Machine Learning and AI Apps | Tools
- www.microsoft.com AutoGen: Enabling next-generation large language model applications
Microsoft researchers are introducing AutoGen, a framework for simplifying the orchestration, optimization, and automation of workflows for large language model (LLM) applications—potentially transforming and extending what LLMs can do. Learn more.
- github.com GitHub - TeamMsgExtractor/msg-extractor: Extracts emails and attachments saved in Microsoft Outlook's .msg files
Extracts emails and attachments saved in Microsoft Outlook's .msg files - GitHub - TeamMsgExtractor/msg-extractor: Extracts emails and attachments saved in Microsoft Outlook's .msg files
- github.com GitHub - BerriAI/litellm: lightweight package to simplify LLM API calls - Azure, OpenAI, Cohere, Anthropic, Replicate. Manages input/output translation
lightweight package to simplify LLM API calls - Azure, OpenAI, Cohere, Anthropic, Replicate. Manages input/output translation - GitHub - BerriAI/litellm: lightweight package to simplify LLM API cal...
-
GitHub - facebookresearch/audiocraft: Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with
github.com GitHub - facebookresearch/audiocraft: Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable...
- github.com GitHub - danswer-ai/danswer: Ask Questions in natural language and get Answers backed by private sources. Connects to tools like Slack, GitHub, Confluence, etc.
Ask Questions in natural language and get Answers backed by private sources. Connects to tools like Slack, GitHub, Confluence, etc. - GitHub - danswer-ai/danswer: Ask Questions in natural language ...
- github.com GitHub - openchatai/OpenChat: LLMs custom-chatbots console ⚡
LLMs custom-chatbots console ⚡. Contribute to openchatai/OpenChat development by creating an account on GitHub.
-
Introducing ONNX Script: Authoring ONNX with the ease of Python - Microsoft Open Source Blog
Blog Post: https://cloudblogs.microsoft.com/opensource/2023/08/01/introducing-onnx-script-authoring-onnx-with-the-ease-of-python/
- github.com GitHub - geekan/MetaGPT: 🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo
🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo - GitHub - geekan/MetaGPT: 🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Task...
- www.markovml.com MarkovML | The easiest way for ML teams to collaborate
MarkovML is collaboration software for modern AI teams. We created an easy-to-use interface for saving and sharing your models, experiments, and datasets – and combined that with powerful analysis tools – so you can build with confidence.
-
- github.com GitHub - C-Nedelcu/talk-to-chatgpt: Talk to ChatGPT AI using your voice and listen to its answers through a voice
Talk to ChatGPT AI using your voice and listen to its answers through a voice - GitHub - C-Nedelcu/talk-to-chatgpt: Talk to ChatGPT AI using your voice and listen to its answers through a voice
- simonwillison.net My LLM CLI tool now supports self-hosted language models via plugins
LLM is my command-line utility and Python library for working with large language models such as GPT-4. I just released version 0.5 with a huge new feature: you can now …
-
Hands on with Microsoft Windows 11 Preview Build with Copilot
YouTube Video
Click to view this content.
-
BabyCommandAGI - Write software through feedback
- repo
- [tweet[(https://twitter.com/saten_work/status/1674856415977181184)
Reviews:
- https://www.producthunt.com/products/babycommandagi
- https://www.futurepedia.io/tool/babycommandagi
- https://aitoptools.com/tool/babycommandagi/
- https://whattheai.tech/tools/babycommandagi/
BabyCommandAGI, which is based on @yoheinakajima 's BabyAGI, can now automatically create apps just by providing feedback.
The following example is for creating a Reversi game Flutter app.
Set the following OBJECTIVE and INITIAL_TASK, then wait for about 30 minutes.
OBJECTIVE: "Please install the Flutter environment via git, implement a Flutter app to play Reversi with black and white stones, and make the Flutter app you created accessible from outside the container by running 'flutter run -d web-server --web-port 8080 --web-hostname 0.0.0.0'."
INITIAL_TASK: "Develop a task list"
The AI will install the Flutter environment on the Linux container and create a Flutter app.
Once 'flutter run -d web-server --web-port 8080 --web-hostname 0.0.0.0' is executed, access
'http://localhost:8080/'
from your browser. The first Flutter app I created was an empty app named Reversi.
There are still many problems, but BabyCommandAGI has successfully installed Flutter on Linux in Docker and has been successful in creating a Flutter project. (However, I have not yet succeeded in implementing the Othello app in Flutter)
Here are the main current steps of BabyCommandAGI.
- Try to download Flutter with curl -> There's no curl command
- Install the curl command with apt-get
- Download Flutter with the curl command
- Set the environment path and run flutter doctor -> Error: Unable to find git in your PATH.
- Install the git command with apt-get
- Delete the original flutter folder
- Clone flutter with git
- Run flutter doctor -> There's no unzip tool
- Install unzip with apt-get
- Successfully create a project with flutter create This is where I am now.
To give feedback to the AI, please enter "f". After a short wait, it will be in a state of waiting for feedback.
"The Reversi board with black and white stones is not displayed and I can't play. Please make it possible to play Reversi."
I gave this feedback. Then wait again until
'flutter run -d web-server --web-port 8080 --web-hostname 0.0.0.0'
is executed. Once it is executed, access 'http://localhost:8080/' again.
This time the board was displayed, but it seems that the stones cannot be placed. (If nothing changes, please give feedback again)
"I can't place stones. Reversi is a game where you place stones and the stones in between become the same color when sandwiched by the same color. Please make it possible to play Reversi."
I gave this feedback.
The stones were displayed, but this time the stones in between did not flip even when sandwiched by stones. (Although the white stones are hard to see, they are there.)
"The sandwiched stones do not become the same color as the sandwiching stones. Reversi is a game where the sandwiched stones become the same color as the sandwiching stones. Please make it possible to play Reversi."
I gave this feedback.
The sandwiched stones started to flip. However, the white stones are hard to see and the stones are small, so
"The white stones are hard to see, so please add a black border to make them easier to see. Also, the stones are small, so please make them a little bigger."
I gave this feedback.
The white stones now have a border and are easier to see, and the stones are a little bigger. However, the black stones have become a strange display.
"The black stones have become a strange square display. Please make the black stones display as black circles."
I gave this feedback.
The strange display of the black stones has also changed to black round stones, and Reversi is now playable. !
With BabyCommandAGI, you don't have to program, just give it feedback and it will automatically program a simple app for you.
Also, while BabyCommandAGI is good at building and engineering environments, it is not designed specifically for them, so there may be other use cases.
- github.com GitHub - 0xpayne/gpt-migrate: Easily migrate your codebase from one framework or language to another.
Easily migrate your codebase from one framework or language to another. - GitHub - 0xpayne/gpt-migrate: Easily migrate your codebase from one framework or language to another.
Migration is a costly, tedious, and non-trivial problem. Do not trust the current version blindly and please use responsibly. Please also be aware that costs can add up quickly as GPT-Migrate is designed to write (and potentially re-write) the entirety of a codebase.
However, with the collective brilliance of the OSS community and the current state of LLMs, it is also a very tractable problem.
-
mymap.ai - A practical map-based interface for organizing multiple GPT conversations.
cross-posted from: https://lemmy.intai.tech/post/4725
> Disclaimer: I have no stake in any of the projects I post about > > So I've been trying out this interface for a couple of days and I'm really enjoying it. It's super handy when I need to look back at something, try different approaches, and see how they stack up against each other. Incredibly useful. > > https://mymap.ai
- blog.unity.com Introducing Unity Muse and Unity Sentis, AI-powered creativity | Unity Blog
Every object, every system, and every pixel in games will eventually be touched by AI. Get to know Unity’s newest AI products for creators: Unity Muse, an expansive platform for AI-driven assistance during creation, and Unity Sentis, which enables developers to embed neural networks in the Unity Run...
-
Neural Network Interactive Browser App: Tensorflow Playground
playground.tensorflow.org Tensorflow — Neural Network PlaygroundTinker with a real neural network right here in your browser.
-
🥁Introducing YouTube-to-chatbot — train a chatbot on an ENTIRE YouTube channel 💬
https://twitter.com/ehalm_/status/1660914850107883520
- github.com GitHub - mshumer/gpt-author
Contribute to mshumer/gpt-author development by creating an account on GitHub.
- meowapps.com AI Engine: The AI Plugin for WordPress
The AI Plugin for WordPress: chatbots, AI Forms, AI Copilot, content generation, and more! Beautiful UI and extensible infrastructure.
-
GPT Engineer: Specify what you want it to build, the AI asks for clarification, and then builds it
https://github.com/AntonOsika/gpt-engineer
-
Cognosys.ai receives massive update: 4x faster browsing mode, specific URL accessibility and file upload capability
https://twitter.com/HomamMalk/status/1668691525700558893?s=20
-
ChatDocs: PrivateGPT + WebUI + GPU Support + More
github.com GitHub - marella/chatdocs: Chat with your documents offline using AI.Chat with your documents offline using AI. Contribute to marella/chatdocs development by creating an account on GitHub.
ChatDocs was created to chat with documents offline using LLMs:
It is based on PrivateGPT but has more features:
--Supports GGML models via C Transformers (another library made by me)
--Supports Transformers models
--Supports GPTQ models
--Web UI
--GPU support
--Highly configurable via chatdocs.yml
It is easy to install and use:
--pip install chatdocs # Install
--chatdocs download # Download models
--chatdocs add /path/to/documents # Add your documents
--chatdocs ui # Start the web UI to chat with your documents
All the configuration options can be changed using a chatdocs.yml config file.
- github.com GitHub - gpt4thewin/docker-nginx-openai-api-cache: A nginx and docker built reverse proxy server to cache the slow expensive requests to the openai api.
A nginx and docker built reverse proxy server to cache the slow expensive requests to the openai api. - GitHub - gpt4thewin/docker-nginx-openai-api-cache: A nginx and docker built reverse proxy ser...
-
AI-Powered Internet Marketing Agency | Metrotechs - GPT-4 Subscriptions available.
metrotechs.io AI-Powered Internet Marketing & Digital Asset PlatformEverything You Need To Launch and Scale Your Brand Online