https://github.com/klich3/firebase-gpt-chat-completion-stream

Example of ChatGPT Stream implementation in Firebase with functions. For this method you have to use `fetch`.
https://github.com/klich3/firebase-gpt-chat-completion-stream

chatgpt chatgpt-api firebase firebase-function firebase-functions gpt openai openai-api

Last synced: about 1 month ago
JSON representation

Example of ChatGPT Stream implementation in Firebase with functions. For this method you have to use `fetch`.

• Host: GitHub
• URL: https://github.com/klich3/firebase-gpt-chat-completion-stream
• Owner: klich3
• License: mit
• Created: 2023-06-01T09:51:41.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-03-18T12:05:47.000Z (10 months ago)
• Last Synced: 2024-04-14T11:27:08.027Z (9 months ago)
• Topics: chatgpt, chatgpt-api, firebase, firebase-function, firebase-functions, gpt, openai, openai-api
• Language: JavaScript
• Homepage:
• Size: 91.8 KB
• Stars: 11
• Watchers: 2
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • Funding: .github/FUNDING.yml
  • License: LICENSE
  • Citation: CITATION.cff

Awesome Lists containing this project

README

        
# Firebase Cloud Functions for GPT Chat Completion

![firebase+gpt](images/firebase_and_gpt.jpg?raw=true)

Example of ChatGPT ***Stream*** implementation in Firebase with functions. For this method you have to use `fetch`.

***Issue:***: This method seems to be slower than the other Stream method because it does not stream.

## SETUP

In `functions` folder create file `.env` with your OpenAI Api key.

Sample: 

```text

OPEN_AI_KEY="sk-"

```

## SETUP WITH CUSTOM FUNCTIONS FOLDER

To use functions in a custom folder different from the default, suppose the destination folder is `functions` inside we create a new folder named `gpt-chat-completion-stream` and copy files from this project that are inside the `functions` folder. Then edit the `firebase.json` file from the root folder of your project.

```json

{

	...

	"firestore": {

		...

	},

	...

	"functions": [

		{

			"source": "functions/gpt-chat-completion-stream",

			"codebase": "gpt-chat-completion-stream",

			"predeploy": ["npm --prefix \"$RESOURCE_DIR\" run lint"],

			"ignore": [

				"node_modules",

				".git",

				"firebase-debug.log",

				"firebase-debug.*.log"

			],

			"runtime": "nodejs16"

		}

	]

	...

}

```

## Deploy

Run `firebase deploy --only functions:gpt-chat-completion-stream`

## Sample usage in REACT

```javascript

const [responseChunk, setResponseChunk] = useState("");

let responseStream = "";

const callPrompt = (e:any) => {

	fetch("https://-.cloudfunctions.net/gptPromptStream", {

		method: "POST",

		body: JSON.stringify({

			prompt: [{role: "user", content: "Hello world"}],

		}),

	}).then(async (response) => {

		if(!response && !response.body) return;

		const decoder = new TextDecoder("utf-8");

		const reader = response?.body?.getReader();

		while (true) {

			const { done, value } = await reader.read();

			

			if (done) {

				break;

			}

			const text = decoder.decode(value);

			responseStream += text;

			setResponseChunk(responseStream);

		}

	})

	.catch((err) => {

		console.error(`Error occurred while attempting Fetch request: ${err}`);

	});

};

...

//JSX part:

<>

	Call prompt

	
Response

	
{responseChunk}

>

```


---

# BEWARE 
⚠️


This method may no longer be functional as the LangChain package is updated daily.

If you feel like collaborating you can create Pull Request...