Mastering LLM & Generative AI ✅

⚡️ Pydoll is a Python library designed to automate Chromium-based browsers (Chrome and Microsoft Edge) without using WebDriver.

The tool simulates "real" user actions and provides flexibility when working with interface elements and network requests.

🔗 Key Features
- Asynchronous automation without WebDriver

- Allows you to do without installing and configuring WebDriver drivers, which simplifies the integration and maintenance process.

- Implemented on the basis of asyncio, so it supports running multiple tasks simultaneously.

- Bypass Cloudflare Turnstile

- There is a built-in mechanism for automatically passing CAPTCHA:

- Synchronous locking (context manager), when code execution is suspended until the task is solved.

- Background mode (non-blocking), when automation continues to work while the CAPTCHA is being solved in the background.

- Supports "human-like" typing (imitation of pauses, speed).

- Recognizes special keys and key combinations (pressing SHIFT, CTRL, ALT, etc.).

- Connecting to existing sessions

- You can connect to already running instances of Chrome or Edge, which is useful for debugging or integrating with existing user sessions.

With no need for WebDriver and the ability to simulate "real user" interactions, Pydoll is useful for projects that require flexible and realistic automation.

📌 Github

When you spent 3 hours debugging generated code that you could have written in an hour.
#meme

📌 FastRAG is a framework that provides developers with modern tools for creating optimized RAG pipelines. Built on Haystack and Hugging Face, this service focuses on effectively combining information retrieval with the generative capabilities of LLM.

The framework provides ready-made components for working with modern semantic search methods, optimized for modern hardware accelerators, including Intel Xeon processors and Gaudi AI accelerators.
At the same time, FastRAG is actively developing - from multimodality support to examples of dynamic synthesis of prompts.

🤖 GitHub