✅ Low code & No logic required to be added
✅ Builtin memory for chatbot context

Our example, uses Meta #Llama small models provided by #groq

Find an image of the code snippet in the first comment 👇

#staytuned for complex workflows & #RAG implementation with #YosrAI low code ⏳

Wael Zohny on LinkedIn: #staytuned #rag #yosrai 🌟 YosrAI - Chatbot with 10+ lines of code ✨ Two Dedicated Agents: 🤖 Chatting Agent: retrieve model output 🤖 Summary Agent: summarizing the chat…

🌟 YosrAI - Chatbot with 10+ lines of code ✨

Two Dedicated Agents:
🤖 Chatting Agent: retrieve model output
🤖 Summary Agent: summarizing the chat history

Creating summary helps to reduce the size of the context used while chatting session is running.

www.linkedin.com/posts/waelzo...

Old meets new: Classic Casio alongside a sleek smartwatch Apple Watch.
Timeless style and modern tech side by side. ⌚️

𝗛𝗲𝗹𝗹𝗼 𝗪𝗼𝗿𝗹𝗱 𝗲𝘅𝗮𝗺𝗽𝗹𝗲 𝗯𝗲𝗹𝗼𝘄:

𝗧𝗲𝗮𝗰𝗵𝗲𝗿: @groqinc.bsky.social with llama3-8b-8192 model

𝗦𝘁𝘂𝗱𝗲𝗻𝘁: Ollama with IBM granite3.1-moe:3b model

#FutureOfWork #AgenticAI #AIInnovation #BusinessTransformation #ArtificialIntelligence #HappyNewYear

✨ 𝗙𝗲𝗮𝘁𝘂𝗿𝗲𝘀:

📝 From 𝗣𝗿𝗼𝗺𝗽𝘁 to 𝗔𝗴𝗲𝗻𝘁
🔄 Build Complex 𝗪𝗼𝗿𝗸𝗳𝗹𝗼𝘄𝘀
🛠️ Custom 𝗧𝗼𝗼𝗹𝘀 Support
📊 Structured 𝗝𝗦𝗢𝗡 Support
🌐 Compatible with most of 𝗟𝗟𝗠 𝗣𝗿𝗼𝘃𝗶𝗱𝗲𝗿𝘀: OpenAI, Anthropic, Groq, Fireworks AI, NVIDIA AI, Cohere, Mistral AI, xAI, Nebius and more!
🤖 𝗦𝘁𝗮𝗻𝗱𝗮𝗹𝗼𝗻𝗲 Agents & 𝗠𝘂𝗹𝘁𝗶-𝗔𝗴𝗲𝗻𝘁 Systems

Wael Zohny on LinkedIn: #futureofwork #agenticai #aiinnovation #businesstransformation… 🌟 𝗬𝗼𝘀𝗿𝗔𝗜 🌟 🚀 𝗦𝘁𝗮𝘆 𝗧𝘂𝗻𝗲𝗱! ⏳ 𝗖𝗼𝗻𝗰𝗲𝗽𝘁: 𝗙𝗿𝗼𝗺 𝗣𝗿𝗼𝗺𝗽𝘁𝘀 𝘁𝗼 𝗣𝗼𝘄𝗲𝗿: 𝗕𝘂𝗶𝗹𝗱, 𝗖𝗼𝗻𝗻𝗲𝗰𝘁, 𝗮𝗻𝗱 𝗜𝗻𝗻𝗼𝘃𝗮𝘁𝗲…

🌟 𝗬𝗼𝘀𝗿𝗔𝗜 🌟 🚀 𝗦𝘁𝗮𝘆 𝗧𝘂𝗻𝗲𝗱!

𝗖𝗼𝗻𝗰𝗲𝗽𝘁:
𝗙𝗿𝗼𝗺 𝗣𝗿𝗼𝗺𝗽𝘁𝘀 𝘁𝗼 𝗣𝗼𝘄𝗲𝗿: 𝗕𝘂𝗶𝗹𝗱, 𝗖𝗼𝗻𝗻𝗲𝗰𝘁, 𝗮𝗻𝗱 𝗜𝗻𝗻𝗼𝘃𝗮𝘁𝗲.

⏳ 𝗦𝗼𝗼𝗻: 𝗜𝗻𝗶𝘁𝗶𝗮𝗹 𝗿𝗲𝗹𝗲𝗮𝘀𝗲 𝘄𝗶𝘁𝗵 𝗮 𝗰𝗼𝗼𝗸𝗯𝗼𝗼𝗸 𝗳𝘂𝗹𝗹 𝗼𝗳 𝗿𝗲𝗮𝗹-𝘄𝗼𝗿𝗹𝗱 𝘂𝘀𝗲 𝗰𝗮𝘀𝗲 𝗲𝘅𝗮𝗺𝗽𝗹𝗲𝘀.

www.linkedin.com/posts/waelzo...

exaone3.5 EXAONE 3.5 is a collection of instruction-tuned bilingual (English and Korean) generative models ranging from 2.4B to 32B parameters, developed and released by LG AI Research.

2.4B model optimized for deployment on small or resource-constrained devices

7.8B model matching the size of its predecessor but offering improved performance

32B model delivering powerful performance.

#ollama #llms #slms

ollama.com/library/exao...

All models support long-context processing of up to 32K tokens. Each model demonstrates state-of-the-art performance in real-world use cases and long-context understanding, while remaining competitive in general domains compared to recently released models of similar sizes.

EXAONE 3.5 is a collection of instruction-tuned bilingual (English and Korean) generative models ranging from 2.4B to 32B parameters, developed and released by LG AI Research.

GitHub - athina-ai/rag-cookbooks: This repository contains various advanced techniques for Retrieval-Augmented Generation (RAG) systems. This repository contains various advanced techniques for Retrieval-Augmented Generation (RAG) systems. - athina-ai/rag-cookbooks

Notebooks github repo:

github.com/athina-ai/ra...

Comprehensive collection of advanced Retrieval-Augmented Generation (RAG) techniques

LangChain, LangGraph, Chromadb, FAISS, Qdrant, Pinecone, Athina AI

#RAG #AI

Top GenAI Opportunities for Tech Products Discover key considerations and actions for tech product managers to harness the opportunity of GenAI in their products and drive continued growth and innovation.

To protect and build market share, it is critical for product leaders to prioritize GenAI capabilities that will deliver enhanced value to customers.

Download the eBook:

www.gartner.com/en/industrie...

Generative AI use cases by industry.
By Gartner

By 2026, more than 80% of independent software vendors will have embedded GenAI capabilities in their enterprise applications, up from less than 5% today.

meta-llama/Llama-3.3-70B-Instruct · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science.

On Hugging Face:

huggingface.co/meta-llama/L...

On Meta:

www.llama.com/llama-downlo...

llama3.3 New state of the art 70B model. Llama 3.3 70B offers similar performance compared to Llama 3.1 405B model.

Model Offers Comparable Quality to 3.1 405B at Less Than 1/5th the Size 🔥

ollama.com/library/llam...

A New Scaling Paradigm: Meta's Llama 3.3 70B Challenges "Death of Scaling Law"  - Groq is Fast AI Inference Model Offers Comparable Quality to 3.1 405B at Less Than 1/5th the Size

✨ Today, Meta released Llama 3.3 70B and it’s a game-changer. By leveraging new post-training techniques, they’ve managed to improve performance across the board, reaching state-of-the-art in areas like reasoning, math, and general knowledge.

#meta #llama #AI

groq.com/a-new-scalin...

3-0

Fixed Mindset vs Growth Mindset

Gartner Top 10 Strategic Technology Trends for 2025 Dive into the trending technologies for 2025 that appear in this year’s edition of the Gartner Top 10 Strategic Technology Trends.

6. Polyfunctional Robots
7. Disinformation Security
8. Energy-Efficient Computing
9. Neurological Enhancement
10. Hybrid Computing

www.gartner.com/en/articles/...

Gartner Top 10 Strategic Technology Trends for 2025

1. Agentic AI
2. Post-quantum Cryptography
3. Spatial Computing
4. AI Governance Platforms
5. Ambient Invisible Intelligence

Full article below: 👇🏻

👋🏻😂

These updates from #ollama simplify workflows, enabling seamless function execution within model responses. With tools like JSON schema generation for functions, this release elevates developer productivity.

#follownow #share
@wzohny.bsky.social

What’s New:

👉🏻 Function tools:
Pass Python functions directly to models as tools.

👉🏻 Enhanced typing support:
Full type annotations for better development experience.

👉🏻 Improved examples:
Updated code samples for easier integration.

Ollama Python library 0.4 with function calling improvements · Ollama Blog Ollama Python library 0.4 with function calling improvements

✨ Ollama Python Library 0.4 🦙

Ollama has announced the release of its Python library 0.4, bringing enhanced functionality to developers.

More details on Ollama blog 👇🏻
ollama.com/blog/functio...

#AI #LLM #ollama
#halffaceinsights

AI Maturity Matrix by BCG, Discover where global economies stand in their readiness and exposure to #AI. From pioneers like #Canada and #Singapore to emerging economies, the chart highlights the diverse pace of AI adoption worldwide.

Where does your country rank?

#AIAdoption #Economy

Introduction - Model Context Protocol Get started with the Model Context Protocol (MCP)

Anthropic released an interesting thing today: an attempt at a standard protocol for LLM tools to talk to services that provide tools and extra context to be used other the models modelcontextprotocol.io

Hi everyone 🤗 this my #1st post, and I’m excited to connect with you.
I'm interested in developing Agentic AI systems to improve human-computer interaction in every business fields.
Feel free to follow me and say hi 👋🏻 and I will follow back.