👩‍💻 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

✈️ Whitehat Lab

🗝️ Weakpass

Недавно был пост об отличном сервисе Weakpass у которого в наличии абсолютно бесплатный API

Прикрутил к боту Password lookup (MD5, NTLM, SHA1 или SHA256)

import requests
from aiogram import Router, F
from aiogram.types import Message
import logging
import app.config.cfg as cfg
import json

router: Router = Router()


def check_hash_string(hash_string: str):
    try:
        headers = {'Content-Type': 'application/json'}
        url = requests.get(f'https://weakpass.com/api/v1/search/{hash_string}.json', headers=headers)
        output = json.loads(url.text)
        hash_info = json.dumps(output, indent=2)
        return hash_info
    except Exception as e:
        logging.warning(e)

@router.message(F.text.startswith(cfg.all_commands['check_hash']))
async def check_hash(message: Message):
    try:
        msg = message.text.split()
        if len(msg) == 2:
            await message.answer(f'<b>{check_hash_string(msg[1])}</b>', disable_web_page_preview=True)
        else:
            await message.answer(f'Пример:\n<code>!check_hash 5f4dcc3b5aa765d61d8327deb882cf99</code>')
    except Exception as e:
        logging.warning(e)

Работает в чате канала

!check_hash 5f4dcc3b5aa765d61d8327deb882cf99

➡️ Home
➡️ Wordlists
➡️ API
💻 Github

#weakpass #api #bot #python

✈️ Whitehat Lab

🔎 RULEZET v1.1.0

Платформа с открытым исходным кодом для обмена, оценки, улучшения и управления правилами обнаружения (YARA, Sigma, Suricata и др.) с поддержкой API

Форматы:

Yara
Sigma
Zeek
Suricata
Crs
Nova
Elastic

Пример:

title: Encoded or Base64 Payload in HTTP POST to F5 Management API
id: f5-base64-upload-2025
description: Detects long base64 strings in HTTP POST body to management or shared endpoints.
author: abdulmyid@gmail.com
status: experimental
logsource:
  product: webproxy
  service: http
detection:
  selection:
    http.method: POST
    url|contains:
      - '/mgmt'
      - '/shared'
    http.request.body|contains_regexp: '[A-Za-z0-9+/]{200,}={0,2}'
  condition: selection
level: medium
falsepositives:
  - Legitimate encoded payloads (token exchanges, APIs).

🔗 Web
💻 Repo

#ti #rules #detection #soc #api

✈️ Whitehat Lab 💬 Chat