The biggest Python topics of 2023 ›

Large Language Models for Natural Language Processing

The topic revolves around natural language processing and large language models, particularly focusing on the advancements and applications of openAI's language models like GPT series. The documents in this subset cover a range of related topics such as generative model programming, utilizing language models for generating README files and text enrichment, integrating language models as Python functions, and exploring query languages for efficient programming with large language models.


whisper: Robust Speech Recognition via Large-Scale Weak Supervision Project

Robust Speech Recognition via Large-Scale Weak Supervision

https://github.com/openai/whisper

bark: Text-Prompted Generative Audio Model Project Started in 2023

🔊 Text-Prompted Generative Audio Model

https://github.com/suno-ai/bark

llama_index: Connect Your LLM’s With External Data Project

LlamaIndex (formerly GPT Index) is a data framework for your LLM applications

https://github.com/run-llama/llama_index

evals: Evaluate and Benchmark OpenAI Models Project Started in 2023

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

https://github.com/openai/evals

RWKV-LM: RNN With Transformer-Level LLM Performance Project

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

https://github.com/BlinkDL/RWKV-LM

CodeGeeX: OSS Multilingual Code Generation Model Project

CodeGeeX: An Open Multilingual Code Generation Model (KDD 2023)

https://github.com/THUDM/CodeGeeX

PentestGPT: GPT-empowered Penetration Testing Tool Project Started in 2023

A GPT-empowered penetration testing tool

https://github.com/GreyDGL/PentestGPT

video-retalking: Lip Synch-ing for Talking Head Video Editing Project

[SIGGRAPH Asia 2022] VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild

https://github.com/OpenTalker/video-retalking

ChatGPT: Your Personal Python Coding Mentor Article

Large language models have gained popularity since OpenAI released ChatGPT. In this tutorial, you’ll learn how to use ChatGPT as your Python coding mentor. You’ll study a variety of use cases, learn how to interpret results, and learn to beware of incorrect and irrelevant responses.

https://realpython.com/chatgpt-coding-mentor-python/

outlines: Generative Model Programming Project Started in 2023

Structured Text Generation

https://github.com/outlines-dev/outlines

Document Your Python Code and Projects With ChatGPT Article

Good documentation is a critical feature of any successful Python project. In practice, writing documentation is hard and can take a lot of time and effort. Nowadays, with tools like ChatGPT, you can quickly document your Python code and projects.

https://realpython.com/document-python-code-with-chatgpt/

Adversarial Attacks on Aligned LLMs Article

Deep CS paper on how to abuse Large Language Models and work around restrictions where the model is refusing to answer.

https://arxiv.org/abs/2307.15043

riffusion: Stable Diffusion for Real-Time Music Generation Project

Stable diffusion for real-time music generation

https://github.com/riffusion/riffusion

simpleaichat: Interface With AI Chat Apps Project Started in 2023

Python package for easily interfacing with chat apps, with robust features and minimal code complexity.

https://github.com/minimaxir/simpleaichat

The Problem With LangChain Article

LangChain is a Python and JavaScript library for interfacing with OpenAI’s GPT and other models for text generation. But, it “is complicated, so it must be better. Right?”

https://minimaxir.com/2023/07/langchain-problem/

lmql: A Query Language for Language Models Project

A language for constraint-guided and efficient LLM programming.

https://github.com/eth-sri/lmql

“Self-Healing” Programs That Fix Themselves Thanks to AI Article

Wolverine is a Python tool that responds to script crashes by using ChatGPT to look for solutions. This brief article describes the process and links to a video demo. With the corresponding Slashdot Discussion.

https://arstechnica.com/information-technology/2023/04/developer-creates-self-healing-programs-that-fix-themselves-thanks-to-gpt-4/

guardrails: Large Language Model Validator Project Started in 2023

Adding guardrails to large language models.

https://github.com/guardrails-ai/guardrails

What’s Your Favorite GPT Powered Tool? Article

https://news.ycombinator.com/item?id=35946260

Llama From Scratch Article

This blog post provides step by step instructions on how to implement llama from scratch, using a dramatically scaled-down version for training.

https://blog.briankitano.com/llama-from-scratch/

FunASR: Speech Recognition Toolkit Project

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models.

https://github.com/alibaba-damo-academy/FunASR

Considering ChatGPT’s Review of a Programming Book Article

What can you learn from feeding an entire book on Python programming into ChatGPT-4 and asking it to provide a technical review? What are the potential pitfalls of using an LLM as a learning tool? This week on the show, author Al Sweigart talks about his recent experiments using ChatGPT and Python.

https://realpython.com/podcasts/rpp/174/

Hallucination Detection for Abstractive Summaries Article

Abstractive summary is an AI task that rephrases and condenses text content into a summary. This article is a deep dive into how to ensure correctness and the math involved in ensuring fluency, coherence, relevance, and consistency.

https://eugeneyan.com/writing/abstractive/

leaptable: Manage LLM-powered Agents on Tabular Data Article

https://github.com/peterwnjenga/leaptable

Data-Driven News Discourse Analysis With Python Article

This tutorial shows you how to do discourse analysis on news using Python through The Guardian’s API. You’ll see how to access content across years and perform topic analysis with sentence embedding.

https://medium.com/data-analytics-at-nesta/tutorial-data-driven-news-discourse-analysis-with-python-part-1-4fdbf5c23991

Generating Code Without Generating Technical Debt? Article

GPT and other large language models can produce huge volumes of code quickly. This allows for faster prototyping and iterative development, trying out multiple solutions. But it can also leave us with a bigger amount of mess / code to maintain.

https://sourcery.ai/blog/chatgpt-maintainable-code/

Prompt Engineering: A Practical Example Article

Learn prompt engineering techniques with a practical, real-world project to get better results from large language models. This tutorial covers zero-shot and few-shot prompting, delimiters, numbered steps, role prompts, chain-of-thought prompting, and more. Improve your LLM-assisted projects today.

https://realpython.com/practical-prompt-engineering/

BabyAGI User Guide With LangChain Article

This notebook demonstrates how to implement BabyAGI by Yohei Nakajima. BabyAGI is an AI agent that can generate and pretend to execute tasks based on a given objective.

https://python.langchain.com/docs/use_cases/agents/baby_agi

llm: Access Large Language Models From the Command-Line Project Started in 2023

Access large language models from the command-line

https://github.com/simonw/llm

Creating a Mastodon Bot With Python Article

“With a Mastodon bot, you can automate tasks such as posting updates, replying to mentions, or even creating interactive chatbots.” This tutorial teaches you how to build such a bot.

https://blog.tiagorangel.com/creating-a-mastodon-bot-with-python

Building a ChatGPT-enhanced Python REPL Article

This blog shows how Logan built a Python REPL augmented with ChatGPT. It details the application itself as well as speculating on software engineering patterns that might emerge in systems built on Large Language Models (LLMs).

https://isthisit.nz/posts/2023/building-a-chat-gpt-enhanced-python-repl/

Automate Processes and Distribute Tools With RPA and RCC Article

Are you exploring automation of your repetitive business tasks with Python? How are you going to share your helpful tools with co-workers? This week on the show, Sampo Ahokas from Robocorp is here to discuss robotic process automation (RPA) and distribution of these robots.

https://realpython.com/podcasts/rpp/152/

Top 6 Text Annotation Tools Article

Text annotation is the process of reading natural language data and adding additional information to it in a way your program can use it. This info can be used to train models or help process the data. This article describes 6 different tools that can help you annotate your text data.

https://www.newscatcherapi.com/blog/top-6-text-annotation-tools

Supercharging My Telegram Group With ChatGPT Article

Using Python and ChatGPT, Duarte enriched his Telegram group with a summarizing command and a user impersonation feature. It was made using the gpt-3.5-turbo API.

https://duarteocarmo.com/blog/supercharging-telegram-bot-chatgpt-python

Your First Recurrent Neural Network (RNN) Article

In this introductory tutorial, you will build a recurrent neural network (RNN) with PyTorch. The RNN will be trained to read names and it will output the natural language they belong to. This is a modern spin on a tutorial from the PyTorch documentation.

https://mathspp.com/blog/your-first-recurrent-neural-network

Building a ChatGPT-based Assistant With Python Article

This article demonstrates a workflow for integrating multiple AI services to perform speech-to-text (STT), natural language processing (NLP), and text-to-speech (TTS) using OpenAI’s ChatGPT and Whisper API’s in Python.

https://www.faizanbashir.me/building-a-chatgpt-based-ai-assistant-with-python-speech-to-text-and-text-to-speech-using-openai-apis

Using Computer Vision to Play a DS Game Article

This posting is about how to use an object detection model to control a DS emulator to become an expert in playing the Super Mario 64 DS minigame “Wanted!”

https://medium.com/@nathancooperjones/using-computer-vision-to-destroy-my-childhood-high-score-in-a-ds-game-38ebd53a1d64

autolabel: Label, Clean and Enrich Text Datasets With LLMs Project Started in 2023

Label, clean and enrich text datasets with LLMs.

https://github.com/refuel-ai/autolabel

griptape: Python Framework for AI Workflows and Pipelines Project Started in 2023

Modular Python framework for AI agents and workflows with chain-of-thought reasoning, tools, and memory. Griptape is an enterprise grade alternative to LangChain.

https://github.com/griptape-ai/griptape

magentic: Seamlessly Integrate LLMs as Python Functions Project Started in 2023

Seamlessly integrate LLMs as Python functions

https://github.com/jackmpcollins/magentic

basaran: OSS Alternative to OpenAI Text Completion API Project Started in 2023

Basaran is an open-source alternative to the OpenAI text completion API. It provides a compatible streaming API for your Hugging Face Transformers-based text generation models.

https://github.com/hyperonym/basaran

compress: Text Compression to Generate Keystroke Expansion Project

Text compression for generating keyboard expansions

https://github.com/eschluntz/compress

cbp-translate: Generate Cyberpunk-Like Subtitles Project

https://github.com/elanmart/cbp-translate

README-AI: Automated Tool for Generating README Files Project Started in 2023

🎈 Automated README file generator, powered by GPT language model APIs

https://github.com/eli64s/README-AI

pyllms: Wrapper for Connecting to Multiple LLMs Project Started in 2023

Minimal Python library to connect to LLMs (OpenAI, Anthropic, AI21, Cohere, Aleph Alpha, HuggingfaceHub, Google PaLM2, with a built-in model performance benchmark.

https://github.com/kagisearch/pyllms/tree/main

litechain: Build Robust, Composable LLM Applications Project Started in 2023

Build robust LLM applications with true composability 🔗

https://github.com/rogeriochaves/langstream

VardaGPT: A Tale About Coding With ChatGPT Project Started in 2023

Ixaxxar walks you through the step by step process he used to build and test a piece of code using ChatGPT as his guide. TL;DR: it isn’t quite ready to replace him yet.

https://github.com/ixaxaar/VardaGPT/blob/master/STORY.md

subtitle: Subtitle Generation for Seamless Content Translation Project Started in 2023

Open-source subtitle generation for seamless content translation.

https://github.com/innovatorved/subtitle

PyWa: Building Bots Using the WhatsApp Cloud API Project Started in 2023

💬 Python wrapper for the WhatsApp Cloud API

https://github.com/david-lev/pywa

Interact With ChatGPT Through a Single-File Python Script Project Started in 2023

A single-file Python script that interacts with ChatGPT API in the command-line.

https://github.com/reorx/ai.py

training-code: Fine-Tuning Causal Language Models Project Started in 2023

The code we currently use to fine-tune models.

https://github.com/PygmalionAI/training-code

cria: Tiny Inference-Only Implementation of LLaMA Project Started in 2023

Tiny inference-only implementation of LLaMA

https://github.com/recmo/cria

Biaslyze: The NLP Bias Identification Toolkit Project Started in 2023

The NLP Bias Identification Toolkit

https://github.com/biaslyze-dev/biaslyze

GPTerm: Turn Plain Text Into Shell Commands Project Started in 2023

Creating Intelligent Terminal Apps with ChatGPT and LLM Models

https://github.com/ademakdogan/GPTerm