Skip to main content

Deploy Ayushma

Repositories 📂

  • Ayushma: Empowering Nurses with Multilingual ICU Protocols. Leveraging the rapid advancements in AI technology, created multilingual interfaces that assist nurses in rapidly upgrading their knowledge about ICU protocols. 💉

  • Ayushma_fe: Auto deployed to ayushma.ohc.in for production branch. All pull requests have preview builds powered by Vercel. 🌐

Requirements 📋

  • Python 3.8 🐍
  • Postgres 15 🐘
  • OpenAI Account with a valid API Key 🔑
  • Pinecone Account with a valid API Key 🔍

Env Variables 🔑

VariableDescription
AI_NAMEName of the AI (default: Ayushma)
OPENAI_API_KEYOpenAI API Key 🔑
PINECONE_API_KEYPinecone API Key 🔍
PINECONE_ENVIRONMENTPinecone Environment
PINECONE_INDEXPinecone Index
CURRENT_DOMAINCurrent Domain where the frontend is hosted. ex. https://ayushma.ohc.network
EMAIL_HOSTSES Email Host (Optional) ✉️
EMAIL_USERSES Email User (Optional) ✉️
EMAIL_PASSWORDSES Email Password (Optional) ✉️
GOOGLE_APPLICATION_CREDENTIALSGoogle Cloud Credentials (Optional). These should be in a file named gc_credential.json in the root of the project ☁️
S3_SECRET_KEYAWS S3 Secret Key (Optional) 🔑
S3_KEY_IDAWS S3 Key ID (Optional) 🔑
S3_BUCKET_NAMEAWS S3 Bucket Name (Optional) 🗄️
S3_REGIONAWS S3 Region (Optional) 🌍
GOOGLE_RECAPTCHA_SECRET_KEYGoogle Recaptcha Secret Key (Optional) 🔐

Images Required 🖼️

  • Ayushma:latest: Latest production Image from GitHub container registry 📦
  • postgres:15: Postgres 15 pulled from Docker Hub 🐘
  • redis:6: Redis is an open-source, networked, in-memory, key-value data store with optional durability. 🔴
  • watchtower: With watchtower you can update the running version of your containerized app simply by pushing a new image to the Docker Hub or your own image registry. Watchtower will pull down your new image, gracefully shut down your existing container and restart it with the same options that were used when it was deployed initially.