Deploy a RAG Pipeline

SciPhi provides the fastest and most featureful way for developers to deploy a high-quality Retrieval-Augmented Generation (RAG) engine through the R2R framework. We’ll cover deploying a vector database and a configurable RAG engine powered by R2R.

You can deploy a RAG pipeline by creating an account with the SciPhi Cloud application. Afterwards, click Deploy to navigate to

Deploy a vector database

R2R is built around Postgres with pgvector. To get started we must first deploy a SciPhi managed vector database instance which will then connect to our selected RAG pipeline.

Selecting your pipeline

Next, click on the deployment solution which corresponds to your use case, or click Custom to link to your own custom build. The form will then auto-populate with relevant information.

We strongly recommend starting with the Q&A RAG solution while SciPhi Cloud remains in beta.

Providing Secrets

During the deployment process, you’ll need to link to a vector database. SciPhi integrates with LanternDB to provide a managed Postgres database. Alternatively, you may connect with your own remote Postgres database provider, such as supabase.

During deployment you must provide any necessary secret variables, such as API keys. These secrets are encrypted at all times during transmission and storage. Our infrastructure is hosted on Google Cloud and our secrets are provisioned through Google Cloud’s Secret Manager. You can read more about SciPhi’s security policy here.

For the basic RAG example shown above a valid OPENAI_API_KEY must be provided or else the pipeline will fail at bulid or runtime.


Once you’ve provided the required secrets, click the “Deploy” button to create your RAG pipeline. SciPhi will handle the deployment process, setting up the necessary infrastructure and services based on your configuration.

In the case of the basic RAG example shown previously this includes a managed Postgres database with pgvector, peformant logging with a Redis, and serverless deployement through Google Cloud Platform.

Upon successful deployment, you will be provided with a unique URL (e.g., that serves as the endpoint for accessing and interacting with your deployed RAG pipeline using the R2R client.