m     ) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mexc\u001b[39;00m\n\u001b[1;32m---> 59\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mclient \u001b[38;5;241m=\u001b[39m \u001b[43msentence_transformers\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mSentenceTransformer\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m     60\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmodel_name\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcache_folder\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcache_folder\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmodel_kwargs\u001b[49m\n\u001b[0;32m     61\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[1;32mc:\\Users\\Admin\\AppData\\Local\\conda\\conda\\envs\\med\\lib\\site-packages\\sentence_transformers\\SentenceTransformer.py:87\u001b[0m, in \u001b[0;36mSentenceTransformer.__init__\u001b[1;34m(self, model_name_or_path, modules, device, cache_folder, use_auth_token)\u001b[0m\n\u001b[0;32m     83\u001b[0m     model_path \u001b[38;5;241m=\u001b[39m os\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;241m.\u001b[39mjoin(cache_folder, model_name_or_path\u001b[38;5;241m.\u001b[39mreplace(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m/\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m_\u001b[39m\u001b[38;5;124m\"\u001b[39m))\n\u001b[0;32m     85\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m os\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;241m.\u001b[39mexists(os\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;241m.\u001b[39mjoin(model_path, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mmodules.json\u001b[39m\u001b[38;5;124m'\u001b[39m)):\n\u001b[0;32m     86\u001b[0m         \u001b[38;5;66;03m# Download from hub with caching\u001b[39;00m\n\u001b[1;32m---> 87\u001b[0m         \u001b[43msnapshot_download\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmodel_name_or_path\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m     88\u001b[0m \u001b[43m                            \u001b[49m\u001b[43mcache_dir\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcache_folder\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m     89\u001b[0m \u001b[43m                            \u001b[49m\u001b[43mlibrary_name\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43msentence-transformers\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[0;32m     90\u001b[0m \u001b[43m                            \u001b[49m\u001b[43mlibrary_version\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m__version__\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m     91\u001b[0m \u001b[43m                            \u001b[49m\u001b[43mignore_files\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mflax_model.msgpack\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mrust_model.ot\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mtf_model.h5\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m     92\u001b[0m \u001b[43m                            \u001b[49m\u001b[43muse_auth_token\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43muse_auth_token\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m     94\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m os\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;241m.\u001b[39mexists(os\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;241m.\u001b[39mjoin(model_path, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mmodules.json\u001b[39m\u001b[38;5;124m'\u001b[39m)):    \u001b[38;5;66;03m#Load as SentenceTransformer model\u001b[39;00m\n\u001b[0;32m     95\u001b[0m     modules \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_load_sbert_model(model_path)\n",
+      "File \u001b[1;32mc:\\Users\\Admin\\AppData\\Local\\conda\\conda\\envs\\med\\lib\\site-packages\\sentence_transformers\\util.py:491\u001b[0m, in \u001b[0;36msnapshot_download\u001b[1;34m(repo_id, revision, cache_dir, library_name, library_version, user_agent, ignore_files, use_auth_token)\u001b[0m\n\u001b[0;32m    486\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m version\u001b[38;5;241m.\u001b[39mparse(huggingface_hub\u001b[38;5;241m.\u001b[39m__version__) \u001b[38;5;241m>\u001b[39m\u001b[38;5;241m=\u001b[39m version\u001b[38;5;241m.\u001b[39mparse(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m0.8.1\u001b[39m\u001b[38;5;124m\"\u001b[39m):\n\u001b[0;32m    487\u001b[0m     \u001b[38;5;66;03m# huggingface_hub v0.8.1 introduces a new cache layout. We sill use a manual layout\u001b[39;00m\n\u001b[0;32m    488\u001b[0m     \u001b[38;5;66;03m# And need to pass legacy_cache_layout=True to avoid that a warning will be printed\u001b[39;00m\n\u001b[0;32m    489\u001b[0m     cached_download_args[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mlegacy_cache_layout\u001b[39m\u001b[38;5;124m'\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[1;32m--> 491\u001b[0m path \u001b[38;5;241m=\u001b[39m \u001b[43mcached_download\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mcached_download_args\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    493\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m os\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;241m.\u001b[39mexists(path \u001b[38;5;241m+\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m.lock\u001b[39m\u001b[38;5;124m\"\u001b[39m):\n\u001b[0;32m    494\u001b[0m     os\u001b[38;5;241m.\u001b[39mremove(path \u001b[38;5;241m+\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m.lock\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
+      "File \u001b[1;32mc:\\Users\\Admin\\AppData\\Local\\conda\\conda\\envs\\med\\lib\\site-packages\\huggingface_hub\\utils\\_validators.py:114\u001b[0m, in \u001b[0;36mvalidate_hf_hub_args.<locals>._inner_fn\u001b[1;34m(*args, **kwargs)\u001b[0m\n\u001b[0;32m    111\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m check_use_auth_token:\n\u001b[0;32m    112\u001b[0m     kwargs \u001b[38;5;241m=\u001b[39m smoothly_deprecate_use_auth_token(fn_name\u001b[38;5;241m=\u001b[39mfn\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m, has_token\u001b[38;5;241m=\u001b[39mhas_token, kwargs\u001b[38;5;241m=\u001b[39mkwargs)\n\u001b[1;32m--> 114\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[1;32mc:\\Users\\Admin\\AppData\\Local\\conda\\conda\\envs\\med\\lib\\site-packages\\huggingface_hub\\file_download.py:797\u001b[0m, in \u001b[0;36mcached_download\u001b[1;34m(url, library_name, library_version, cache_dir, user_agent, force_download, force_filename, proxies, etag_timeout, resume_download, token, local_files_only, legacy_cache_layout)\u001b[0m\n\u001b[0;32m    794\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m os\u001b[38;5;241m.\u001b[39mname \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mnt\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(os\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;241m.\u001b[39mabspath(cache_path)) \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m255\u001b[39m:\n\u001b[0;32m    795\u001b[0m     cache_path \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;130;01m\\\\\u001b[39;00m\u001b[38;5;130;01m\\\\\u001b[39;00m\u001b[38;5;124m?\u001b[39m\u001b[38;5;130;01m\\\\\u001b[39;00m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;241m+\u001b[39m os\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;241m.\u001b[39mabspath(cache_path)\n\u001b[1;32m--> 797\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m WeakFileLock(lock_path):\n\u001b[0;32m    798\u001b[0m     _download_to_tmp_and_move(\n\u001b[0;32m    799\u001b[0m         incomplete_path\u001b[38;5;241m=\u001b[39mPath(cache_path \u001b[38;5;241m+\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m.incomplete\u001b[39m\u001b[38;5;124m\"\u001b[39m),\n\u001b[0;32m    800\u001b[0m         destination_path\u001b[38;5;241m=\u001b[39mPath(cache_path),\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m    806\u001b[0m         force_download\u001b[38;5;241m=\u001b[39mforce_download,\n\u001b[0;32m    807\u001b[0m     )\n\u001b[0;32m    809\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m force_filename \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n",
+      "File \u001b[1;32mc:\\Users\\Admin\\AppData\\Local\\conda\\conda\\envs\\med\\lib\\contextlib.py:113\u001b[0m, in \u001b[0;36m_GeneratorContextManager.__enter__\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m    111\u001b[0m \u001b[38;5;28;01mdel\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39margs, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mkwds, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfunc\n\u001b[0;32m    112\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m--> 113\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mnext\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgen\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    114\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mStopIteration\u001b[39;00m:\n\u001b[0;32m    115\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mRuntimeError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mgenerator didn\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mt yield\u001b[39m\u001b[38;5;124m\"\u001b[39m) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n",
+      "File \u001b[1;32mc:\\Users\\Admin\\AppData\\Local\\conda\\conda\\envs\\med\\lib\\site-packages\\huggingface_hub\\utils\\_fixes.py:84\u001b[0m, in \u001b[0;36mWeakFileLock\u001b[1;34m(lock_file)\u001b[0m\n\u001b[0;32m     82\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"A filelock that won't raise an exception if release fails.\"\"\"\u001b[39;00m\n\u001b[0;32m     83\u001b[0m lock \u001b[38;5;241m=\u001b[39m FileLock(lock_file)\n\u001b[1;32m---> 84\u001b[0m \u001b[43mlock\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43macquire\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m     86\u001b[0m \u001b[38;5;28;01myield\u001b[39;00m lock\n\u001b[0;32m     88\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n",
+      "File \u001b[1;32mc:\\Users\\Admin\\AppData\\Local\\conda\\conda\\envs\\med\\lib\\site-packages\\filelock\\_api.py:333\u001b[0m, in \u001b[0;36mBaseFileLock.acquire\u001b[1;34m(self, timeout, poll_interval, poll_intervall, blocking)\u001b[0m\n\u001b[0;32m    331\u001b[0m         msg \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mLock \u001b[39m\u001b[38;5;132;01m%s\u001b[39;00m\u001b[38;5;124m not acquired on \u001b[39m\u001b[38;5;132;01m%s\u001b[39;00m\u001b[38;5;124m, waiting \u001b[39m\u001b[38;5;132;01m%s\u001b[39;00m\u001b[38;5;124m seconds ...\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m    332\u001b[0m         _LOGGER\u001b[38;5;241m.\u001b[39mdebug(msg, lock_id, lock_filename, poll_interval)\n\u001b[1;32m--> 333\u001b[0m         \u001b[43mtime\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msleep\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpoll_interval\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    334\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m:  \u001b[38;5;66;03m# Something did go wrong, so decrement the counter.\u001b[39;00m\n\u001b[0;32m    335\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_context\u001b[38;5;241m.\u001b[39mlock_counter \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mmax\u001b[39m(\u001b[38;5;241m0\u001b[39m, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_context\u001b[38;5;241m.\u001b[39mlock_counter \u001b[38;5;241m-\u001b[39m \u001b[38;5;241m1\u001b[39m)\n",
+      "\u001b[1;31mKeyboardInterrupt\u001b[0m: "
+     ]
+    }
+   ],
+   "source": [
+    "embedding = download_huggingfaceembedding()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "NameError",
+     "evalue": "name 'embedding' is not defined",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[15], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m \u001b[43membedding\u001b[49m\n",
+      "\u001b[1;31mNameError\u001b[0m: name 'embedding' is not defined"
+     ]
+    }
+   ],
+   "source": [
+    "embedding"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "NameError",
+     "evalue": "name 'embedding' is not defined",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[18], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m query_result \u001b[38;5;241m=\u001b[39m \u001b[43membedding\u001b[49m\u001b[38;5;241m.\u001b[39membed_query(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mHello World!\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m      2\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mLength:\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28mlen\u001b[39m(query_result))\n\u001b[0;32m      3\u001b[0m query_result\n",
+      "\u001b[1;31mNameError\u001b[0m: name 'embedding' is not defined"
+     ]
+    }
+   ],
+   "source": [
+    "query_result = embedding.embed_query(\"Hello World!\")\n",
+    "print(\"Length:\", len(query_result))\n",
+    "query_result"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Requirement already satisfied: pinecone.client in c:\\users\\admin\\appdata\\local\\conda\\conda\\envs\\med\\lib\\site-packages (4.1.1)\n",
+      "Requirement already satisfied: certifi>=2019.11.17 in c:\\users\\admin\\appdata\\local\\conda\\conda\\envs\\med\\lib\\site-packages (from pinecone.client) (2024.6.2)\n",
+      "Requirement already satisfied: pinecone-plugin-interface<0.0.8,>=0.0.7 in c:\\users\\admin\\appdata\\local\\conda\\conda\\envs\\med\\lib\\site-packages (from pinecone.client) (0.0.7)\n",
+      "Requirement already satisfied: tqdm>=4.64.1 in c:\\users\\admin\\appdata\\roaming\\python\\python38\\site-packages (from pinecone.client) (4.66.4)\n",
+      "Requirement already satisfied: typing-extensions>=3.7.4 in c:\\users\\admin\\appdata\\local\\conda\\conda\\envs\\med\\lib\\site-packages (from pinecone.client) (4.11.0)\n",
+      "Requirement already satisfied: urllib3>=1.26.0 in c:\\users\\admin\\appdata\\local\\conda\\conda\\envs\\med\\lib\\site-packages (from pinecone.client) (2.2.1)\n",
+      "Requirement already satisfied: colorama in c:\\users\\admin\\appdata\\local\\conda\\conda\\envs\\med\\lib\\site-packages (from tqdm>=4.64.1->pinecone.client) (0.4.6)\n",
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
+   "source": [
+    "pip install pinecone.client"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# After having my index, we can load it like this - \n",
+    "\n",
+    "\n",
+    "query = \"What are Allegies?\"\n",
+    "\n",
+    "docs = docsearch.similarity_search(query=query, k=3)\n",
+    "\n",
+    "print(\"Result:\", docs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prompt_template = \"\"\"\n",
+    "Use the following piece of information to answer the user's question.\n",
+    "If you don't know the answer, just say that you don't know, don't try to generate any random answer from your own\n",
+    "\n",
+    "Context:{context}\n",
+    "Question:{question}\n",
+    "\n",
+    "Only return the helpful answer and nothing else\n",
+    "helpful answer:\n",
+    "\"\"\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "PROMPT = PromptTemplate(template=prompt_template, input_variables=[\"context\",\"question\"])\n",
+    "chain_type_kwargs = {\"prompt\":PROMPT}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = CTransformers(model=\"model/llama-2-7b-chat.ggmlv3.q4_0.bin\",\n",
+    "                    model_type=\"llama\",\n",
+    "                    config={\"max_new_tokens\":512,\n",
+    "                            'temperature':0.8})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "qa = RetrievalQA.from_chain_type(\n",
+    "    llm=llm,\n",
+    "    chain_type=\"stuff\",\n",
+    "    retriever= docsearch.as_retriever(search_kwargs={\"k\":2}),\n",
+    "    return_source_documents = True,\n",
+    "    chain_type_kwargs=chain_type_kwargs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "while True:\n",
+    "    user_input = input(f\"Input Prompt: \")\n",
+    "    result = qa({\"query\":user_input})\n",
+    "    print(\"Response:\", result[\"result\"])"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "medchatbot",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.19"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

requirements.txt

@@ -0,0 +1,13 @@
+ctransformers
+sentence-transformers==2.2.2
+pinecone-client
+langchain==0.0.225
+flask
+pypdf
+python-dotenv
+pinecone
+langchain_community
+sentence_transformers
+langchain_pinecone
+gunicorn
+PyPDF2

research/trials.ipynb

@@ -0,0 +1,1164 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\Admin\\AppData\\Roaming\\Python\\Python38\\site-packages\\pinecone\\data\\index.py:1: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from tqdm.autonotebook import tqdm\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain import PromptTemplate\n",
+    "from langchain.chains import RetrievalQA\n",
+    "from langchain.embeddings import HuggingFaceEmbeddings\n",
+    "from langchain.vectorstores import Pinecone\n",
+    "import pinecone\n",
+    "from langchain.document_loaders import PyPDFLoader, DirectoryLoader\n",
+    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
+    "from langchain.prompts import PromptTemplate\n",
+    "from langchain.llms import CTransformers\n",
+    "import os\n",
+    "from langchain.llms import Replicate"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Extract data from the PDF\n",
+    "def load_pdf(data):\n",
+    "    loader = DirectoryLoader(data,\n",
+    "                    glob=\"*.pdf\",\n",
+    "                    loader_cls=PyPDFLoader)\n",
+    "    \n",
+    "    documents = loader.load()\n",
+    "\n",
+    "    return documents"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "FileNotFoundError",
+     "evalue": "Directory not found: 'Careers.pdf'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mFileNotFoundError\u001b[0m                         Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[16], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m extracted_data \u001b[38;5;241m=\u001b[39m \u001b[43mload_pdf\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mCareers.pdf\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n",
+      "Cell \u001b[1;32mIn[3], line 7\u001b[0m, in \u001b[0;36mload_pdf\u001b[1;34m(data)\u001b[0m\n\u001b[0;32m      2\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mload_pdf\u001b[39m(data):\n\u001b[0;32m      3\u001b[0m     loader \u001b[38;5;241m=\u001b[39m DirectoryLoader(data,\n\u001b[0;32m      4\u001b[0m                     glob\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m*.pdf\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[0;32m      5\u001b[0m                     loader_cls\u001b[38;5;241m=\u001b[39mPyPDFLoader)\n\u001b[1;32m----> 7\u001b[0m     documents \u001b[38;5;241m=\u001b[39m \u001b[43mloader\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mload\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m      9\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m documents\n",
+      "File \u001b[1;32m~\\AppData\\Roaming\\Python\\Python38\\site-packages\\langchain_community\\document_loaders\\directory.py:117\u001b[0m, in \u001b[0;36mDirectoryLoader.load\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m    115\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mload\u001b[39m(\u001b[38;5;28mself\u001b[39m) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m List[Document]:\n\u001b[0;32m    116\u001b[0m \u001b[38;5;250m    \u001b[39m\u001b[38;5;124;03m\"\"\"Load documents.\"\"\"\u001b[39;00m\n\u001b[1;32m--> 117\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mlist\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mlazy_load\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[1;32m~\\AppData\\Roaming\\Python\\Python38\\site-packages\\langchain_community\\document_loaders\\directory.py:123\u001b[0m, in \u001b[0;36mDirectoryLoader.lazy_load\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m    121\u001b[0m p \u001b[38;5;241m=\u001b[39m Path(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpath)\n\u001b[0;32m    122\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m p\u001b[38;5;241m.\u001b[39mexists():\n\u001b[1;32m--> 123\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mFileNotFoundError\u001b[39;00m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mDirectory not found: \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m    124\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m p\u001b[38;5;241m.\u001b[39mis_dir():\n\u001b[0;32m    125\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mExpected directory, got file: \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
+      "\u001b[1;31mFileNotFoundError\u001b[0m: Directory not found: 'Careers.pdf'"
+     ]
+    }
+   ],
+   "source": [
+    "\n",
+    "extracted_data = load_pdf(\"Data/\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#extracted_data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#create text Chunks\n",
+    "def text_split(extracted_pdf):\n",
+    "    text_splitter = RecursiveCharacterTextSplitter(chunk_size=500,\n",
+    "                                   chunk_overlap=20)\n",
+    "    text_chunks=text_splitter.split_documents(extracted_pdf)\n",
+    "    return text_chunks "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "chunks created\n",
+      "The number of chunks is: 15409\n"
+     ]
+    }
+   ],
+   "source": [
+    "text_chunks = text_split(extracted_data)\n",
+    "print(\"chunks created\")\n",
+    "print(\"The number of chunks is:\",len(text_chunks))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#download embedding model\n",
+    "def download_hugging_face_embeddings():\n",
+    "    embeddings = HuggingFaceEmbeddings(model_name=\"sentence-transformers/all-MiniLM-L6-v2\")\n",
+    "    return embeddings"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\Admin\\AppData\\Roaming\\Python\\Python38\\site-packages\\langchain_core\\_api\\deprecation.py:119: LangChainDeprecationWarning: The class `HuggingFaceEmbeddings` was deprecated in LangChain 0.2.2 and will be removed in 0.3.0. An updated version of the class exists in the langchain-huggingface package and should be used instead. To use it run `pip install -U langchain-huggingface` and import as `from langchain_huggingface import HuggingFaceEmbeddings`.\n",
+      "  warn_deprecated(\n",
+      "C:\\Users\\Admin\\AppData\\Roaming\\Python\\Python38\\site-packages\\huggingface_hub\\file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.\n",
+      "  warnings.warn(\n"
+     ]
+    }
+   ],
+   "source": [
+    "embeddings = download_hugging_face_embeddings()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "HuggingFaceEmbeddings(client=SentenceTransformer(\n",
+       "  (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel \n",
+       "  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})\n",
+       "  (2): Normalize()\n",
+       "), model_name='sentence-transformers/all-MiniLM-L6-v2', cache_folder=None, model_kwargs={}, encode_kwargs={}, multi_process=False, show_progress=False)"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "embeddings"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Length: 384\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "[-0.020386872813105583,\n",
+       " 0.02528088353574276,\n",
+       " -0.0005662009352818131,\n",
+       " 0.011615470983088017,\n",
+       " -0.037988364696502686,\n",
+       " -0.11998124420642853,\n",
+       " 0.041709501296281815,\n",
+       " -0.020857175812125206,\n",
+       " -0.05900680273771286,\n",
+       " 0.024232536554336548,\n",
+       " 0.06212019547820091,\n",
+       " 0.06767985969781876,\n",
+       " 0.03310026600956917,\n",
+       " -0.010369333438575268,\n",
+       " -0.031215619295835495,\n",
+       " -0.032733283936977386,\n",
+       " -0.002111728535965085,\n",
+       " 0.009261957369744778,\n",
+       " -0.12476464360952377,\n",
+       " 0.011236833408474922,\n",
+       " 0.03904539346694946,\n",
+       " 0.054402466863393784,\n",
+       " -0.0028255104552954435,\n",
+       " 0.04455625265836716,\n",
+       " -0.0854201465845108,\n",
+       " -0.022873710840940475,\n",
+       " 0.039140552282333374,\n",
+       " 0.03604690730571747,\n",
+       " -0.0321267768740654,\n",
+       " -0.06425873190164566,\n",
+       " 0.05812908709049225,\n",
+       " 0.04669089987874031,\n",
+       " 0.08061555027961731,\n",
+       " -0.0077342689037323,\n",
+       " -0.022083202376961708,\n",
+       " 0.06713154911994934,\n",
+       " -0.04504143446683884,\n",
+       " -0.10212118923664093,\n",
+       " 0.0012643759837374091,\n",
+       " 0.04680193215608597,\n",
+       " 0.02639589086174965,\n",
+       " -0.06990959495306015,\n",
+       " -0.04453347623348236,\n",
+       " -0.006901898421347141,\n",
+       " 0.019288599491119385,\n",
+       " 0.02059079520404339,\n",
+       " 0.006518140435218811,\n",
+       " 0.035493891686201096,\n",
+       " 0.10393310338258743,\n",
+       " 0.01750371791422367,\n",
+       " -0.04294285178184509,\n",
+       " -0.057037338614463806,\n",
+       " -0.011423510499298573,\n",
+       " 0.009236752055585384,\n",
+       " 0.04582153260707855,\n",
+       " 0.0070036184042692184,\n",
+       " 0.02421007864177227,\n",
+       " -0.06064579635858536,\n",
+       " -0.014943967573344707,\n",
+       " -0.0305157620459795,\n",
+       " -0.06836125254631042,\n",
+       " 0.05706855654716492,\n",
+       " -0.03227071464061737,\n",
+       " 0.04119705408811569,\n",
+       " 0.09017682075500488,\n",
+       " -0.07689837366342545,\n",
+       " -0.022328900173306465,\n",
+       " 0.02609133906662464,\n",
+       " -0.057754434645175934,\n",
+       " -0.060503143817186356,\n",
+       " -0.043829482048749924,\n",
+       " 0.010114436037838459,\n",
+       " 0.03421920910477638,\n",
+       " 0.07573983073234558,\n",
+       " -0.04518907144665718,\n",
+       " 0.005837503354996443,\n",
+       " 0.0184907466173172,\n",
+       " -0.0018646110547706485,\n",
+       " 0.017705997452139854,\n",
+       " 0.054946303367614746,\n",
+       " 0.06722188740968704,\n",
+       " -0.10008065402507782,\n",
+       " 0.017738861963152885,\n",
+       " 0.043243926018476486,\n",
+       " 0.01077823992818594,\n",
+       " -0.014706484042108059,\n",
+       " -0.013241068460047245,\n",
+       " -0.001782232546247542,\n",
+       " -0.045426856726408005,\n",
+       " -0.03418899327516556,\n",
+       " -0.14636532962322235,\n",
+       " -0.011157987639307976,\n",
+       " -0.011241820640861988,\n",
+       " 0.011740676127374172,\n",
+       " -0.08864285796880722,\n",
+       " -0.028394203633069992,\n",
+       " 0.07532472908496857,\n",
+       " -0.018445875495672226,\n",
+       " -0.17038744688034058,\n",
+       " 0.15587182343006134,\n",
+       " 0.022921469062566757,\n",
+       " 0.046667248010635376,\n",
+       " 0.040010735392570496,\n",
+       " 0.02375500649213791,\n",
+       " 0.049802809953689575,\n",
+       " 0.030321596190333366,\n",
+       " 0.0003741529362741858,\n",
+       " 0.06957260519266129,\n",
+       " -0.022312656044960022,\n",
+       " -0.02747281827032566,\n",
+       " 0.006083943415433168,\n",
+       " -0.04853246361017227,\n",
+       " 0.049238789826631546,\n",
+       " -0.007612141780555248,\n",
+       " 0.06917710602283478,\n",
+       " -0.07174898684024811,\n",
+       " -0.020257242023944855,\n",
+       " 0.014374688267707825,\n",
+       " -0.030236804857850075,\n",
+       " 0.004180468153208494,\n",
+       " 0.05348922684788704,\n",
+       " -0.058872416615486145,\n",
+       " 0.023056630045175552,\n",
+       " 0.013102822005748749,\n",
+       " 0.01088209543377161,\n",
+       " 0.02322239615023136,\n",
+       " 0.028361210599541664,\n",
+       " -3.843664856439317e-33,\n",
+       " 0.0435662642121315,\n",
+       " -0.003594552166759968,\n",
+       " 0.042123064398765564,\n",
+       " 0.1231817975640297,\n",
+       " 0.017473308369517326,\n",
+       " 0.00942733883857727,\n",
+       " -0.09451454132795334,\n",
+       " -0.021238375455141068,\n",
+       " 0.03426387161016464,\n",
+       " 0.025959163904190063,\n",
+       " 0.028061239048838615,\n",
+       " 0.012698487378656864,\n",
+       " -0.04617796093225479,\n",
+       " 0.030305471271276474,\n",
+       " -0.045230939984321594,\n",
+       " 0.11220850050449371,\n",
+       " -0.09135962277650833,\n",
+       " -0.013798639178276062,\n",
+       " 0.025815125554800034,\n",
+       " 0.08335626125335693,\n",
+       " -0.07693815231323242,\n",
+       " -0.010359508916735649,\n",
+       " 0.009555504657328129,\n",
+       " 0.08872868865728378,\n",
+       " -0.009140676818788052,\n",
+       " 0.008417350240051746,\n",
+       " 0.010792146436870098,\n",
+       " -0.09071637690067291,\n",
+       " 0.09623939543962479,\n",
+       " 0.007239796221256256,\n",
+       " -0.03825897350907326,\n",
+       " -0.05111745372414589,\n",
+       " 0.020446274429559708,\n",
+       " 0.01577543467283249,\n",
+       " -0.00584018137305975,\n",
+       " 0.011155584827065468,\n",
+       " -0.007191200274974108,\n",
+       " -0.07329276949167252,\n",
+       " -0.07283007353544235,\n",
+       " -0.006110389716923237,\n",
+       " -0.05931411683559418,\n",
+       " 0.045463789254426956,\n",
+       " 0.04360096901655197,\n",
+       " -0.007337683811783791,\n",
+       " -0.02558256685733795,\n",
+       " -0.0344063900411129,\n",
+       " 0.02559274062514305,\n",
+       " 0.018136944621801376,\n",
+       " 0.04025298357009888,\n",
+       " 0.03997461870312691,\n",
+       " -0.04333764687180519,\n",
+       " 0.008319374173879623,\n",
+       " -0.03883630037307739,\n",
+       " 0.05585148185491562,\n",
+       " -0.010561023838818073,\n",
+       " 0.01699744537472725,\n",
+       " 0.04742543399333954,\n",
+       " -0.048003457486629486,\n",
+       " -0.013104816898703575,\n",
+       " 0.046607110649347305,\n",
+       " -0.003912207204848528,\n",
+       " 0.10242760181427002,\n",
+       " -0.04255157709121704,\n",
+       " -0.028219876810908318,\n",
+       " -0.008180612698197365,\n",
+       " -0.01885264366865158,\n",
+       " 0.05203333869576454,\n",
+       " 0.033868011087179184,\n",
+       " 0.059511031955480576,\n",
+       " 0.004061603918671608,\n",
+       " -0.01956753432750702,\n",
+       " 0.02674257941544056,\n",
+       " 0.02093179151415825,\n",
+       " 0.02192043699324131,\n",
+       " 0.012750852853059769,\n",
+       " 0.05398520082235336,\n",
+       " 0.052067991346120834,\n",
+       " -0.0031074492726475,\n",
+       " 0.02487236261367798,\n",
+       " -0.07944536954164505,\n",
+       " 0.028617681935429573,\n",
+       " -0.0007746760384179652,\n",
+       " -0.003381764981895685,\n",
+       " -0.05178724229335785,\n",
+       " 0.09358307719230652,\n",
+       " 0.018984489142894745,\n",
+       " -0.009582558646798134,\n",
+       " -0.0856575071811676,\n",
+       " -0.017498208209872246,\n",
+       " -0.004158390685915947,\n",
+       " -0.06506012380123138,\n",
+       " 0.05912616476416588,\n",
+       " 0.035769641399383545,\n",
+       " -0.005036777351051569,\n",
+       " -0.08909005671739578,\n",
+       " 2.5757033649164638e-33,\n",
+       " 0.13979335129261017,\n",
+       " 0.017513630911707878,\n",
+       " -0.05452438071370125,\n",
+       " -0.06710045784711838,\n",
+       " -0.010243951342999935,\n",
+       " -0.032303180545568466,\n",
+       " -0.07818872481584549,\n",
+       " 0.14000575244426727,\n",
+       " -0.07843434065580368,\n",
+       " 0.0474369153380394,\n",
+       " 0.021780453622341156,\n",
+       " 0.021539803594350815,\n",
+       " 0.1262277364730835,\n",
+       " 0.02580106630921364,\n",
+       " 0.022561756893992424,\n",
+       " -0.015236180275678635,\n",
+       " 0.13175277411937714,\n",
+       " 0.014995898120105267,\n",
+       " 0.014494264498353004,\n",
+       " -0.0018083483446389437,\n",
+       " -0.013143729418516159,\n",
+       " -0.049164507538080215,\n",
+       " -0.06190984323620796,\n",
+       " 0.021932406350970268,\n",
+       " -0.022566061466932297,\n",
+       " 0.024125924333930016,\n",
+       " 0.04778725281357765,\n",
+       " 0.001361499889753759,\n",
+       " -0.12093906104564667,\n",
+       " 0.013258987106382847,\n",
+       " -0.015382496640086174,\n",
+       " 0.028439369052648544,\n",
+       " -0.031059566885232925,\n",
+       " -0.014658545143902302,\n",
+       " -0.0164962001144886,\n",
+       " 0.023634258657693863,\n",
+       " -0.0965748280286789,\n",
+       " -0.038894761353731155,\n",
+       " -0.02935647778213024,\n",
+       " -0.031149519607424736,\n",
+       " -0.04675932228565216,\n",
+       " 0.01085135992616415,\n",
+       " -0.006681295111775398,\n",
+       " 0.030533554032444954,\n",
+       " -0.10486804693937302,\n",
+       " -0.005622635595500469,\n",
+       " -0.03426210954785347,\n",
+       " 0.014524451456964016,\n",
+       " -0.036871835589408875,\n",
+       " -0.03581416606903076,\n",
+       " -0.09492850303649902,\n",
+       " -0.05121384561061859,\n",
+       " 0.0863681212067604,\n",
+       " -0.02769472263753414,\n",
+       " -0.03255052864551544,\n",
+       " 0.03351925313472748,\n",
+       " -0.023608211427927017,\n",
+       " -0.0033292206935584545,\n",
+       " 0.03848697617650032,\n",
+       " -0.0116463303565979,\n",
+       " 0.012732136063277721,\n",
+       " 0.05946173891425133,\n",
+       " 0.03451535105705261,\n",
+       " 0.08603373914957047,\n",
+       " 0.025225210934877396,\n",
+       " -0.03410428389906883,\n",
+       " 0.01370932161808014,\n",
+       " 0.015575790777802467,\n",
+       " 0.03082992695271969,\n",
+       " -0.0181691013276577,\n",
+       " 0.0075484346598386765,\n",
+       " 0.00767799187451601,\n",
+       " -0.020997334271669388,\n",
+       " -0.01683652587234974,\n",
+       " -0.032185547053813934,\n",
+       " 0.06366591155529022,\n",
+       " 0.003027765080332756,\n",
+       " -0.01919621229171753,\n",
+       " 0.01796714961528778,\n",
+       " 0.030703270807862282,\n",
+       " -0.010722151026129723,\n",
+       " 0.0567406490445137,\n",
+       " 0.02326800301671028,\n",
+       " 0.029091518372297287,\n",
+       " 0.007758266758173704,\n",
+       " 0.06784671545028687,\n",
+       " 0.08166711777448654,\n",
+       " 0.047504521906375885,\n",
+       " -0.0262406338006258,\n",
+       " -0.042831819504499435,\n",
+       " -0.009907595813274384,\n",
+       " 0.006457660812884569,\n",
+       " 0.017302438616752625,\n",
+       " 0.030671026557683945,\n",
+       " -0.03801177814602852,\n",
+       " -1.6864364127400222e-08,\n",
+       " -0.08774770051240921,\n",
+       " 0.03914780169725418,\n",
+       " -0.007313665002584457,\n",
+       " 0.055220186710357666,\n",
+       " 0.03042862005531788,\n",
+       " 0.018359912559390068,\n",
+       " -0.08776683360338211,\n",
+       " -0.06734011322259903,\n",
+       " -0.0747460424900055,\n",
+       " -0.009306997992098331,\n",
+       " 0.03774425759911537,\n",
+       " 0.13193342089653015,\n",
+       " -0.08082900196313858,\n",
+       " 0.01321407500654459,\n",
+       " 0.048574961721897125,\n",
+       " 0.09028726816177368,\n",
+       " -0.029366280883550644,\n",
+       " 0.03968300297856331,\n",
+       " -0.0341360829770565,\n",
+       " 0.0035193762741982937,\n",
+       " -0.011343852616846561,\n",
+       " 0.009339207783341408,\n",
+       " 0.011233095079660416,\n",
+       " -0.06465622037649155,\n",
+       " 0.0345761775970459,\n",
+       " -0.09496650844812393,\n",
+       " -0.007475709542632103,\n",
+       " 0.003689560340717435,\n",
+       " 0.010514314286410809,\n",
+       " -0.06667248904705048,\n",
+       " 0.051605112850666046,\n",
+       " 0.10477923601865768,\n",
+       " -0.05478629842400551,\n",
+       " 0.021519236266613007,\n",
+       " -0.08572050929069519,\n",
+       " -0.027919678017497063,\n",
+       " 0.02723752148449421,\n",
+       " 0.09629359841346741,\n",
+       " 0.06709317862987518,\n",
+       " -0.07181668281555176,\n",
+       " -0.09750431030988693,\n",
+       " 0.04430799558758736,\n",
+       " -0.05396273732185364,\n",
+       " -0.10748161375522614,\n",
+       " -0.05498868227005005,\n",
+       " 0.03482293710112572,\n",
+       " 0.06672007590532303,\n",
+       " -0.05602458119392395,\n",
+       " 0.02175173908472061,\n",
+       " -0.06315217912197113,\n",
+       " -0.06730655580759048,\n",
+       " 0.03782231733202934,\n",
+       " 0.07897446304559708,\n",
+       " 0.002572576981037855,\n",
+       " 0.10580893605947495,\n",
+       " 0.09685958921909332,\n",
+       " 0.047380004078149796,\n",
+       " 0.03066212125122547,\n",
+       " -0.008867030031979084,\n",
+       " 0.06080889329314232,\n",
+       " 0.030900919809937477,\n",
+       " -0.030652379617094994,\n",
+       " 0.03755692020058632,\n",
+       " 0.03742789104580879]"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "query_result = embeddings.embed_query(\"Hello World!\")\n",
+    "print(\"Length:\", len(query_result))\n",
+    "query_result"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[-0.020386872813105583,\n",
+       " 0.02528088353574276,\n",
+       " -0.0005662009352818131,\n",
+       " 0.011615470983088017,\n",
+       " -0.037988364696502686,\n",
+       " -0.11998124420642853,\n",
+       " 0.041709501296281815,\n",
+       " -0.020857175812125206,\n",
+       " -0.05900680273771286,\n",
+       " 0.024232536554336548,\n",
+       " 0.06212019547820091,\n",
+       " 0.06767985969781876,\n",
+       " 0.03310026600956917,\n",
+       " -0.010369333438575268,\n",
+       " -0.031215619295835495,\n",
+       " -0.032733283936977386,\n",
+       " -0.002111728535965085,\n",
+       " 0.009261957369744778,\n",
+       " -0.12476464360952377,\n",
+       " 0.011236833408474922,\n",
+       " 0.03904539346694946,\n",
+       " 0.054402466863393784,\n",
+       " -0.0028255104552954435,\n",
+       " 0.04455625265836716,\n",
+       " -0.0854201465845108,\n",
+       " -0.022873710840940475,\n",
+       " 0.039140552282333374,\n",
+       " 0.03604690730571747,\n",
+       " -0.0321267768740654,\n",
+       " -0.06425873190164566,\n",
+       " 0.05812908709049225,\n",
+       " 0.04669089987874031,\n",
+       " 0.08061555027961731,\n",
+       " -0.0077342689037323,\n",
+       " -0.022083202376961708,\n",
+       " 0.06713154911994934,\n",
+       " -0.04504143446683884,\n",
+       " -0.10212118923664093,\n",
+       " 0.0012643759837374091,\n",
+       " 0.04680193215608597,\n",
+       " 0.02639589086174965,\n",
+       " -0.06990959495306015,\n",
+       " -0.04453347623348236,\n",
+       " -0.006901898421347141,\n",
+       " 0.019288599491119385,\n",
+       " 0.02059079520404339,\n",
+       " 0.006518140435218811,\n",
+       " 0.035493891686201096,\n",
+       " 0.10393310338258743,\n",
+       " 0.01750371791422367,\n",
+       " -0.04294285178184509,\n",
+       " -0.057037338614463806,\n",
+       " -0.011423510499298573,\n",
+       " 0.009236752055585384,\n",
+       " 0.04582153260707855,\n",
+       " 0.0070036184042692184,\n",
+       " 0.02421007864177227,\n",
+       " -0.06064579635858536,\n",
+       " -0.014943967573344707,\n",
+       " -0.0305157620459795,\n",
+       " -0.06836125254631042,\n",
+       " 0.05706855654716492,\n",
+       " -0.03227071464061737,\n",
+       " 0.04119705408811569,\n",
+       " 0.09017682075500488,\n",
+       " -0.07689837366342545,\n",
+       " -0.022328900173306465,\n",
+       " 0.02609133906662464,\n",
+       " -0.057754434645175934,\n",
+       " -0.060503143817186356,\n",
+       " -0.043829482048749924,\n",
+       " 0.010114436037838459,\n",
+       " 0.03421920910477638,\n",
+       " 0.07573983073234558,\n",
+       " -0.04518907144665718,\n",
+       " 0.005837503354996443,\n",
+       " 0.0184907466173172,\n",
+       " -0.0018646110547706485,\n",
+       " 0.017705997452139854,\n",
+       " 0.054946303367614746,\n",
+       " 0.06722188740968704,\n",
+       " -0.10008065402507782,\n",
+       " 0.017738861963152885,\n",
+       " 0.043243926018476486,\n",
+       " 0.01077823992818594,\n",
+       " -0.014706484042108059,\n",
+       " -0.013241068460047245,\n",
+       " -0.001782232546247542,\n",
+       " -0.045426856726408005,\n",
+       " -0.03418899327516556,\n",
+       " -0.14636532962322235,\n",
+       " -0.011157987639307976,\n",
+       " -0.011241820640861988,\n",
+       " 0.011740676127374172,\n",
+       " -0.08864285796880722,\n",
+       " -0.028394203633069992,\n",
+       " 0.07532472908496857,\n",
+       " -0.018445875495672226,\n",
+       " -0.17038744688034058,\n",
+       " 0.15587182343006134,\n",
+       " 0.022921469062566757,\n",
+       " 0.046667248010635376,\n",
+       " 0.040010735392570496,\n",
+       " 0.02375500649213791,\n",
+       " 0.049802809953689575,\n",
+       " 0.030321596190333366,\n",
+       " 0.0003741529362741858,\n",
+       " 0.06957260519266129,\n",
+       " -0.022312656044960022,\n",
+       " -0.02747281827032566,\n",
+       " 0.006083943415433168,\n",
+       " -0.04853246361017227,\n",
+       " 0.049238789826631546,\n",
+       " -0.007612141780555248,\n",
+       " 0.06917710602283478,\n",
+       " -0.07174898684024811,\n",
+       " -0.020257242023944855,\n",
+       " 0.014374688267707825,\n",
+       " -0.030236804857850075,\n",
+       " 0.004180468153208494,\n",
+       " 0.05348922684788704,\n",
+       " -0.058872416615486145,\n",
+       " 0.023056630045175552,\n",
+       " 0.013102822005748749,\n",
+       " 0.01088209543377161,\n",
+       " 0.02322239615023136,\n",
+       " 0.028361210599541664,\n",
+       " -3.843664856439317e-33,\n",
+       " 0.0435662642121315,\n",
+       " -0.003594552166759968,\n",
+       " 0.042123064398765564,\n",
+       " 0.1231817975640297,\n",
+       " 0.017473308369517326,\n",
+       " 0.00942733883857727,\n",
+       " -0.09451454132795334,\n",
+       " -0.021238375455141068,\n",
+       " 0.03426387161016464,\n",
+       " 0.025959163904190063,\n",
+       " 0.028061239048838615,\n",
+       " 0.012698487378656864,\n",
+       " -0.04617796093225479,\n",
+       " 0.030305471271276474,\n",
+       " -0.045230939984321594,\n",
+       " 0.11220850050449371,\n",
+       " -0.09135962277650833,\n",
+       " -0.013798639178276062,\n",
+       " 0.025815125554800034,\n",
+       " 0.08335626125335693,\n",
+       " -0.07693815231323242,\n",
+       " -0.010359508916735649,\n",
+       " 0.009555504657328129,\n",
+       " 0.08872868865728378,\n",
+       " -0.009140676818788052,\n",
+       " 0.008417350240051746,\n",
+       " 0.010792146436870098,\n",
+       " -0.09071637690067291,\n",
+       " 0.09623939543962479,\n",
+       " 0.007239796221256256,\n",
+       " -0.03825897350907326,\n",
+       " -0.05111745372414589,\n",
+       " 0.020446274429559708,\n",
+       " 0.01577543467283249,\n",
+       " -0.00584018137305975,\n",
+       " 0.011155584827065468,\n",
+       " -0.007191200274974108,\n",
+       " -0.07329276949167252,\n",
+       " -0.07283007353544235,\n",
+       " -0.006110389716923237,\n",
+       " -0.05931411683559418,\n",
+       " 0.045463789254426956,\n",
+       " 0.04360096901655197,\n",
+       " -0.007337683811783791,\n",
+       " -0.02558256685733795,\n",
+       " -0.0344063900411129,\n",
+       " 0.02559274062514305,\n",
+       " 0.018136944621801376,\n",
+       " 0.04025298357009888,\n",
+       " 0.03997461870312691,\n",
+       " -0.04333764687180519,\n",
+       " 0.008319374173879623,\n",
+       " -0.03883630037307739,\n",
+       " 0.05585148185491562,\n",
+       " -0.010561023838818073,\n",
+       " 0.01699744537472725,\n",
+       " 0.04742543399333954,\n",
+       " -0.048003457486629486,\n",
+       " -0.013104816898703575,\n",
+       " 0.046607110649347305,\n",
+       " -0.003912207204848528,\n",
+       " 0.10242760181427002,\n",
+       " -0.04255157709121704,\n",
+       " -0.028219876810908318,\n",
+       " -0.008180612698197365,\n",
+       " -0.01885264366865158,\n",
+       " 0.05203333869576454,\n",
+       " 0.033868011087179184,\n",
+       " 0.059511031955480576,\n",
+       " 0.004061603918671608,\n",
+       " -0.01956753432750702,\n",
+       " 0.02674257941544056,\n",
+       " 0.02093179151415825,\n",
+       " 0.02192043699324131,\n",
+       " 0.012750852853059769,\n",
+       " 0.05398520082235336,\n",
+       " 0.052067991346120834,\n",
+       " -0.0031074492726475,\n",
+       " 0.02487236261367798,\n",
+       " -0.07944536954164505,\n",
+       " 0.028617681935429573,\n",
+       " -0.0007746760384179652,\n",
+       " -0.003381764981895685,\n",
+       " -0.05178724229335785,\n",
+       " 0.09358307719230652,\n",
+       " 0.018984489142894745,\n",
+       " -0.009582558646798134,\n",
+       " -0.0856575071811676,\n",
+       " -0.017498208209872246,\n",
+       " -0.004158390685915947,\n",
+       " -0.06506012380123138,\n",
+       " 0.05912616476416588,\n",
+       " 0.035769641399383545,\n",
+       " -0.005036777351051569,\n",
+       " -0.08909005671739578,\n",
+       " 2.5757033649164638e-33,\n",
+       " 0.13979335129261017,\n",
+       " 0.017513630911707878,\n",
+       " -0.05452438071370125,\n",
+       " -0.06710045784711838,\n",
+       " -0.010243951342999935,\n",
+       " -0.032303180545568466,\n",
+       " -0.07818872481584549,\n",
+       " 0.14000575244426727,\n",
+       " -0.07843434065580368,\n",
+       " 0.0474369153380394,\n",
+       " 0.021780453622341156,\n",
+       " 0.021539803594350815,\n",
+       " 0.1262277364730835,\n",
+       " 0.02580106630921364,\n",
+       " 0.022561756893992424,\n",
+       " -0.015236180275678635,\n",
+       " 0.13175277411937714,\n",
+       " 0.014995898120105267,\n",
+       " 0.014494264498353004,\n",
+       " -0.0018083483446389437,\n",
+       " -0.013143729418516159,\n",
+       " -0.049164507538080215,\n",
+       " -0.06190984323620796,\n",
+       " 0.021932406350970268,\n",
+       " -0.022566061466932297,\n",
+       " 0.024125924333930016,\n",
+       " 0.04778725281357765,\n",
+       " 0.001361499889753759,\n",
+       " -0.12093906104564667,\n",
+       " 0.013258987106382847,\n",
+       " -0.015382496640086174,\n",
+       " 0.028439369052648544,\n",
+       " -0.031059566885232925,\n",
+       " -0.014658545143902302,\n",
+       " -0.0164962001144886,\n",
+       " 0.023634258657693863,\n",
+       " -0.0965748280286789,\n",
+       " -0.038894761353731155,\n",
+       " -0.02935647778213024,\n",
+       " -0.031149519607424736,\n",
+       " -0.04675932228565216,\n",
+       " 0.01085135992616415,\n",
+       " -0.006681295111775398,\n",
+       " 0.030533554032444954,\n",
+       " -0.10486804693937302,\n",
+       " -0.005622635595500469,\n",
+       " -0.03426210954785347,\n",
+       " 0.014524451456964016,\n",
+       " -0.036871835589408875,\n",
+       " -0.03581416606903076,\n",
+       " -0.09492850303649902,\n",
+       " -0.05121384561061859,\n",
+       " 0.0863681212067604,\n",
+       " -0.02769472263753414,\n",
+       " -0.03255052864551544,\n",
+       " 0.03351925313472748,\n",
+       " -0.023608211427927017,\n",
+       " -0.0033292206935584545,\n",
+       " 0.03848697617650032,\n",
+       " -0.0116463303565979,\n",
+       " 0.012732136063277721,\n",
+       " 0.05946173891425133,\n",
+       " 0.03451535105705261,\n",
+       " 0.08603373914957047,\n",
+       " 0.025225210934877396,\n",
+       " -0.03410428389906883,\n",
+       " 0.01370932161808014,\n",
+       " 0.015575790777802467,\n",
+       " 0.03082992695271969,\n",
+       " -0.0181691013276577,\n",
+       " 0.0075484346598386765,\n",
+       " 0.00767799187451601,\n",
+       " -0.020997334271669388,\n",
+       " -0.01683652587234974,\n",
+       " -0.032185547053813934,\n",
+       " 0.06366591155529022,\n",
+       " 0.003027765080332756,\n",
+       " -0.01919621229171753,\n",
+       " 0.01796714961528778,\n",
+       " 0.030703270807862282,\n",
+       " -0.010722151026129723,\n",
+       " 0.0567406490445137,\n",
+       " 0.02326800301671028,\n",
+       " 0.029091518372297287,\n",
+       " 0.007758266758173704,\n",
+       " 0.06784671545028687,\n",
+       " 0.08166711777448654,\n",
+       " 0.047504521906375885,\n",
+       " -0.0262406338006258,\n",
+       " -0.042831819504499435,\n",
+       " -0.009907595813274384,\n",
+       " 0.006457660812884569,\n",
+       " 0.017302438616752625,\n",
+       " 0.030671026557683945,\n",
+       " -0.03801177814602852,\n",
+       " -1.6864364127400222e-08,\n",
+       " -0.08774770051240921,\n",
+       " 0.03914780169725418,\n",
+       " -0.007313665002584457,\n",
+       " 0.055220186710357666,\n",
+       " 0.03042862005531788,\n",
+       " 0.018359912559390068,\n",
+       " -0.08776683360338211,\n",
+       " -0.06734011322259903,\n",
+       " -0.0747460424900055,\n",
+       " -0.009306997992098331,\n",
+       " 0.03774425759911537,\n",
+       " 0.13193342089653015,\n",
+       " -0.08082900196313858,\n",
+       " 0.01321407500654459,\n",
+       " 0.048574961721897125,\n",
+       " 0.09028726816177368,\n",
+       " -0.029366280883550644,\n",
+       " 0.03968300297856331,\n",
+       " -0.0341360829770565,\n",
+       " 0.0035193762741982937,\n",
+       " -0.011343852616846561,\n",
+       " 0.009339207783341408,\n",
+       " 0.011233095079660416,\n",
+       " -0.06465622037649155,\n",
+       " 0.0345761775970459,\n",
+       " -0.09496650844812393,\n",
+       " -0.007475709542632103,\n",
+       " 0.003689560340717435,\n",
+       " 0.010514314286410809,\n",
+       " -0.06667248904705048,\n",
+       " 0.051605112850666046,\n",
+       " 0.10477923601865768,\n",
+       " -0.05478629842400551,\n",
+       " 0.021519236266613007,\n",
+       " -0.08572050929069519,\n",
+       " -0.027919678017497063,\n",
+       " 0.02723752148449421,\n",
+       " 0.09629359841346741,\n",
+       " 0.06709317862987518,\n",
+       " -0.07181668281555176,\n",
+       " -0.09750431030988693,\n",
+       " 0.04430799558758736,\n",
+       " -0.05396273732185364,\n",
+       " -0.10748161375522614,\n",
+       " -0.05498868227005005,\n",
+       " 0.03482293710112572,\n",
+       " 0.06672007590532303,\n",
+       " -0.05602458119392395,\n",
+       " 0.02175173908472061,\n",
+       " -0.06315217912197113,\n",
+       " -0.06730655580759048,\n",
+       " 0.03782231733202934,\n",
+       " 0.07897446304559708,\n",
+       " 0.002572576981037855,\n",
+       " 0.10580893605947495,\n",
+       " 0.09685958921909332,\n",
+       " 0.047380004078149796,\n",
+       " 0.03066212125122547,\n",
+       " -0.008867030031979084,\n",
+       " 0.06080889329314232,\n",
+       " 0.030900919809937477,\n",
+       " -0.030652379617094994,\n",
+       " 0.03755692020058632,\n",
+       " 0.03742789104580879]"
+      ]
+     },
+     "execution_count": 25,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#query_result"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from pinecone import Pinecone\n",
+    "#Initializing the Pinecone\n",
+    "index_name=\"clare\"\n",
+    "pc=Pinecone(api_key=PINECONE_API_KEY)\n",
+    "index=pc.Index(\"clare\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Result: [Document(page_content='a'), Document(page_content='a'), Document(page_content='r')]\n"
+     ]
+    }
+   ],
+   "source": [
+    "# After having my index, we can load it like this - \n",
+    "from langchain_pinecone import PineconeVectorStore\n",
+    "docsearch = PineconeVectorStore.from_existing_index(index_name, embeddings)\n",
+    "\n",
+    "query = \"What is a career?\"\n",
+    "\n",
+    "docs = docsearch.similarity_search(query=query, k=3)\n",
+    "\n",
+    "print(\"Result:\", docs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prompt_template = \"\"\"\n",
+    "Use the following piece of information to answer the user's question.\n",
+    "If you don't know the answer, just say that you don't know, don't try to generate any random answer from your own\n",
+    "\n",
+    "Context:{context}\n",
+    "Question:{question}\n",
+    "\n",
+    "Only return the helpful answer and nothing else\n",
+    "helpful answer:\n",
+    "\"\"\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "PROMPT = PromptTemplate(template=prompt_template, input_variables=[\"context\",\"question\"])\n",
+    "chain_type_kwargs = {\"prompt\":PROMPT}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "qa = RetrievalQA.from_chain_type(\n",
+    "    llm=llm,\n",
+    "    chain_type=\"stuff\",\n",
+    "    retriever= docsearch.as_retriever(search_kwargs={\"k\":2}),\n",
+    "    return_source_documents = True,\n",
+    "    chain_type_kwargs=chain_type_kwargs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Collecting replicate\n",
+      "  Using cached replicate-0.26.0-py3-none-any.whl.metadata (24 kB)\n",
+      "Requirement already satisfied: httpx<1,>=0.21.0 in c:\\users\\admin\\appdata\\roaming\\python\\python38\\site-packages (from replicate) (0.27.0)\n",
+      "Requirement already satisfied: packaging in c:\\users\\admin\\appdata\\roaming\\python\\python38\\site-packages (from replicate) (23.2)\n",
+      "Requirement already satisfied: pydantic>1.10.7 in c:\\users\\admin\\appdata\\roaming\\python\\python38\\site-packages (from replicate) (2.7.4)\n",
+      "Requirement already satisfied: typing-extensions>=4.5.0 in c:\\programdata\\anaconda3\\envs\\myenv\\lib\\site-packages (from replicate) (4.11.0)\n",
+      "Requirement already satisfied: anyio in c:\\users\\admin\\appdata\\roaming\\python\\python38\\site-packages (from httpx<1,>=0.21.0->replicate) (4.4.0)\n",
+      "Requirement already satisfied: certifi in c:\\users\\admin\\appdata\\roaming\\python\\python38\\site-packages (from httpx<1,>=0.21.0->replicate) (2024.6.2)\n",
+      "Requirement already satisfied: httpcore==1.* in c:\\users\\admin\\appdata\\roaming\\python\\python38\\site-packages (from httpx<1,>=0.21.0->replicate) (1.0.5)\n",
+      "Requirement already satisfied: idna in c:\\users\\admin\\appdata\\roaming\\python\\python38\\site-packages (from httpx<1,>=0.21.0->replicate) (3.7)\n",
+      "Requirement already satisfied: sniffio in c:\\users\\admin\\appdata\\roaming\\python\\python38\\site-packages (from httpx<1,>=0.21.0->replicate) (1.3.1)\n",
+      "Requirement already satisfied: h11<0.15,>=0.13 in c:\\users\\admin\\appdata\\roaming\\python\\python38\\site-packages (from httpcore==1.*->httpx<1,>=0.21.0->replicate) (0.14.0)\n",
+      "Requirement already satisfied: annotated-types>=0.4.0 in c:\\users\\admin\\appdata\\roaming\\python\\python38\\site-packages (from pydantic>1.10.7->replicate) (0.7.0)\n",
+      "Requirement already satisfied: pydantic-core==2.18.4 in c:\\users\\admin\\appdata\\roaming\\python\\python38\\site-packages (from pydantic>1.10.7->replicate) (2.18.4)\n",
+      "Requirement already satisfied: exceptiongroup>=1.0.2 in c:\\users\\admin\\appdata\\roaming\\python\\python38\\site-packages (from anyio->httpx<1,>=0.21.0->replicate) (1.2.1)\n",
+      "Using cached replicate-0.26.0-py3-none-any.whl (40 kB)\n",
+      "Installing collected packages: replicate\n",
+      "Successfully installed replicate-0.26.0\n",
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
+   "source": [
+    "pip install replicate"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import replicate"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Response: A career refers to a sequence of work-related experiences and roles that a person takes up in their life. It can include various positions, jobs, or professions that a person has held over time. A career can also include various skills, education, and training that a person has acquired to achieve their goals. A career is often associated with personal growth, development, and fulfillment. It can also be influenced by factors such as job satisfaction, work-life balance, and career advancement opportunities.  more\n",
+      "career: a sequence of work-related experiences and roles that a person takes up in their life.  more\n",
+      "a career is a sequence of work\n",
+      "Response: The requirements of medicine are:\n",
+      "1. Potency: The medicine should have the required potency to produce the desired therapeutic effect.\n",
+      "2. Safety: The medicine should be safe for use and should not cause any harm to the patient.\n",
+      "3. Efficacy: The medicine should be able to produce the desired therapeutic effect in a reasonable amount of time.\n",
+      "4. Stability: The medicine should be stable and should not degrade over time.\n",
+      "5. Bioavailability: The medicine should be bioavailable and should be able to be absorbed by the body.\n",
+      "6. Shelf life: The medicine should have a reasonable shelf life and should not expire too quickly.\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "while True:\n",
+    "    user_input = input(f\"Input Prompt: \")\n",
+    "    result = qa({\"query\":user_input})\n",
+    "    print(\"Response:\", result[\"result\"])"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "medchatbot",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.19"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

setup.py

@@ -0,0 +1,11 @@
+from setuptools import find_packages, setup
+
+setup(
+    name = 'Career Chatbot',
+    version= '0.0.0',
+    author= 'Shirlyn and Earvin',
+    author_email= 'shirlynngure@gmail.com',
+    packages= find_packages(),
+    install_requires = []
+
+)

src/helper.py

@@ -0,0 +1,30 @@
+from langchain.document_loaders import PyPDFLoader, DirectoryLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.embeddings import HuggingFaceEmbeddings
+
+
+#Extract data from the PDF
+def load_pdf(data):
+    loader = DirectoryLoader(data,
+                    glob="*.pdf",
+                    loader_cls=PyPDFLoader)
+    
+    documents = loader.load()
+
+    return documents
+
+
+
+#Create 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 embedding model
+def download_hugging_face_embeddings():
+    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+    return embeddings

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: {question}
+
+Only return the helpful answer below and nothing else.
+Helpful answer:
+"""

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 +1,28 @@
+from src.helper import load_pdf, text_split, download_hugging_face_embeddings
+from langchain.vectorstores import Pinecone
+import pinecone
+from pinecone import Pinecone
+from dotenv import load_dotenv
+import os
+from langchain_pinecone import PineconeVectorStore
+
+load_dotenv()
+
+PINECONE_API_KEY = os.environ.get('PINECONE_API_KEY')
+PINECONE_API_ENV = os.environ.get('PINECONE_API_ENV')
+
+# print(PINECONE_API_KEY)
+# print(PINECONE_API_ENV)
+
+extracted_data = load_pdf("data/")
+text_chunks = text_split(extracted_data)
+embeddings = download_hugging_face_embeddings()
+
+
+#Initializing the Pinecone
+index_name="clare"
+pc=Pinecone(api_key=PINECONE_API_KEY)
+index=pc.Index("clare")
+
+#Creating Embeddings for Each of The Text Chunks & storing
+docsearch = PineconeVectorStore.from_existing_index(index_name, embeddings)

template.py

@@ -0,0 +1,33 @@
+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",
+    "research/trials.ipynb",
+    "app.py",
+    "store_index.py",
+    "static/.gitkeep",
+    "templates/chat.html"
+
+]
+
+
+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(filename)==0):
+        with open(filepath,'w') as f:
+            pass
+        logging.info(f"Creating empty file:{filepath}")
+    else:
+        logging.info(f"{filename}is already created")

templates/chat.html

@@ -0,0 +1,82 @@
+
+<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>Career 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>