Chitchat Bot

The chitchat bot can have informal conversations with the user on day-to-day topics. The chitchat bot uses the following ACE Agent features:

• Using LLM for responding to user queries

• Colang 2.0 based bot

• Support deployment using the Chat Engine Server Architecture and Event Architecture

Docker-based bot deployment

The chitchat sample bot uses OpenAI gpt-4-turbo as the main model. This sample bot is present in the quickstart directory at ./samples/chitchat_bot/.

1. Set the OpenAI API key environment variable.

   export OPENAI_API_KEY=...
   

2. Set your NGC Personal API key in the NGC_CLI_API_KEY environment variable.

   export NGC_CLI_API_KEY=...
   

3. Prepare the environment for the Docker compose commands.

   export BOT_PATH=./samples/chitchat_bot/
   source deploy/docker/docker_init.sh
   

4. Deploy the Search and NLP models. This might take 20-40 minutes for the first time. With the chitchat sample bot, the Riva ASR (Automatic Speech Recognition) and TTS (Text to Speech) models will be deployed.

   docker compose -f deploy/docker/docker-compose.yml up model-utils-speech
   

5. Deploy the ACE Agent microservices. Deploy the Chat Controller and Chat Engine microservices.

   docker compose -f deploy/docker/docker-compose.yml up speech-event-bot -d
   

6. Wait for a few minutes for all services to be ready. You can check the Docker logs for individual microservices to confirm. You will see log print Server listening on 0.0.0.0:50055 in the Docker logs for the Chat Controller container.

7. Interact with the bot using the URL http://<workstation IP>:7006/. For accessing the mic on the browser, we need to either convert http to https endpoint by adding SSL validation or update your chrome://flags/ or edge://flags/ to allow http://<workstation IP>:7006 as a secure endpoint.