@motorro/firebase-ai-chat-openai

Firebase OpenAI chat library

OpenAI chat library. See top-level documentation for complete reference.

OpenAI setup

We also need to set up the OpenAI API. To do this we need to get the OpenAI API key and to define the used assistant ID:

const region = "europe-west1";
const openAiApiKey = defineSecret("OPENAI_API_KEY");
const openAiAssistantId = defineString("OPENAI_ASSISTANT_ID");

const options: CallableOptions = {
  secrets: [openAiApiKey],
  region: region,
  invoker: "public"
};

Refer to Configure your environment article for more information on setting environment and secret variables for your functions.

Command dispatcher configuration

The requests to front-facing functions return to user as fast as possible after changing the chat state in Firestore. As soon as the AI run could take a considerable time, we run theme in a Cloud Task "offline" from the client request. To execute the Assistant run we use the second class from the library - the OpenAiChatWorker. To create it, use the AiChat factory we created as described in the main documentation.

To register the Cloud Task handler you may want to create the following function:

import {onTaskDispatched} from "firebase-functions/v2/tasks";
import OpenAI from "openai";
import {OpenAiWrapper, Meta} from "@motorro/firebase-ai-chat-openai";

export const calculator = onTaskDispatched(
    {
      secrets: [openAiApiKey],
      retryConfig: {
        maxAttempts: 1,
        minBackoffSeconds: 30
      },
      rateLimits: {
        maxConcurrentDispatches: 6
      },
      region: region
    },
    async (req) => {
      // Create and run a worker
      // See the `dispatchers` definitions below
      await chatFactory.worker(new OpenAI({apiKey: openAiApiKey.value()}), dispatchers).dispatch(
          req,
          (chatDocumentPath: string, meta: Meta) => {
             // Optional task completion handler
             // Meta - some meta-data passed to chat operation
          }   
      );
    }
);

The OpenAiChatWorker handles the OpenAiChatCommand and updates OpenAiChatState with the results.

Full example is available in the sample Firebase project.