Steps to Build a Healthcare AI Assistant Chatbot Using Llama3-OpenBioLLM-70B

August 19, 2024

The 2020 pandemic marked a pivotal moment in modern history, highlighting the urgent need to make health advice accessible to people of all backgrounds. Over the past two years, Generative AI technologies, particularly large language models (LLMs), have demonstrated remarkable potential in broadening access to knowledge and information through human-like language. The question now is: can we leverage LLMs to make healthcare more accessible?

In this article, we will walk you through the process of building a Healthcare AI chatbot that can be integrated into your healthcare app or offered as an add-on service to your customers. We will use an LLM that has been fine-tuned specifically for the healthcare domain, ensuring it understands the specialized vocabulary and knowledge required.

We will also showcase the steps to deploy it on E2E Cloud, which is India’s most price-performant AI cloud offering the advanced cloud GPUs you need for leveraging cutting-edge LLMs from Hugging Face and other sources. We will also explain the importance of data sovereignty and why a MeitY-empanelled CSP like E2E Cloud is the ideal platform for healthcare AI solutions.

Why Create Healthcare Assistant Chatbots

Integrating LLMs into the healthcare domain has the potential to revolutionize the medical industry. It can:

Increase accessibility and availability of general medical advice.
Enhance patient engagement.
Provide 24/7 responses, especially for simple queries, when medical professionals are unavailable or occupied with more urgent cases.

According to NASSCOM, AI in healthcare is projected to contribute between $25 billion and $30 billion to India's GDP by 2025. The World Economic Forum states that it can add $1 trillion to India’s economy by 2035.

Importance of Using a Data Sovereign Architecture

However, healthcare is one of the domains where protecting sensitive information is critical. To ensure this, the businesses operating in this domain typically focus on creating data sovereign applications.

Data sovereignty refers to the principle that data is subject to the laws and regulations of the country in which it is collected or stored. For healthcare chatbots, data sovereignty is important for several reasons:

Data Security: Storing data within a specific jurisdiction, you can leverage local legal protections and frameworks designed to safeguard data security.
Cross-Border Data Transfers: If data needs to be transferred across borders, ensure that such transfers comply with international agreements and regulations.

To ensure data sovereignty, companies must deploy the technology stack powering their healthcare AI application within the appropriate jurisdiction and choose a cloud provider that complies with the stringent regulatory requirements demanded by the healthcare sector.

E2E Cloud excels in this area. Our MeitY empanelment ensures compliance with stringent regulatory requirements. With data centers located in India and our cloud adhering to Indian IT laws, you can trust that your data will remain under your control when building on E2E Cloud.

It's important to remember that security and data privacy are shared responsibilities. Ensure you are also adhering to the relevant laws and regulations.

A Guide to Building a Healthcare AI Chatbot

To build this chatbot, we will use Llama3-OpenBioLLM-70B. Llama3-OpenBioLLM-70B model is designed specifically for medical purposes and specially tuned over medical data. With the power of open-source Llama3 and training on over 70 billion parameters, it is one of the best open-source models available for medical use cases.

Prerequisites and Initial Setup

First, sign in or sign up to E2E Myaccount. Once you have signed up, you can launch a GPU instance. You will need a GPU with over 32 GB RAM, or you will need a quantized version (lower accuracy, but also lower RAM requirements).

For this experiment, we suggest using an A100 or H100 Cloud GPU. When you want to scale it later, you can opt for InfiniBand-powered cluster configurations like 4xH100, 8xH100, or even 64xH100.

Once you have set up your cloud GPU and added your public SSH Key, you can get started with the steps below.

The diagram below shows our implementation architecture.

Setting Up the Environment

The first step is to install all the necessary libraries that will be needed to create an efficient healthcare chatbot. We will use LangChain as our framework, and Qdrant as our vector store. We will also use Gradio to create a UI.

First, create a virtual environment.


python3 -m venv .venv
source .venv/bin/activate

Next, install the libraries.


pip install langchain_community
pip install pypdf
pip install qdrant-client
pip install sentence-transformers
pip install gradio

Once the installation process is completed, we need to import them into the project. Open VS Code, install remote explorer, and start with the following code:


from sentence_transformers import SentenceTransformer
import pandas as pd
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, set_seed

Loading the Dataset

For this project, we have used a medical dataset from Kaggle. It contains a set of around 1600 medical questions with their respective answers. Let's load the CSV file into our project using pandas.


df = pd.read_csv('/train.csv')

Now load all the questions and answers into two separate lists for further processing.


ques_data = df['Question'].tolist()
answer_data = df['Answer'].tolist()

Embedding Model

Next load the embedding model from Hugging Face using transformers and convert all the questions into their respective vector embeddings to store them in the vector database.


model = SentenceTransformer("sentence-transformers/all-mpnet-base-v2")
vectors = model.encode(ques_data)

Storing Embeddings in the Database

We are using Qdrant as the vector store database to store the embeddings generated for the questions.

The first step is to initiate the database client.


from qdrant_client import QdrantClient
from qdrant_client.models import Distance, VectorParams

client = QdrantClient(":memory:")

Next, we need to create a collection in the database where all the questions will be stored in the form of vector embeddings.


client.recreate_collection(
    collection_name="doc_data",
    vectors_config=VectorParams(size=len(vectors[0]), distance=Distance.COSINE),
)

Once the collection is created, upload the respective question embeddings into the database along with their IDs.


client.upload_collection(
    collection_name="doc_data",
    ids=[i for i in range(len(ques_data))],
    vectors=vectors,
)

Semantic Search

Semantic similarity search will be used here to find documents that match the user query. To perform a similarity search, you have to first convert the user query into vector embeddings, and compare that with the vector embeddings of the dataset already stored (from Kaggle).

Here’s how you can do it.


def fetch_best_match(question):
  model = SentenceTransformer("sentence-transformers/all-mpnet-base-v2")
  ques_vector = model.encode(question)
  result = client.query_points(collection_name="doc_data",query=ques_vector)
  sim_ids = []
  for i in result.points:
    sim_ids.append(i.id)
  context = answer_data[sim_ids[0]]
  return context

Constructing the LLM Prompt

To make the response more user-friendly, we will craft the prompt to respond succinctly.

Since we will be using the language model Llama3-OpenBioLLM-70B, the prompt format is that of Llama3.1 specification, and we will ask the LLM to respond based on the context provided. The context will be fetched from the vector database depending on the user query and semantic search.


def fetch_llm_response(question,context):
  model_checkpoint = "aaditya/Llama3-OpenBioLLM-70B"
  tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
  model = AutoModelForCausalLM.from_pretrained(model_checkpoint, device_map="cuda")
  chat = [
    {"role": "user", "content": f"this is question {question} asked by user you are a chatbot answer the question based on this context {context} in not more than 3-4 points"}
  ]
  token_inputs = tokenizer.apply_chat_template(chat, tokenize=True, return_tensors="pt", add_generation_prompt=True).to("cuda")
  token_outputs = model.generate(input_ids=token_inputs, do_sample=True, max_new_tokens=500, temperature=.5)
  new_tokens = token_outputs[0][token_inputs.shape[-1]:]
  decoded_output = tokenizer.decode(new_tokens, skip_special_tokens=True)
  return decoded_output

Creating the Front End

We will be using Gradio to create the front end, where users can put in their queries and get the responses displayed in the web app. In real life, you would be integrating it with your own branded UI.


import gradio as gr

def chatbot_response(user_input):
    if user_input:
      context = fetch_best_match(user_input)
      return fetch_llm_response(user_input,context)
    else:
        return "Bot: Please enter a message."

iface = gr.Interface(
    fn=chatbot_response,
    inputs="text",
    outputs="text",
    title="Medical RAG",
    description="Type your issue below and the bot will respond."
)

iface.launch()

Results

The final result of our medical chatbot looks like this:

‍

Ensuring Security and Compliance

Before launching the chatbot in production, some security measures should ideally be followed:

End-to-End Encryption: Ensure that data exchanged between the user and the chatbot is encrypted.
Regular Security Audits: Review and update security practices to address any vulnerabilities or threats.
Multi-Factor Authentication: Implement MFA to enhance security by requiring users to provide two or more verification factors like passwords and one-time codes before granting access.

Conclusion

Building a Healthcare AI chatbot leveraging LLMs offers a powerful tool for making healthcare information more accessible, personalized, and timely. By following the steps outlined in this guide, you can create a robust chatbot that enhances patient engagement and supports medical professionals with routine queries.

However, building and deploying such a solution requires a platform that ensures both performance and compliance, particularly with the stringent regulatory requirements in the healthcare sector. E2E Cloud offers the perfect cloud infrastructure with its advanced cloud GPUs, MeitY empanelment, outstanding price-performance ratio, and commitment to data sovereignty.

Ready to take your healthcare AI solution to the next level? Sign up to E2E Cloud today and start building with the confidence that your data is secure, compliant, and hosted on India’s most price-performant AI cloud. You can also reach out to us at sales@e2enetworks.com.

Sign up for Free Trial

Latest Blogs

November 4, 2024

A Complete Guide To Customer Acquisition For Startups

Any business is enlivened by its customers. Therefore, a strategy to constantly bring in new clients is an ongoing requirement. In this regard, having a proper customer acquisition strategy can be of great importance.

So, if you are just starting your business, or planning to expand it, read on to learn more about this concept.

The problem with customer acquisition

As an organization, when working in a diverse and competitive market like India, you need to have a well-defined customer acquisition strategy to attain success. However, this is where most startups struggle. Now, you may have a great product or service, but if you are not in the right place targeting the right demographic, you are not likely to get the results you want.

To resolve this, typically, companies invest, but if that is not channelized properly, it will be futile.

So, the best way out of this dilemma is to have a clear customer acquisition strategy in place.

How can you create the ideal customer acquisition strategy for your business?

Define what your goals are

You need to define your goals so that you can meet the revenue expectations you have for the current fiscal year. You need to find a value for the metrics –

MRR – Monthly recurring revenue, which tells you all the income that can be generated from all your income channels.
CLV – Customer lifetime value tells you how much a customer is willing to spend on your business during your mutual relationship duration.
CAC – Customer acquisition costs, which tells how much your organization needs to spend to acquire customers constantly.
Churn rate – It tells you the rate at which customers stop doing business.

All these metrics tell you how well you will be able to grow your business and revenue.

Identify your ideal customers

You need to understand who your current customers are and who your target customers are. Once you are aware of your customer base, you can focus your energies in that direction and get the maximum sale of your products or services. You can also understand what your customers require through various analytics and markers and address them to leverage your products/services towards them.

Choose your channels for customer acquisition

How will you acquire customers who will eventually tell at what scale and at what rate you need to expand your business? You could market and sell your products on social media channels like Instagram, Facebook and YouTube, or invest in paid marketing like Google Ads. You need to develop a unique strategy for each of these channels.

Communicate with your customers

If you know exactly what your customers have in mind, then you will be able to develop your customer strategy with a clear perspective in mind. You can do it through surveys or customer opinion forms, email contact forms, blog posts and social media posts. After that, you just need to measure the analytics, clearly understand the insights, and improve your strategy accordingly.

Combining these strategies with your long-term business plan will bring results. However, there will be challenges on the way, where you need to adapt as per the requirements to make the most of it. At the same time, introducing new technologies like AI and ML can also solve such issues easily. To learn more about the use of AI and ML and how they are transforming businesses, keep referring to the blog section of E2E Networks.

‍

Reference Links

https://www.helpscout.com/customer-acquisition/

https://www.cloudways.com/blog/customer-acquisition-strategy-for-startups/

https://blog.hubspot.com/service/customer-acquisition

This is a decorative image for: Constructing 3D objects through Deep Learning

October 18, 2022

Image-based 3D Object Reconstruction State-of-the-Art and trends in the Deep Learning Era

3D reconstruction is one of the most complex issues of deep learning systems. There have been multiple types of research in this field, and almost everything has been tried on it — computer vision, computer graphics and machine learning, but to no avail. However, that has resulted in CNN or convolutional neural networks foraying into this field, which has yielded some success.

The Main Objective of the 3D Object Reconstruction

Developing this deep learning technology aims to infer the shape of 3D objects from 2D images. So, to conduct the experiment, you need the following:

Highly calibrated cameras that take a photograph of the image from various angles.
Large training datasets can predict the geometry of the object whose 3D image reconstruction needs to be done. These datasets can be collected from a database of images, or they can be collected and sampled from a video.

By using the apparatus and datasets, you will be able to proceed with the 3D reconstruction from 2D datasets.

State-of-the-art Technology Used by the Datasets for the Reconstruction of 3D Objects

The technology used for this purpose needs to stick to the following parameters:

Input

Training with the help of one or multiple RGB images, where the segmentation of the 3D ground truth needs to be done. It could be one image, multiple images or even a video stream.

The testing will also be done on the same parameters, which will also help to create a uniform, cluttered background, or both.

Output

The volumetric output will be done in both high and low resolution, and the surface output will be generated through parameterisation, template deformation and point cloud. Moreover, the direct and intermediate outputs will be calculated this way.

Network architecture used

The architecture used in training is 3D-VAE-GAN, which has an encoder and a decoder, with TL-Net and conditional GAN. At the same time, the testing architecture is 3D-VAE, which has an encoder and a decoder.

Training used

The degree of supervision used in 2D vs 3D supervision, weak supervision along with loss functions have to be included in this system. The training procedure is adversarial training with joint 2D and 3D embeddings. Also, the network architecture is extremely important for the speed and processing quality of the output images.

Practical applications and use cases

Volumetric representations and surface representations can do the reconstruction. Powerful computer systems need to be used for reconstruction.

Given below are some of the places where 3D Object Reconstruction Deep Learning Systems are used:

3D reconstruction technology can be used in the Police Department for drawing the faces of criminals whose images have been procured from a crime site where their faces are not completely revealed.
It can be used for re-modelling ruins at ancient architectural sites. The rubble or the debris stubs of structures can be used to recreate the entire building structure and get an idea of how it looked in the past.
They can be used in plastic surgery where the organs, face, limbs or any other portion of the body has been damaged and needs to be rebuilt.
It can be used in airport security, where concealed shapes can be used for guessing whether a person is armed or is carrying explosives or not.
It can also help in completing DNA sequences.

So, if you are planning to implement this technology, then you can rent the required infrastructure from E2E Networks and avoid investing in it. And if you plan to learn more about such topics, then keep a tab on the blog section of the website.

‍

Reference Links

https://tongtianta.site/paper/68922

https://github.com/natowi/3D-Reconstruction-with-Deep-Learning-Methods

This is a decorative image for: Comprehensive Guide to Deep Q-Learning for Data Science Enthusiasts

October 18, 2022

A Comprehensive Guide To Deep Q-Learning For Data Science Enthusiasts

For all data science enthusiasts who would love to dig deep, we have composed a write-up about Q-Learning specifically for you all. Deep Q-Learning and Reinforcement learning (RL) are extremely popular these days. These two data science methodologies use Python libraries like TensorFlow 2 and openAI’s Gym environment.

So, read on to know more.

What is Deep Q-Learning?

Deep Q-Learning utilizes the principles of Q-learning, but instead of using the Q-table, it uses the neural network. The algorithm of deep Q-Learning uses the states as input and the optimal Q-value of every action possible as the output. The agent gathers and stores all the previous experiences in the memory of the trained tuple in the following order:

State> Next state> Action> Reward

The neural network training stability increases using a random batch of previous data by using the experience replay. Experience replay also means the previous experiences stocking, and the target network uses it for training and calculation of the Q-network and the predicted Q-Value. This neural network uses openAI Gym, which is provided by taxi-v3 environments.

Now, any understanding of Deep Q-Learning is incomplete without talking about Reinforcement Learning.

What is Reinforcement Learning?

Reinforcement is a subsection of ML. This part of ML is related to the action in which an environmental agent participates in a reward-based system and uses Reinforcement Learning to maximize the rewards. Reinforcement Learning is a different technique from unsupervised learning or supervised learning because it does not require a supervised input/output pair. The number of corrections is also less, so it is a highly efficient technique.

Now, the understanding of reinforcement learning is incomplete without knowing about Markov Decision Process (MDP). MDP is involved with each state that has been presented in the results of the environment, derived from the state previously there. The information which composes both states is gathered and transferred to the decision process. The task of the chosen agent is to maximize the awards. The MDP optimizes the actions and helps construct the optimal policy.

For developing the MDP, you need to follow the Q-Learning Algorithm, which is an extremely important part of data science and machine learning.

What is Q-Learning Algorithm?

The process of Q-Learning is important for understanding the data from scratch. It involves defining the parameters, choosing the actions from the current state and also choosing the actions from the previous state and then developing a Q-table for maximizing the results or output rewards.

The 4 steps that are involved in Q-Learning:

Initializing parameters – The RL (reinforcement learning) model learns the set of actions that the agent requires in the state, environment and time.
Identifying current state – The model stores the prior records for optimal action definition for maximizing the results. For acting in the present state, the state needs to be identified and perform an action combination for it.
Choosing the optimal action set and gaining the relevant experience – A Q-table is generated from the data with a set of specific states and actions, and the weight of this data is calculated for updating the Q-Table to the following step.
Updating Q-table rewards and next state determination – After the relevant experience is gained and agents start getting environmental records. The reward amplitude helps to present the subsequent step.

In case the Q-table size is huge, then the generation of the model is a time-consuming process. This situation requires Deep Q-learning.

Hopefully, this write-up has provided an outline of Deep Q-Learning and its related concepts. If you wish to learn more about such topics, then keep a tab on the blog section of the E2E Networks website.

Reference Links

https://analyticsindiamag.com/comprehensive-guide-to-deep-q-learning-for-data-science-enthusiasts/

https://medium.com/@jereminuerofficial/a-comprehensive-guide-to-deep-q-learning-8aeed632f52f

October 13, 2022

GAUDI: A Neural Architect for Immersive 3D Scene Generation

The evolution of artificial intelligence in the past decade has been staggering, and now the focus is shifting towards AI and ML systems to understand and generate 3D spaces. As a result, there has been extensive research on manipulating 3D generative models. In this regard, Apple’s AI and ML scientists have developed GAUDI, a method specifically for this job.

An introduction to GAUDI

The GAUDI 3D immersive technique founders named it after the famous architect Antoni Gaudi. This AI model takes the help of a camera pose decoder, which enables it to guess the possible camera angles of a scene. Hence, the decoder then makes it possible to predict the 3D canvas from almost every angle.

What does GAUDI do?

GAUDI can perform multiple functions –

The extensions of these generative models have a tremendous effect on ML and computer vision. Pragmatically, such models are highly useful. They are applied in model-based reinforcement learning and planning world models, SLAM is s, or 3D content creation.
Generative modelling for 3D objects has been used for generating scenes using graf, pigan, and gsn, which incorporate a GAN (Generative Adversarial Network). The generator codes radiance fields exclusively. Using the 3D space in the scene along with the camera pose generates the 3D image from that point. This point has a density scalar and RGB value for that specific point in 3D space. This can be done from a 2D camera view. It does this by imposing 3D datasets on those 2D shots. It isolates various objects and scenes and combines them to render a new scene altogether.
GAUDI also removes GANs pathologies like mode collapse and improved GAN.
GAUDI also uses this to train data on a canonical coordinate system. You can compare it by looking at the trajectory of the scenes.

How is GAUDI applied to the content?

The steps of application for GAUDI have been given below:

Each trajectory is created, which consists of a sequence of posed images (These images are from a 3D scene) encoded into a latent representation. This representation which has a radiance field or what we refer to as the 3D scene and the camera path is created in a disentangled way. The results are interpreted as free parameters. The problem is optimized by and formulation of a reconstruction objective.
This simple training process is then scaled to trajectories, thousands of them creating a large number of views. The model samples the radiance fields totally from the previous distribution that the model has learned.
The scenes are thus synthesized by interpolation within the hidden space.
The scaling of 3D scenes generates many scenes that contain thousands of images. During training, there is no issue related to canonical orientation or mode collapse.
A novel de-noising optimization technique is used to find hidden representations that collaborate in modelling the camera poses and the radiance field to create multiple datasets with state-of-the-art performance in generating 3D scenes by building a setup that uses images and text.

To conclude, GAUDI has more capabilities and can also be used for sampling various images and video datasets. Furthermore, this will make a foray into AR (augmented reality) and VR (virtual reality). With GAUDI in hand, the sky is only the limit in the field of media creation. So, if you enjoy reading about the latest development in the field of AI and ML, then keep a tab on the blog section of the E2E Networks website.

‍

Reference Links

https://www.researchgate.net/publication/362323995_GAUDI_A_Neural_Architect_for_Immersive_3D_Scene_Generation

https://www.technology.org/2022/07/31/gaudi-a-neural-architect-for-immersive-3d-scene-generation/

https://www.patentlyapple.com/2022/08/apple-has-unveiled-gaudi-a-neural-architect-for-immersive-3d-scene-generation.html

Build on the most powerful infrastructure cloud

Contact Sales Get Started for Free

A vector illustration of a tech city using latest cloud technologies & infrastructure

Steps to Build a Healthcare AI Assistant Chatbot Using Llama3-OpenBioLLM-70B

Table of Contents

Why Create Healthcare Assistant Chatbots

Importance of Using a Data Sovereign Architecture

A Guide to Building a Healthcare AI Chatbot

Prerequisites and Initial Setup

Setting Up the Environment

Loading the Dataset

Embedding Model

Storing Embeddings in the Database

Semantic Search

Constructing the LLM Prompt

Creating the Front End

Results

Ensuring Security and Compliance

Conclusion

Inside the H200 Tensor Core GPU: An In-Depth Architectural Analysis

Launching and Using Pixtral-12B on TIR AI Platform: Bill Parsing with vLLM

Step-by-Step Guide to Bulk Invoice Processing Using Llama 3.2-11B

Insights from Jensen Huang’s Keynote Speech | NVIDIA AI Summit Mumbai

A Detailed Comparison of the NVIDIA H200 and H100 Architectures for Developers

Building a Llama 3.2-11B-Based RAG System with Vision Model Integration

A Complete Guide To Customer Acquisition For Startups

Image-based 3D Object Reconstruction State-of-the-Art and trends in the Deep Learning Era

The Main Objective of the 3D Object Reconstruction

A Comprehensive Guide To Deep Q-Learning For Data Science Enthusiasts

GAUDI: A Neural Architect for Immersive 3D Scene Generation

Build on the most powerful infrastructure cloud