Skip to content

openai.md

Latest commit

 

History

History
245 lines (181 loc) · 6.64 KB

openai.md

File metadata and controls

245 lines (181 loc) · 6.64 KB

OpenChat Playground with OpenAI

This page describes how to run OpenChat Playground (OCP) with OpenAI models integration.

Get the repository root

  1. Get the repository root.

    # bash/zsh
REPOSITORY_ROOT=$(git rev-parse --show-toplevel)
    # PowerShell
$REPOSITORY_ROOT = git rev-parse --show-toplevel

Run on local machine

  1. Make sure you are at the repository root.

    cd $REPOSITORY_ROOT

  2. Add OpenAI API Key for OpenAI GPT connection. Make sure you should replace {{OPENAI_API_KEY}} with your OpenAI API key.

    # bash/zsh
dotnet user-secrets --project $REPOSITORY_ROOT/src/OpenChat.PlaygroundApp \
    set OpenAI:ApiKey "{{OPENAI_API_KEY}}"
    # PowerShell
dotnet user-secrets --project $REPOSITORY_ROOT/src/OpenChat.PlaygroundApp `
    set OpenAI:ApiKey "{{OPENAI_API_KEY}}"

    For more details about OpenAI API Keys, refer to the doc, API Keys.

  3. Run the app. The default model OCP uses is GPT-4.1-mini.

    # bash/zsh
dotnet run --project $REPOSITORY_ROOT/src/OpenChat.PlaygroundApp -- \
    --connector-type OpenAI
    # PowerShell
dotnet run --project $REPOSITORY_ROOT/src/OpenChat.PlaygroundApp -- `
    --connector-type OpenAI

    Alternatively, if you want to run with a different model, say GPT-4o, other than the default one, you can specify it as an argument:

    # bash/zsh
dotnet run --project $REPOSITORY_ROOT/src/OpenChat.PlaygroundApp -- \
    --connector-type OpenAI \
    --model gpt-4o
    # PowerShell
dotnet run --project $REPOSITORY_ROOT/src/OpenChat.PlaygroundApp -- `
    --connector-type OpenAI `
    --model gpt-4o

  4. Open your web browser, navigate to http://localhost:5280, and enter prompts.

Run in local container

  1. Make sure you are at the repository root.

    cd $REPOSITORY_ROOT

  2. Build a container.

    docker build -f Dockerfile -t openchat-playground:latest .

  3. Get OpenAI API Key.

    # bash/zsh
API_KEY=$(dotnet user-secrets --project ./src/OpenChat.PlaygroundApp list --json | \
          sed -n '/^\/\//d; p' | jq -r '."OpenAI:ApiKey"')
    # PowerShell
$API_KEY = (dotnet user-secrets --project ./src/OpenChat.PlaygroundApp list --json | `
            Select-String -NotMatch '^//(BEGIN|END)' | ConvertFrom-Json).'OpenAI:ApiKey'

  4. Run the app. The default model OCP uses is GPT-4.1-mini.

    # bash/zsh - from locally built container
docker run -i --rm -p 8080:8080 openchat-playground:latest \
    --connector-type OpenAI \
    --api-key $API_KEY
    # PowerShell - from locally built container
docker run -i --rm -p 8080:8080 openchat-playground:latest `
    --connector-type OpenAI `
    --api-key $API_KEY
    # bash/zsh - from GitHub Container Registry
docker run -i --rm -p 8080:8080 ghcr.io/aliencube/open-chat-playground/openchat-playground:latest \
    --connector-type OpenAI \
    --api-key $API_KEY
    # PowerShell - from GitHub Container Registry
docker run -i --rm -p 8080:8080 ghcr.io/aliencube/open-chat-playground/openchat-playground:latest `
    --connector-type OpenAI `
    --api-key $API_KEY

    Alternatively, if you want to run with a different model, say GPT-4o, other than the default one, you can specify it as an argument:

    # bash/zsh - from locally built container
docker run -i --rm -p 8080:8080 openchat-playground:latest \
    --connector-type OpenAI \
    --api-key $API_KEY \
    --model gpt-4o
    # PowerShell - from locally built container
docker run -i --rm -p 8080:8080 openchat-playground:latest `
    --connector-type OpenAI `
    --api-key $API_KEY `
    --model gpt-4o
    # bash/zsh - from GitHub Container Registry
docker run -i --rm -p 8080:8080 ghcr.io/aliencube/open-chat-playground/openchat-playground:latest \
    --connector-type OpenAI \
    --api-key $API_KEY \
    --model gpt-4o
    # PowerShell - from GitHub Container Registry
docker run -i --rm -p 8080:8080 ghcr.io/aliencube/open-chat-playground/openchat-playground:latest `
    --connector-type OpenAI `
    --api-key $API_KEY `
    --model gpt-4o

  5. Open your web browser, navigate to http://localhost:8080, and enter prompts.

Run on Azure

  1. Make sure you are at the repository root.

    cd $REPOSITORY_ROOT

  2. Login to Azure.

    azd auth login

  3. Check login status.

    azd auth login --check-status

  4. Initialize azd template.

    azd init

    NOTE: You will be asked to provide environment name for provisioning.

  5. Get OpenAI API Key.

    # bash/zsh
API_KEY=$(dotnet user-secrets --project ./src/OpenChat.PlaygroundApp list --json | \
          sed -n '/^\/\//d; p' | jq -r '."OpenAI:ApiKey"')
    # PowerShell
$API_KEY = (dotnet user-secrets --project ./src/OpenChat.PlaygroundApp list --json | `
            Select-String -NotMatch '^//(BEGIN|END)' | ConvertFrom-Json).'OpenAI:ApiKey'

  6. Set OpenAI API Key to azd environment variables.

    azd env set OPENAI_API_KEY $API_KEY

    The default model OCP uses is GPT-4.1-mini. If you want to run with a different model, say gpt-4o, other than the default one, add it to azd environment variables.

    azd env set OPENAI_MODEL gpt-4o

  7. Set the connector type to OpenAI.

    azd env set CONNECTOR_TYPE OpenAI

  8. Run the following commands in order to provision and deploy the app.

    azd up

    NOTE: You will be asked to provide Azure subscription and location for deployment.

    Once deployed, you will be able to see the deployed OCP app URL.

  9. Open your web browser, navigate to the OCP app URL, and enter prompts.

  10. Clean up all the resources.

    azd down --force --purge