🚀 AG2 v0.5.0 is here! Two super cool features: 1. ReasoningAgent: Your o1 alternative - Tree of Thoughts with beam search - Systematic multi-path reasoning - Smart solution evaluation 2. Structured Output & GraphRAG - Pydantic schemas for perfect JSON responses @OpenAI -

Thank you @rUv , very happy to see gets applied. @llama_index

How to compare different local models quickly with @ollama and lionagi ? -----works with lionagi==0.0.207

How to compare different local models quickly with @ollama and lionagi ? -----works with lionagi==0.0.207

Can a LLM solve a multi-step problem with only the most basic tools? Try do the problem by hand first. Full notebook: https://t.co/a9OhRK6ndh #lionagi #AI #AGI #LLM #OpenAI #GenAI

More Lions is All you need speed up llama2 by 1700% https://t.co/I5MruSs6NU

Legit a 2.2 million line PR: https://t.co/wA5FarXEsx We did this so we never have to do this ever again

Define a Research Workflow for a RAG-powered agent 📖🤖 This is a cool notebook by @quantoceanli showing how you can build an agentic workflow to do scientific research from ArXiv, Wikipedia, textbooks, and more. Have it first fetch relevant abstracts from ArXiv, propose an

More Lions is All you need speed up llama2 by 1700% https://t.co/I5MruSs6NU

Can a LLM solve a multi-step problem with only the most basic tools? Try do the problem by hand first. Full notebook: https://t.co/a9OhRK6ndh #lionagi #AI #AGI #LLM #OpenAI #GenAI

RAG Assisted Auto Developer 🔎🧑‍💻 Here’s a neat cookbook by @quantoceanli to build a devbot that can 1) understand a codebase, 2) write additional code based on the codebase. It’s a nice mix of different tools: @llama_index to index an existing codebase, Autogen / OpenAI Code

Here's how you can easily build an ArXiv research assistant 🧑‍🔬🤖 with @llama_index + LionAGI by @quantoceanli 👇 1) Define a @llama_index RAG pipeline as an agent tool 2) Plug tool into LionAGI, letting you compose custom agentic pipelines Check it out: https://t.co/GaSf1ie59N

Community Showcase 🌟: LionAGI, a simple but powerful agent framework by @quantoceanli designed for interacting with data 🛠️ ✅ Easily compose your own workflow - can be sequential or a loop. Can include chain-of-thought and use of external tools. ✅ Efficient data operations

I just published Make Knowledge Graph RAG with LlamaIndex from own obsidian notes

REBEL is an awesome model for knowledge graph construction 🔗 🦙 But: it can be quite noisy + hallucinate non-entities. @quantoceanli proposes a super simple trick 💡: filter entities with Wikipedia! Leads to much better KG results. Nb in @llama_index : https://t.co/rDj83N1KJp

I just published Make Knowledge Graph RAG with LlamaIndex from own obsidian notes