Running LLM As Chatbot in your cloud

This repository is a fork of deep-diver/LLM-As-Chatbot. The only difference from the original repo is the .dstack.yml file, which allows you to run LLM-As-Chatbot in your cloud account with a single command. This file allows you to run LLM-As-Chatbot in your cloud with a single dstack run command, automatically provisioning cloud resources for you.

1. Install and set up dstack

pip install "dstack[was,gcp,azure]" -U
dstack start

Once the server is up, make sure to log in and create a project with your cloud credentials (AWS, GCP, or Azure). After creating the project, copy its dstack config command and run it locally to configure the CLI to use this project.

2. Create a profile

Create a .dstack/profiles.yml file that points to the created project and describes the resources.

Example:

profiles:
  - name: gcp
    project: gcp
    resources:
      memory: 48GB
      gpu:
        memory: 24GB
    default: true

3. Initialization

Run the dstack init command:

dstack init

4. Run the app in your cloud

Use the dstack run command:

dstack run . --build

This command will build the environment and run LLM-As-Chatbot in your cloud.

dstack will automatically forward the port to your local machine, providing secure and convenient access.

More information

For more details on how dstack works, check out its documentation.