Dr. Marc Jäger

Agwntic AI | Generative AI | Data Science | Physics | Chemistry | Innovator | Investor | Python | E Guitar | Fitness | Self-Improvement | Biohacking | Curious |

[LangChain @LangChain]

🏆 Winning RAG Solution

A powerful RAG implementation that analyzes company annual reports through LangChain's framework. Features PDF parsing, multi-LLM support, and advanced retrieval for precise question-answering.

Check out the solution:
https://t.co/Kpt3viorzb

[LangChain @LangChain]

🤖 🎥 LangGraph Reflection Tutorial

Discover how to build AI agents that self-evaluate and improve using LangGraph's reflection architecture. See automated quality control in action with our LLM-as-Judge system.

Check out the tutorial 👉 https://t.co/97sbsMzaZp

[Sumanth @Sumanth_077]

Microsoft launched the best course on AI Agents!

AI Agents for Beginners

The Free 10 lesson course is available on Github and will teach you the basics of building AI Agents

[Daniel San @dani_avila7]

Claude 3.7 Sonnet is insane... just one prompt, and you get these animated cards in HTML, JS, and CSS.

You can try it for free in VSCode using the CodeGPT extension.

Sharing the prompt in this thread 👇

[Akshay 🚀 @akshay_pachaar]

Microsoft has released its own document parser for LLM use!
.
.
Introducing MarkItDown, a 100% open-source, one-stop solution for effortlessly converting any file to Markdown—perfect for text analysis, indexing, and more!

Here’s what makes it special:

↳ Converts PDF, Word, Excel, PPT, images, audio to markdown
↳ Extracts EXIF, OCR, and transcripts automatically
↳ Available via CLI, Python API, or Docker
↳ Offers LLM-based image descriptions
↳ Supports batch conversions

Link to the repo in next tweet!
_____
Find me → @akshay_pachaar ✔️
For more insights & tutorials on AI and Machine Learning.

[LangChain @LangChain]

📹ReelsMaker

ReelsMaker is a Python-based/streamlit application designed to create captivating faceless videos for social media platforms like TikTok and YouTube

💬AI-Powered Prompt Generation
✒️Subtitles Generation
🗨️Text-to-Speech

https://t.co/PALdtmF9at

[LangChain @LangChain]

🚀 Pre-release of LangChain v0.2

The pre-release of LangChain v0.2 is out today, paving the way towards greater stability + security.

Read the full blog here: https://t.co/EqZLtMC6lo

With the help of our users and developers, we've iterated on our stable library version and have decoupled langchain from langchain-community to make langchain more lightweight, focused, and secure.

With v0.2, you can look forward to:
• Versioned docs with improved discoverability, so you can match information and instructions with your minor version
• LangGraph as the recommended way to build agents, which makes it easy to define cycles and built-in memory — and then customize and modify them

Since our last v0.1 release, we've also made improvements to:
• Standard chat model features, including standardized tool calling support and an interface for structuring output
• Async support for many core abstractions
• Streaming support with a new Event Streaming API
• Partner packages for 20+ providers across Python and JavaScript packages

Thank you to our community for helping us build better and more reliably! 🤗

👂Give your feedback: https://t.co/1yHRqMXULd

[Google AI @GoogleAI]

Introducing a new approach for adaptive prompting of #LLMs that train with unlabeled samples + pseudo-demonstrations generated by the model itself to close the gap between few-shot and 0-shot performance on reasoning, NLU and language generation tasks. → https://t.co/ZtSEZOxNCc

[OpenAI @OpenAI]

ChatGPT and Whisper are now available through our API (plus developer policy updates). We ❤️ developers: https://t.co/vpoyxZ7XnD

[Jonathan Neuscheler @JonNeuscheler]

McDonald’s möchte 2023 alle 6 Stunden ein weiteres Restaurant eröffnen 🍔

Insgesamt 1.500 zusätzliche Filialen sollen hinzukommen. Alle neuen Standorte werden Lizenzgebühren an die Muttergesellschaft abführen.

So steigt der Gewinn immer weiter. Buy & Hold, Fries are gold 🍟

[Hugging Face @huggingface]

Reinforcement Learning with Transformers! 🤯🔥🔥

[Hugging Face @huggingface]

Document parsing meets 🤗 Transformers!

📄#LayoutLMv2 and #LayoutXLM by @MSFTResearch are now available! 🔥

They're capable of parsing document images (like PDFs) by incorporating text, layout, and visual information, as in the @gradio demo below ⬇️

https://t.co/Hr0kFIPHXW

[Dr. Daniel Stelter @thinkBTO]

Wer wissen will, was der #Schaufensterkandidat #Scholz @OlafScholz wirklich bringt, sollte nicht das #Sommerinterview sehen, sondern diesen 👇#Podcast hören https://t.co/1zcJfVNre6

[Google AI @GoogleAI]

Understanding how to best use unlabeled examples in real-world applications of #ML is often challenging. Today we present a semi-supervised learning approach that can be applied at scale to achieve performance gains beyond that of fully-supervised models. https://t.co/DoRumTHBCs

[Sylvain Gugger @GuggerSylvain]

We made it easier to train a new tokenizer on a given corpus with 🤗Transformers and 🤗Tokenizers — check out this new example done with @LucileSaulnier!

https://t.co/cKhFRWO2bf

[Omar Sanseviero @osanseviero]

(sorry, I know this meme is old)

Marvel: Avengers Endgame is the biggest crossover ever of all time

@huggingface: I got this.

[Hugging Face @huggingface]

The first part of the Hugging Face Course is finally out!

Come learn how the 🤗 Ecosystem works 🥳: Transformers, Tokenizers, Datasets, Accelerate, the Model Hub!

Share with your friends who want to learn NLP, it's free!

Come join us at https://t.co/6YNx6vY3VT

[Amazing Physics @amazing_physics]

Amazing Physics

[Filipp Piatov @fpiatov]

Hat Annalena Baerbock direkt nach ihrer Rede etwa "Scheiße" zu Robert Habeck gesagt?

[Amazing Physics @amazing_physics]

Chemistry Rainbow