chat-predict-cloudfunction-java

Java Cloud Function that wraps the PaLM Chat Bison Models using langchain4j

This application demonstrates a Cloud Function written in Java that initializes the Vertex AI Chat module and then provides an endpoint to invoke PaLM Chat Bison model. It uses the langchain4j package.

NOTE: Before you move forward, ensure that you have followed the instructions in SETUP.md. Additionally, ensure that you have cloned this repository and are currently in the chat-predict-cloudfunction-java folder for the rest of the commands.

Environment variables required

Your Cloud Function requires access to two environment variables:

• GCP_PROJECT : This the Google Cloud Project Id.
• GCP_REGION : This is the region in which you are deploying your Cloud Function. For e.g. us-central1.

These variables are needed since the Vertex AI initialization needs the Google Cloud Project Id and the region.

In Cloud Shell, execute the following commands:

export GCP_PROJECT='<Your GCP Project Id>'  # Change this
export GCP_REGION='us-central1'             # If you change this, make sure region is supported by Model Garden. When in doubt, keep this.

These variables can be set via the following instructions via any of the following ways:

1. At the time of deploying the Google Cloud Function. We will be using this method in the next section when we deploy the Cloud Function.
2. Updating the environment variables after deploying the Google Cloud Function.

Deploying the Cloud Function

Assuming that you have a copy of this project on your local machine with gcloud SDK setup on the machine, follow these steps:

1. Go to the root folder of this project where the pom.xml file is present.

2. Provide the following command:

   gcloud functions deploy PredictChatFunction \
   --gen2 \
   --runtime=java11 \
   --region=$GCP_REGION \
   --source=. \
   --entry-point=gcfv2.PredictChatFunction \
   --trigger-http \
   --set-env-vars=GCP_PROJECT=$GCP_PROJECT,GCP_REGION=$GCP_REGION \
   --allow-unauthenticated

Invoking the Cloud Function

Since this Cloud Function is deployed with a HTTP trigger, you can directly invoke it. Sample calls are shown below:

curl -m 70 -X POST https://$GCP_REGION-$GCP_PROJECT.cloudfunctions.net/PredictChatFunction \
-H "Content-Type: application/json" \
-d '{
  "prompt": "what is langchain4j?"
}'