gradio/demo/autocomplete/run.py
Abubakar Abid 6e6121a1ac
Sets up the Python gradio client (#3300)
* placeholder

* changelog

* added to readme

* client

* implement futures

* utils

* scripts

* lint

* reorg

* scripts

* serialization

* cleanup

* fns

* serialize

* cache

* callbacks

* updates

* formatting

* packaging

* requirements

* remove changelog

* client

* access token

* formatting

* deprecate

* format backend

* client replace

* updates

* moving from utils

* remove code duplication

* rm duplicates

* simplify

* galleryserializer

* serializable

* load serializers

* fixing errors

* errors

* typing

* tests

* changelog

* lint

* fix lint

* fixing files

* formatting

* type

* fix type checking

* changelog

* changelog

* Update client/python/gradio_client/client.py

Co-authored-by: Lucain <lucainp@gmail.com>

* formatting, tests

* formatting, tests

* gr.load

* refactoring

* refactoring'

* formatting

* formatting

* tests

* tests

* fix tests

* cleanup

* added tests

* adding scripts

* formatting

* address review comments

* readme

* serialize info

* remove from changelog

* version 0.0.2 released

* lint

* type fix

* check

* type issues

* hf_token

* update hf token

* telemetry

* docs, circle dependency

* hf token

* formatting

* updates

* sort

* script

* external

* docs

* formatting

* fixes

* scripts

* requirements

* fix tests

* context

* changes

* formatting

* fixes

* format fix

---------

Co-authored-by: Lucain <lucainp@gmail.com>
2023-03-23 15:33:44 -07:00

21 lines
806 B
Python

import gradio as gr
import os
# save your HF API token from https:/hf.co/settings/tokens as an env variable to avoid rate limiting
auth_token = os.getenv("auth_token")
# load a model from https://hf.co/models as an interface, then use it as an api
# you can remove the api_key parameter if you don't care about rate limiting.
api = gr.load("huggingface/EleutherAI/gpt-j-6B", api_key=auth_token)
def complete_with_gpt(text):
return text[:-50] + api(text[-50:])
with gr.Blocks() as demo:
textbox = gr.Textbox(placeholder="Type here...", lines=4)
btn = gr.Button("Autocomplete")
# define what will run when the button is clicked, here the textbox is used as both an input and an output
btn.click(fn=complete_with_gpt, inputs=textbox, outputs=textbox, queue=False)
demo.launch()