Medical Chatbot using LLM & Gale Encyclopedia of Medicine

Built a medical chatbot using The GALE ENCYCLOPEDIA of MEDICINE, allowing users to ask questions about diseases and receive precise, informative responses. This chatbot functions as a valuable resource for those seeking medical knowledge, offering an interactive, conversational experience similar to ChatGPT. It leverages advanced technologies, including the LangChain framework for language model management, Hugging Face's sentence transformers model for 384-dimensional embeddings, Pinecone as a vector database, OpenAI's GPT for natural language understanding, and a user-friendly interface developed with Flask.

How to run?

STEPS:

Clone the repository

Project repo: https://github.com/robinyUArizona/MedGPT-DiagnosisBot-LargeLanguageModel.git

STEP 01- Create a conda environment after opening the repository

conda create -n medchat_env python=3.10 -y

conda activate medchat_env

STEP 02- install the requirements

pip install -r requirements.txt

Create a .env file in the root directory and add your Pinecone & openai credentials as follows:

PINECONE_API_KEY = "xxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
OPENAI_API_KEY = "xxxxxxxxxxxxxxxxxxxxxxxxxxxxx"

# run the following command to store embeddings to pinecone
python store_index.py

# Finally run the following command
python app.py

Now,

open up localhost:

Techstack Used:

• LLM Framework: LangChain
• Embeddings Models: Hugging Face Embeddings - sentence transfomers model 384 dimensional
• Vector Database: Pinecone
• LLM: OpenAI, GPT
• UI: Flask

AWS-CICD-Deployment-with-Github-Actions

1. Login to AWS console.

2. Create IAM user for deployment

#with specific access

1. EC2 access : It is virtual machine

2. ECR: Elastic Container registry to save your docker image in aws


#Description: About the deployment

1. Build docker image of the source code

2. Push your docker image to ECR

3. Launch Your EC2 

4. Pull Your image from ECR in EC2

5. Lauch your docker image in EC2

#Policy:

1. AmazonEC2ContainerRegistryFullAccess

2. AmazonEC2FullAccess

3. Create ECR repo to store/save docker image

- Save the URI: 970547337635.dkr.ecr.ap-south-1.amazonaws.com/medicalchatbot

4. Create EC2 machine (Ubuntu)

5. Open EC2 and Install docker in EC2 Machine:

#optinal

sudo apt-get update -y

sudo apt-get upgrade

#required

curl -fsSL https://get.docker.com -o get-docker.sh

sudo sh get-docker.sh

sudo usermod -aG docker ubuntu

newgrp docker

6. Configure EC2 as self-hosted runner:

setting>actions>runner>new self hosted runner> choose os> then run command one by one

7. Setup github secrets:

• AWS_ACCESS_KEY_ID
• AWS_SECRET_ACCESS_KEY
• AWS_DEFAULT_REGION
• ECR_REPO
• PINECONE_API_KEY
• OPENAI_API_KEY