Skip to content

Latest commit

 

History

History
136 lines (98 loc) · 4.29 KB

README.md

File metadata and controls

136 lines (98 loc) · 4.29 KB

Firebase Genkit + Anthropic AI

Firebase Genkit <> Anthropic AI Plugin

Anthropic AI Community Plugin for Google Firebase Genkit

Github lerna version NPM Downloads GitHub Org's stars GitHub License Static Badge
GitHub Issues or Pull Requests GitHub Issues or Pull Requests GitHub commit activity

genkitx-anthropic is a community plugin for using Anthropic AI and all its supported models with Firebase Genkit.

This Genkit plugin allows to use Anthropic AI models through their official APIs.

If you want to use Anthropic AI models through Google Vertex AI, please refer to the official Vertex AI plugin.

Supported models

The plugin supports the most recent Anthropic models: Claude 3.5 Sonnet, Claude 3 Opus, Claude 3 Sonnet, and Claude 3 Haiku.

Installation

Install the plugin in your project with your favorite package manager:

  • npm install genkitx-anthropic
  • yarn add genkitx-anthropic

Usage

Initialize

import 'dotenv/config';

import { configureGenkit } from '@genkit-ai/core';
import { defineFlow, startFlowsServer } from '@genkit-ai/flow';
import { anthropic } from 'genkitx-anthropic';

configureGenkit({
  plugins: [
    // Anthropic API key is required and defaults to the ANTHROPIC_API_KEY environment variable
    anthropic({ apiKey: process.env.ANTHROPIC_API_KEY }),
  ],
  logLevel: 'debug',
  enableTracingAndMetrics: true,
});

Basic examples

The simplest way to call the text generation model is by using the helper function generate:

// ...configure Genkit (as shown above)...

const response = await generate({
  model: claude3Haiku, // model imported from genkitx-anthropic
  prompt: 'Tell me a joke.',
});

console.log(await response.text());

Multi-modal prompt

// ...configure Genkit (as shown above)...

const response = await generate({
  model: claude3Haiku,
  prompt: [
    { text: 'What animal is in the photo?' },
    { media: { url: imageUrl } },
  ],
  config: {
    // control of the level of visual detail when processing image embeddings
    // Low detail level also decreases the token usage
    visualDetailLevel: 'low',
  },
});
console.log(await response.text());

Within a flow

// ...configure Genkit (as shown above)...

export const myFlow = defineFlow(
  {
    name: 'menuSuggestionFlow',
    inputSchema: z.string(),
    outputSchema: z.string(),
  },
  async (subject) => {
    const llmResponse = await generate({
      prompt: `Suggest an item for the menu of a ${subject} themed restaurant`,
      model: claude3Opus,
    });

    return llmResponse.text();
  }
);
startFlowsServer();

Contributing

Want to contribute to the project? That's awesome! Head over to our Contribution Guidelines.

Need support?

Note

This repository depends on Google's Firebase Genkit. For issues and questions related to Genkit, please refer to instructions available in Genkit's repository.

Reach out by opening a discussion on Github Discussions.

Credits

This plugin is proudly maintained by the team at The Fire Company. 🔥

License

This project is licensed under the Apache 2.0 License.