Build a Retrieval Augmented Generation (RAG) AI

This guide will instruct you through setting up and deploying your first application with Cloudflare AI. You will build a fully-featured AI-powered application, using tools like Workers AI, Vectorize, D1, and Cloudflare Workers.

At the end of this tutorial, you will have built an AI tool that allows you to store information and query it using a Large Language Model. This pattern, known as Retrieval Augmented Generation, or RAG, is a useful project you can build by combining multiple aspects of Cloudflare’s AI toolkit. You do not need to have experience working with AI tools to build this application.

1. Sign up for a Cloudflare account ↗.
2. Install npm ↗.
3. Install Node.js ↗.

Node.js version manager

Use a Node version manager like Volta ↗ or nvm ↗ to avoid permission issues and change Node.js versions. Wrangler, discussed later in this guide, requires a Node version of 16.17.0 or later.

You will also need access to Vectorize.

1. Create a new Worker project

C3 (create-cloudflare-cli) is a command-line tool designed to help you setup and deploy Workers to Cloudflare as fast as possible.

Open a terminal window and run C3 to create your Worker project:

npm

npm create cloudflare@latest -- rag-ai-tutorial

yarn

yarn create cloudflare@latest rag-ai-tutorial

pnpm

pnpm create cloudflare@latest rag-ai-tutorial

For setup, select the following options:

• For What would you like to start with?, choose Hello World example.
• For Which template would you like to use?, choose Hello World Worker.
• For Which language do you want to use?, choose JavaScript.
• For Do you want to use git for version control?, choose Yes.
• For Do you want to deploy your application?, choose No (we will be making some changes before deploying).

In your project directory, C3 has generated several files.

What files did C3 create?

1. wrangler.toml: Your Wrangler configuration file.
2. worker.js (in /src): A minimal 'Hello World!' Worker written in ES module syntax.
3. package.json: A minimal Node dependencies configuration file.
4. package-lock.json: Refer to npm documentation on package-lock.json ↗.
5. node_modules: Refer to npm documentation node_modules ↗.

Now, move into your newly created directory:

cd rag-ai-tutorial

2. Develop with Wrangler CLI

The Workers command-line interface, Wrangler, allows you to create, test, and deploy your Workers projects. C3 will install Wrangler in projects by default.

After you have created your first Worker, run the wrangler dev command in the project directory to start a local server for developing your Worker. This will allow you to test your Worker locally during development.

npx wrangler dev --remote

Note

If you have not used Wrangler before, it will try to open your web browser to login with your Cloudflare account.

If you have issues with this step or you do not have access to a browser interface, refer to the wrangler login documentation for more information.

You will now be able to go to http://localhost:8787 ↗ to see your Worker running. Any changes you make to your code will trigger a rebuild, and reloading the page will show you the up-to-date output of your Worker.

3. Adding the AI binding

To begin using Cloudflare’s AI products, you can add the ai block to wrangler.toml. This will set up a binding to Cloudflare’s AI models in your code that you can use to interact with the available AI models on the platform.

This example features the @cf/meta/llama-3-8b-instruct model, which generates text.

[ai]
binding = "AI"

Now, find the src/index.js file. Inside the fetch handler, you can query the AI binding:

export default {
  async fetch(request, env, ctx) {
    const answer = await env.AI.run("@cf/meta/llama-3-8b-instruct", {
      messages: [{ role: "user", content: `What is the square root of 9?` }],
    });

    return new Response(JSON.stringify(answer));
  },
};

By querying the LLM through the AI binding, we can interact directly with Cloudflare AI’s large language models directly in our code. In this example, we are using the @cf/meta/llama-3-8b-instruct model, which generates text.

You can deploy your Worker using wrangler:

npx wrangler deploy

Making a request to your Worker will now generate a text response from the LLM, and return it as a JSON object.

curl https://example.username.workers.dev

{"response":"Answer: The square root of 9 is 3."}

4. Adding embeddings using Cloudflare D1 and Vectorize

Embeddings allow you to add additional capabilities to the language models you can use in your Cloudflare AI projects. This is done via Vectorize, Cloudflare’s vector database.

To begin using Vectorize, create a new embeddings index using wrangler. This index will store vectors with 768 dimensions, and will use cosine similarity to determine which vectors are most similar to each other:

npx wrangler vectorize create vector-index --dimensions=768 --metric=cosine

Then, add the configuration details for your new Vectorize index to wrangler.toml:

# ... existing wrangler configuration

[[vectorize]]
binding = "VECTOR_INDEX"
index_name = "vector-index"

A vector index allows you to store a collection of dimensions, which are floating point numbers used to represent your data. When you want to query the vector database, you can also convert your query into dimensions. Vectorize is designed to efficiently determine which stored vectors are most similar to your query.

To implement the searching feature, you must set up a D1 database from Cloudflare. In D1, you can store your app’s data. Then, you change this data into a vector format. When someone searches and it matches the vector, you can show them the matching data.

Create a new D1 database using wrangler:

npx wrangler d1 create database

Then, paste the configuration details output from the previous command into wrangler.toml:

# ... existing wrangler configuration

[[d1_databases]]
binding = "DB" # available in your Worker on env.DB
database_name = "database"
database_id = "abc-def-geh" # replace this with a real database_id (UUID)

In this application, we’ll create a notes table in D1, which will allow us to store notes and later retrieve them in Vectorize. To create this table, run a SQL command using wrangler d1 execute:

npx wrangler d1 execute database --remote --command "CREATE TABLE IF NOT EXISTS notes (id INTEGER PRIMARY KEY, text TEXT NOT NULL)"

Now, we can add a new note to our database using wrangler d1 execute:

npx wrangler d1 execute database --remote --command "INSERT INTO notes (text) VALUES ('The best pizza topping is pepperoni')"

5. Creating notes and adding them to Vectorize

To expand on your Workers function in order to handle multiple routes, we will add hono, a routing library for Workers. This will allow us to create a new route for adding notes to our database. Install hono using npm:

npm install hono

Then, import hono into your src/index.js file. You should also update the fetch handler to use hono:

import { Hono } from "hono";
const app = new Hono();

app.get("/", async (c) => {
  const answer = await c.env.AI.run("@cf/meta/llama-3-8b-instruct", {
    messages: [{ role: "user", content: `What is the square root of 9?` }],
  });

  return c.json(answer);
});

export default app;

This will establish a route at the root path / that is functionally equivalent to the previous version of your application. Now, we can add a new route for adding notes to our database.

This example features the @cf/baai/bge-base-en-v1.5 model, which can be used to create an embedding. Embeddings are stored and retrieved inside Vectorize, Cloudflare’s vector database. The user query is also turned into an embedding so that it can be used for searching within Vectorize.

app.post("/notes", async (c) => {
  const { text } = await c.req.json();
  if (!text) {
    return c.text("Missing text", 400);
  }

  const { results } = await c.env.DB.prepare(
    "INSERT INTO notes (text) VALUES (?) RETURNING *",
  )
    .bind(text)
    .run();

  const record = results.length ? results[0] : null;

  if (!record) {
    return c.text("Failed to create note", 500);
  }

  const { data } = await c.env.AI.run("@cf/baai/bge-base-en-v1.5", {
    text: [text],
  });
  const values = data[0];

  if (!values) {
    return c.text("Failed to generate vector embedding", 500);
  }

  const { id } = record;
  const inserted = await c.env.VECTOR_INDEX.upsert([
    {
      id: id.toString(),
      values,
    },
  ]);

  return c.json({ id, text, inserted });
});

This function does the following things:

1. Parse the JSON body of the request to get the text field.
2. Insert a new row into the notes table in D1, and retrieve the id of the new row.
3. Convert the text into a vector using the embeddings model of the LLM binding.
4. Upsert the id and vectors into the vector-index index in Vectorize.
5. Return the id and text of the new note as JSON.

By doing this, you will create a new vector representation of the note, which can be used to retrieve the note later.

6. Querying Vectorize to retrieve notes

To complete your code, you can update the root path (/) to query Vectorize. You will convert the query into a vector, and then use the vector-index index to find the most similar vectors.

The topK parameter limits the number of vectors returned by the function. For instance, providing a topK of 1 will only return the most similar vector based on the query. Setting topK to 5 will return the 5 most similar vectors.

Given a list of similar vectors, you can retrieve the notes that match the record IDs stored alongside those vectors. In this case, we are only retrieving a single note - but you may customize this as needed.

You can insert the text of those notes as context into the prompt for the LLM binding. This is the basis of Retrieval-Augmented Generation, or RAG: providing additional context from data outside of the LLM to enhance the text generated by the LLM.

We’ll update the prompt to include the context, and to ask the LLM to use the context when responding:

import { Hono } from "hono";
const app = new Hono();

// Existing post route...
// app.post('/notes', async (c) => { ... })

app.get('/', async (c) => {
  const question = c.req.query('text') || "What is the square root of 9?"

  const embeddings = await c.env.AI.run('@cf/baai/bge-base-en-v1.5', { text: question })
  const vectors = embeddings.data[0]

  const vectorQuery = await c.env.VECTOR_INDEX.query(vectors, { topK: 1 });
  const vecId = vectorQuery.matches[0].id

  let notes = []
  if (vecId) {
    const query = `SELECT * FROM notes WHERE id = ?`
    const { results } = await c.env.DB.prepare(query).bind(vecId).all()
    if (results) notes = results.map(vec => vec.text)
  }

  const contextMessage = notes.length
    ? `Context:\n${notes.map(note => `- ${note}`).join("\n")}`
    : ""

  const systemPrompt = `When answering the question or responding, use the context provided, if it is provided and relevant.`

  const { response: answer } = await c.env.AI.run(
    '@cf/meta/llama-3-8b-instruct',
    {
      messages: [
        ...(notes.length ? [{ role: 'system', content: contextMessage }] : []),
        { role: 'system', content: systemPrompt },
        { role: 'user', content: question }
      ]
    }
  )

  return c.text(answer);
});

app.onError((err, c) => {
  return c.text(err);
});

export default app;

7. Deleting notes and vectors

If you no longer need a note, you can delete it from the database. Any time that you delete a note, you will also need to delete the corresponding vector from Vectorize. You can implement this by building a DELETE /notes/:id route in your src/index.js file:

app.delete('/notes/:id', async (c) => {
  const { id } = c.req.param();

  const query = `DELETE FROM notes WHERE id = ?`
  await c.env.DATABASE.prepare(query).bind(id).run()

  await c.env.VECTOR_INDEX.deleteByIds([id])

  return c.status(204)
})

8. Deploy your project

If you did not deploy your Worker during step 1, deploy your Worker via Wrangler, to a *.workers.dev subdomain, or a Custom Domain, if you have one configured. If you have not configured any subdomain or domain, Wrangler will prompt you during the publish process to set one up.

npx wrangler deploy

Preview your Worker at <YOUR_WORKER>.<YOUR_SUBDOMAIN>.workers.dev.

Note

When pushing to your *.workers.dev subdomain for the first time, you may see 523 errors while DNS is propagating. These errors should resolve themselves after a minute or so.

Related resources

A full version of this codebase is available on GitHub. It includes a frontend UI for querying, adding, and deleting notes, as well as a backend API for interacting with the database and vector index. You can find it here: github.com/kristianfreeman/cloudflare-retrieval-augmented-generation-example ↗.

To do more:

• Explore the reference diagram for a Retrieval Augmented Generation (RAG) Architecture.
• Review Cloudflare’s AI documentation.
• Review Tutorials to build projects on Workers.
• Explore Examples to experiment with copy and paste Worker code.
• Understand how Workers works in Reference.
• Learn about Workers features and functionality in Platform.
• Set up Wrangler to programmatically create, test, and deploy your Worker projects.