Google Vertex AI

To enable Vertex AI models with Letta, set GOOGLE_CLOUD_PROJECT and GOOGLE_CLOUD_LOCATION in your environment variables.

You can use Letta with Vertex AI by configuring your GCP project ID and region.

Enabling Google Vertex AI as a provider

To start, make sure you are authenticated with Google Vertex AI:

$ gcloud auth application-default login

To enable the Google Vertex AI provider, you must set the GOOGLE_CLOUD_PROJECT and GOOGLE_CLOUD_LOCATION environment variables. You can get these values from the Vertex console.

$ export GOOGLE_CLOUD_PROJECT='your-project-id'
> export GOOGLE_CLOUD_LOCATION='us-central1'

Using the `docker run` server with Google Vertex AI

To enable Google Vertex AI models, simply set your GOOGLE_CLOUD_PROJECT and GOOGLE_CLOUD_LOCATION as environment variables:

$ # replace `~/.letta/.persist/pgdata` with wherever you want to store your agent data
> docker run \
>   -v ~/.letta/.persist/pgdata:/var/lib/postgresql/data \
>   -p 8283:8283 \
>   -e GOOGLE_CLOUD_PROJECT="your-project-id" \
>   -e GOOGLE_CLOUD_LOCATION="us-central1" \
>   letta/letta:latest

CLI (pypi only)

Using `letta run` and `letta server` with Google AI

Make sure you install the required dependencies with:

$ pip install 'letta[google]'

To chat with an agent, run:

$ export GOOGLE_CLOUD_PROJECT='your-project-id'
> export GOOGLE_CLOUD_LOCATION='us-central1'
> letta run

To run the Letta server, run:

$ export GOOGLE_CLOUD_PROJECT='your-project-id'
> export GOOGLE_CLOUD_LOCATION='us-central1'
> letta server

To select the model used by the server, use the dropdown in the ADE or specify a LLMConfig object in the Python SDK.