Using EdgeDB AI​

Configuring a provider​

To configure a provider, you will first need to obtain an API key for your chosen provider, which you may do from their respective sites:

• OpenAI API keys

• Mistral API keys

• Anthropic API keys

With your API key, you may now configure in the UI by clickin the “Add Provider” button, selecting the appropriate API, and pasting your key in the “Secret” field.

You may alternatively configure a provider via EdgeQL:

configure current database
insert ext::ai::OpenAIProviderConfig {
  secret := 'sk-....',
};

This object has other properties as well, including client_id and api_url, which can be set as strings to override the defaults for the chosen provider.

We have provider config types for each of the three supported APIs:

• OpenAIProviderConfig

• MistralProviderConfig

• AnthropicProviderConfig

Add an index​

To start using EdgeDB AI on a type, create an index:

module default {
  type Astronomy {
    content: str;
    deferred index ext::ai::index(embedding_model := 'text-embedding-3-small')
      on (.content);
  }
};

In this example, we have added an AI index on the Astronomy type’s content property using the text-embedding-3-small model. Once you have the index in your schema, create and apply your migration, and you’re ready to start running queries!

You may want to include multiple properties in your AI index. Fortunately, you can define an AI index on an expression:

module default {
  type Astronomy {
    climate: str;
    atmosphere: str;
    deferred index ext::ai::index(embedding_model := 'text-embedding-3-small')
      on (.climate ++ ' ' ++ .atmosphere);
  }
};

Run a semantic similarity query​

Once your index has been migrated, running a query against the embeddings is super simple:

select ext::ai::search(Astronomy, query)

Simple, but you’ll still need to generate embeddings from your query or pass in existing embeddings. If your ultimate goal is retrieval-augmented generation (i.e., RAG), we’ve got you covered.

Use RAG via HTTP​

By making an HTTP request to https://<edgedb-host>:<port>/branch/<branch-name>/ai/rag, you can generate text via the generative AI API of your choice within the context of a type with a deferred embedding index.

$ 

curl --json '{

    "query": "What color is the sky on Mars?",
    "model": "gpt-4-turbo-preview",
    "context": {"query":"select Astronomy"}
  }' https://<edgedb-host>:<port>/branch/<branch-name>/ai/rag
{"response": "The sky on Mars is red."}

Since LLMs are often slow, it may be useful to stream the response. To do this, add "stream": true to your request JSON.

Use RAG via JavaScript​

@edgedb/ai offers a convenient wrapper around ext::ai. Install it with npm install @edgedb/ai (or via your package manager of choice) and implement it like this example:

import { createClient } from "edgedb";
import { createAI } from "@edgedb/ai";

const client = createClient();

const gpt4AI = createAI(client, {
  model: "gpt-4-turbo-preview",
});

const blogAI = gpt4AI.withContext({
  query: "select Astronomy"
});

console.log(await blogAI.queryRag(
  "What color is the sky on Mars?"
));