& : Loading the knowledge base A knowledge base is a collection of relevant and up-to-date information that serves as a foundation for RAG. In our case it's the docs stored in a directory. Here's how you can load it as document objects in LlamaIndex:
OPEN SOURCE
-
Building a Local RAG System with LlamaIndex and Ollama
By
–
Before we begin, take a look at what we're about to create!
— Akshay 🚀 (@akshay_pachaar) 7 décembre 2024
Here's what you'll learn:
– @Llama_Index for orchestration
– @qdrant_engine to self-host a vector DB
– @Ollama for locally serving Llama-3.3
– @LightningAI for development & hosting
Let's go! 🚀 pic.twitter.com/qIKJjv0mxJBefore we begin, take a look at what we're about to create! Here's what you'll learn: – @Llama_Index for orchestration
– @qdrant_engine to self-host a vector DB
– @Ollama for locally serving Llama-3.3
– @LightningAI for development & hosting Let's go! -
Building a Local RAG Application with MetaAI’s Llama-3.3
By
–
Let's build a RAG app using MetaAI's Llama-3.3 (100% local):
-
Major VLM Revolution: Open-Source Models from Google, OpenGVLabs, Qwen, Microsoft
By
–
VLMs are going through quite an open revolution AND on-device friendly sizes: > Google DeepMind w/ PaliGemma2 – 3B, 10B & 28B > OpenGVLabs w/ InternVL 2.5 – 1B, 2B, 4B, 8B, 26B, 38B & 78B > Qwen w/ Qwen 2 VL – 2B, 7B & 72B > Microsoft w/ FlorenceVL – 3B & 8B (Links below)
-
AgentLab: Open Source Framework for Web Agents
By
–
[#Article] AgentLab, an open source framework for the development and evaluation of Web agents https://actuia.com/actualite/agentlab-un-framework-open-source-pour-le-developpement-et-levaluation-des-agents-web/
…
#AI #artificialintelligence -
Groq Benchmark: Llama 3.3 70B Inference Speed Performance
By
–
More Friday goodies: @ArtificialAnlys benchmark of Llama 3.3 70B running on Groq Read more here: https://
groq.com/new-ai-inferen
ce-speed-benchmark-for-llama-3-3-70b-powered-by-groq/
… -
70B Model Beats GPT-4o and Mistral Large 405B
By
–
This absolutely NUTS, a 70B beating GPT4o, Mistral Large 123B AND 405B! Truly got ChatGPT at home!
-
Qwen 2 Vision Language Models Now Available on Hugging Face
By
–
Based.. literally, all the Qwen 2 series VLM (Vision Language Models) base models are out on Hugging Face! Try them out here: https://
huggingface.co/Qwen -
Keras Hub: Latest Pretrained Models from Keras Team
By
–
Main topic: Keras Hub and the latest pretrained models shipped by the Keras team.
-
Keras Community Meeting Call Starting Now Open to All
By
–
The Keras community meeting call is starting now! Anyone is free to join the call (link in next tweet)