yandricr / gpti-js Goto Github PK

Will there be support to use the role 'system' in messages for GPT Models, so we could set our own system instructions? Thanks.

{
api: 'dalleai',
code: 400,
status: false,
message: 'error',
doc: 'https://gpti.projectsrpp.repl.co/'
}

Hello, I use bing as you wrote in readme.md. but returns 500

{
  code: 500,
  status: false,
  error: 'INTERNAL_SERVER_ERROR',
  message: 'general (unknown) error'
}

Module is not working right now.

Hello! Thank you for this free services!
Recently when i tried to use Emi model, i keep getting error code 500

{
    "code": 500,
    "status": false,
    "error": "INTERNAL_SERVER_ERROR",
    "message": "general (unknown) error"
}

Hello! Thank you for this amazing project! I was wondering if there are any plans to support the newest OpenAI GPT-4 models?
Regards

Can you get gptweb working to connect messages?

I mean like

gptweb({
  message: [],
  promp: "Are you familiar with the movie Wonka released in 2023?",
  markdown: false
} ...)

test:

curl -X POST \
  https://nexra.aryahcr.cc/api/image/complements \
  -H 'Content-Type: application/json' \
  -d '{
    "prompt": "Friends gathered around a bonfire in an ancient forest. Laughter, stories, and a starry sky paint an unforgettable moment of connection beneath the shadows of the mountains.",
    "model": "prodia",
    "data": {
        "model": "absolutereality_V16.safetensors [37db0fc3]",
        "steps": 25,
        "cfg_scale": 7,
        "sampler": "DPM++ 2M Karras",
        "negative_prompt": ""
    }
}'

response text:
bug: _

_{"code":200,"status":true,"prompt":"画一只狗","model":"Prodia","data":{"model":"absolutereality_V16.safetensors [37db0fc3]","steps":25,"cfg_scale":7,"sampler":"DPM++ 2M Karras","negative_prompt":""},"images":["data:image/jpeg;base64,iVBORw0KGgoAAAANSUhEUgAAAgAAAAIACAIAAAB7GkOtAAABDWlUWHRwYXJhbWV0ZXJzAAAAAADnlLvkuIDlj6rni5cKU3RlcHM6IDI1LCBTYW1wbGVyOiBEU ...."]}

1. Are the gpt api and DALL-E called by the author's server free, or do they cost money?
2. What is the hardware configuration of the author's server?
3. If you use free api, please tell me the address, especially dall-e, I have been looking for free api interface

when i use bing model i get this {"code":500,"status":false,"error":"INTERNAL_SERVER_ERROR","message":"general (unknown) error"},
it's only on bing model, gpt and others are fine

Hello, all parameters are correct. I'm using module since 2-3 weeks. Suddenly stopped working. Giving code 400. Everything is correct. I didn't change any code.

Can you make it so we're able to cancel the request using AbortController

I tried the XL and V2 version but even with the default prompt they are not working!

(GPT 4 works for me tho)

Looks like AI image generator gives output as base64? Is there a way to set it to normal link like before?

Does this lib support response stream type?

The code for this project should be written in a more standardized way. It is difficult to maintain a bunch of codes all piled together.

The features of this project are valuable and great.