Crawlee

A web scraping and browser automation library for Python to build reliable crawlers. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with BeautifulSoup, Playwright, and raw HTTP. Both headful and headless mode. With proxy rotation.

https://github.com/apify/crawlee-python

Streaming Chatbot with Burr, FastAPI, and React

Expose the OpenAI streaming API with server-sent-events.

https://blog.dagworks.io/p/streaming-chatbot-with-burr-fastapi

Entering text in the terminal is complicated

The article explores the complexities and inconsistencies of text input in terminal environments, discussing various modes from basic input to advanced systems like readline and custom solutions. It provides insights into how different programs handle text input, offers tips for users, and explains the origins and features of common keyboard shortcuts used in terminal text editing.

https://jvns.ca/blog/2024/07/08/readline/

FastEmbed

Fast, Accurate, Lightweight Python library to make State of the Art Embedding.

https://github.com/qdrant/fastembed

Run Multi-Node Django for Time Series Data with TimescaleDB, Celery and more.

Run many iterations of Django across Docker Compose or Raspberry Pis to handle large amounts of time series data.

https://www.youtube.com/watch?v=kykDfDtp7Wg

Kedreamix / Linly-Talker

Digital Avatar Conversational System - Linly-Talker. 😄✨ Linly-Talker is an intelligent AI system that combines large language models (LLMs) with visual models to create a novel human-AI interaction method. 🤝🤖 It integrates various technologies like Whisper, Linly, Microsoft Speech Services, and SadTalker talking head generation system. 🌟🔬

https://github.com/Kedreamix/Linly-Talker

0xtools

X-Ray vision for Linux systems.

https://github.com/tanelpoder/0xtools

Click: Build Your Own Command Line Interface Tool

This video provides a tutorial on creating a Command Line Interface (CLI) tool in Python using the Click package. The project involves building a simple note-taking tool with functionalities to write, read, update, and delete notes. Additionally, it explores some lesser-known features of Click that enhance tool functionality.

https://www.youtube.com/watch?v=FWacanslfFM

vectorlite

A fast and tunable vector search extension for SQLite.

https://github.com/1yefuwang1/vectorlite

A Python Epoch Timestamp Timezone Trap

This is an article about a Python epoch timestamp timezone trap. It discusses how epoch timestamps can be tricky to work with in Python, especially when dealing with timezones. The author provides a few tips for avoiding the trap.

https://nerderati.com/a-python-epoch-timestamp-timezone-trap/

AI Dialer

A full stack app for interruptible, low-latency and near-human quality AI phone calls built from stitching LLMs, speech understanding tools, text-to-speech models, and Twilio’s phone API.

https://github.com/akiani/aidialer

PyTorch Lightning: A Comprehensive Hands-On Tutorial

This comprehensive, hands-on tutorial teaches you how to simplify deep learning model development with PyTorch Lightning. Perfect for beginners and experienced developers alike, it covers environment setup, model training, and practical examples.

https://www.datacamp.com/tutorial/pytorch-lightning-tutorial

Korvus

Korvus is a search SDK that unifies the entire RAG pipeline in a single database query. Built on top of Postgres with bindings for Python, JavaScript, Rust and C.

https://github.com/postgresml/korvus

mem0ai / mem0

The memory layer for Personalized AI

https://github.com/mem0ai/mem0

A helper for LLM SDKs

LLMEasyTools generates tool schemas and executes function calls received from the LLM.

https://github.com/zby/LLMEasyTools