mirror of
https://github.com/HumanAIGC-Engineering/gradio-webrtc.git
synced 2026-02-05 01:49:23 +08:00
853d6a06b5
* Add code * add code * add code * Rename messages * rename * add code * Add demo * docs + demos + bug fixes * add code * styles * user guide * Styles * Add code * misc docs updates * print nit * whisper + pr * url for images * whsiper update * Fix bugs * remove demo files * version number * Fix pypi readme * Fix * demos * Add llama code editor * Update llama code editor and object detection cookbook * Add more cookbook demos * add code * Fix links for PR deploys * add code * Fix the install * add tts * TTS docs * Typo * Pending bubbles for reply on pause * Stream redesign (#63) * better error handling * Websocket error handling * add code --------- Co-authored-by: Freddy Boulton <freddyboulton@hf-freddy.local> * remove docs from dist * Some docs typos * more typos * upload changes + docs * docs * better phone * update docs * add code * Make demos better * fix docs + websocket start_up * remove mention of FastAPI app * fastphone tweaks * add code * ReplyOnStopWord fixes * Fix cookbook * Fix pypi readme * add code * bump versions * sambanova cookbook * Fix tags * Llm voice chat * kyutai tag * Add error message to all index.html * STT module uses Moonshine * Not required from typing extensions * fix llm voice chat * Add vpn warning * demo fixes * demos * Add more ui args and gemini audio-video * update cookbook * version 9 --------- Co-authored-by: Freddy Boulton <freddyboulton@hf-freddy.local>
74 lines
2.3 KiB
Python
74 lines
2.3 KiB
Python
import base64
|
|
import os
|
|
import re
|
|
from pathlib import Path
|
|
|
|
import numpy as np
|
|
import openai
|
|
from dotenv import load_dotenv
|
|
from fastrtc import (
|
|
AdditionalOutputs,
|
|
ReplyOnPause,
|
|
audio_to_bytes,
|
|
)
|
|
from groq import Groq
|
|
|
|
load_dotenv()
|
|
|
|
groq_client = Groq(api_key=os.environ.get("GROQ_API_KEY"))
|
|
|
|
client = openai.OpenAI(
|
|
api_key=os.environ.get("SAMBANOVA_API_KEY"),
|
|
base_url="https://api.sambanova.ai/v1",
|
|
)
|
|
|
|
path = Path(__file__).parent / "assets"
|
|
|
|
spinner_html = open(path / "spinner.html").read()
|
|
|
|
|
|
system_prompt = "You are an AI coding assistant. Your task is to write single-file HTML applications based on a user's request. Only return the necessary code. Include all necessary imports and styles. You may also be asked to edit your original response."
|
|
user_prompt = "Please write a single-file HTML application to fulfill the following request.\nThe message:{user_message}\nCurrent code you have written:{code}"
|
|
|
|
|
|
def extract_html_content(text):
|
|
"""
|
|
Extract content including HTML tags.
|
|
"""
|
|
match = re.search(r"<!DOCTYPE html>.*?</html>", text, re.DOTALL)
|
|
return match.group(0) if match else None
|
|
|
|
|
|
def display_in_sandbox(code):
|
|
encoded_html = base64.b64encode(code.encode("utf-8")).decode("utf-8")
|
|
data_uri = f"data:text/html;charset=utf-8;base64,{encoded_html}"
|
|
return f'<iframe src="{data_uri}" width="100%" height="600px"></iframe>'
|
|
|
|
|
|
def generate(user_message: tuple[int, np.ndarray], history: list[dict], code: str):
|
|
yield AdditionalOutputs(history, spinner_html)
|
|
|
|
text = groq_client.audio.transcriptions.create(
|
|
file=("audio-file.mp3", audio_to_bytes(user_message)),
|
|
model="whisper-large-v3-turbo",
|
|
response_format="verbose_json",
|
|
).text
|
|
|
|
user_msg_formatted = user_prompt.format(user_message=text, code=code)
|
|
history.append({"role": "user", "content": user_msg_formatted})
|
|
|
|
response = client.chat.completions.create(
|
|
model="Meta-Llama-3.1-70B-Instruct",
|
|
messages=history, # type: ignore
|
|
temperature=0.1,
|
|
top_p=0.1,
|
|
)
|
|
|
|
output = response.choices[0].message.content
|
|
html_code = extract_html_content(output)
|
|
history.append({"role": "assistant", "content": output})
|
|
yield AdditionalOutputs(history, html_code)
|
|
|
|
|
|
CodeHandler = ReplyOnPause(generate) # type: ignore
|