LogoLogo
Home
  • Introduction
  • Quickstart
    • Starter guide
    • Core Concepts
      • Stack Type
      • Data Loader
      • Inputs/Outputs
      • Text Splitters
      • Embedding Model
      • Vector Store
      • Large Language Model
      • Memory
      • Chain
    • Testing Stack
    • Deployment
    • Knowledge Base
    • Organization and Teams
    • Secret Keys
    • Logs
  • Components
    • Inputs
    • Outputs
    • Document Loaders
    • Prompts
    • Text Splitters
    • Embeddings
    • Vector Store
    • Retrievers
    • Multi Modals
    • Agents
    • Large Language Models
    • Memories
    • Chains
    • Output Parsers
  • Customization
    • Writing Custom Components in GenAI Stack
    • Build your own custom component
    • Define parameters used for required components
  • Usecases
    • Simple QA using Open Source Large Language Models
    • Multilingual Indic Language Translation
    • Document Search and Chat
    • Chat with Multiple Documents
  • Terminologies
    • RAG - Retrieval Augmented Generation
    • Hybrid Search - Ensemble Retriever
  • REST APIs
    • GenAI Stack REST APIs
    • Chat API Reference
    • Text Generation API Reference
    • Rate Limiting and Sleep Mode
  • Troubleshooting
    • How to verify what is loaded and chunked from the loader?
  • Acknowledgements
    • Special Mentions
Powered by GitBook
On this page
  • Chat
  • Text generation

Was this helpful?

  1. Quickstart

Deployment

PreviousTesting StackNextKnowledge Base

Last updated 10 months ago

Was this helpful?

Deploying your stack is a crucial step in transitioning your chatbot application from the testing phase to live usage. This process involves setting up the application on a server and making it accessible to users through the web.

How to Deploy Your Stack

  1. Initiate Deployment:

    • After thoroughly testing your application through the Chat Interface, click on the "Deploy" button.

  2. Deployment Options:

When you click on the "Deploy" button, a dropdown menu will appear with three options:

  • Free:

    • The stack will be deployed and will automatically shut down after 2 hours.

    • Suitable for short-term testing and demonstrations.

  • Premium:

    • The stack will be deployed and will remain active indefinitely.

    • Ideal for continuous use without worrying about downtime.

  • Dedicated:

    • The stack will be deployed on a dedicated server.

    • You can choose a custom domain.

    • Autoscaling options are available, allowing the application to handle varying loads efficiently.

    • This option is best for high-traffic applications needing robust performance.

  1. Generate and Share Link:

  • Upon successful deployment, a shareable link will be generated.

  • You can share this link to allow others to access and interact with your application easily.

Deploying your chatbot application effectively ensures it is accessible, reliable, and ready for user interaction. Choose the deployment option that best fits your needs and get started today!

Chat

The Input Variables of the Chat are the Queries inputted by the user for chat and the Multiple Files that are to be uploaded by the user for the same, as shown below:

Multiple Inputs can also be uploaded one by one! Multiple types of Files can also be uploaded at the same time in this interface like PDFs, Text, URLs, CSVs, Videos etc to create the final chat. As shown in the Image below, multiple instances of each type of file can be uploaded by the user in the Upload section.

Text generation

After entering the required inputs you can click on the generate button . After the generation is completed the generated text will appear in the bottom.

As mentioned in , if you want to allow user to upload their own Inputs and the Input Component is attached to the Document Loader when you build the stack, you will see an Input Upload sidebar. Your own Inputs can be uploaded here before beginning the chat!

Input components
Chat interface with upload sidebar
Text generation interface