Secure RAG with OpenFGA Build secure RAG systems with document-level authorization using LangChain and OpenFGA. The FGARetriever implementation provides:
– Authorization layer
– Vector store integration
– RAG pipeline Learn how to implement it: https://
auth0.com/blog/building-
a-secure-rag-with-python-langchain-and-openfga/
…
OPEN SOURCE
-

Secure RAG Systems with LangChain and OpenFGA Authorization
By
–
-

Safe AI Agent Tutorial: Blockchain Operations with LangChain
By
–
Safe AI Agent Tutorial Create AI agents that handle Safe wallet operations and smart contracts using LangChain. This open-source guide shows how to combine blockchain interactions with intelligent agents. AI wallet agent https://
github.com/5afe/safe-ai-a
gent-tutorial
… -
TorchTune Library Growth Inspired by LitGPT
By
–
Oh yeah, torchtune is a good library. It was modeled after our LitGPT library and has grown quite a bit!
-
Drop-in replacement code for modified attention mechanism available
By
–
Yup, the reader posted the code for a drop-in replacement for the modified attention mechanism. Just copy and paste it into the Chapter 5 code, which is available in the GitHub repo linked above.
-

Merging Query and Key Weight Matrices in LLM Training
By
–
Can we merge the query and key weight matrices in an LLM into a single covariance matrix and still train effectively? Here are some promising early results from a reader: https://
github.com/rasbt/LLMs-fro
m-scratch/discussions/517
…
Anyone else familiar with projects that tried this? -
Llamapalooza roadshow comes to Seattle with Meta and AWS
By
–
🦙 🛣️ Llamapalooza is going on the road!
— Cerebras (@cerebras) 14 février 2025
On February 27th – we will be in Seattle for an unforgettable evening of exploring llama models in production, featuring headliners from @AIatMeta, @awscloud, and Cerebras.
Shoutout to our cohosts @ollama and @AITinkerers!
Tickets are… pic.twitter.com/39bR2xngQ3Llamapalooza is going on the road! On February 27th – we will be in Seattle for an unforgettable evening of exploring llama models in production, featuring headliners from
@AIatMeta
, @awscloud
, and Cerebras. Shoutout to our cohosts @ollama and @AITinkerers
!
Tickets are -
Platform hosts 3,500 terabytes of GGUF model files
By
–
we currently host 3,500 terabytes of .gguf files – just saying
-

Public AI Assistant Workshop: Democratizing Productivity and Information Access
By
–
AI has the potential to revolutionize productivity & equitable access to information worldwide. How can we make it a reality? Join tomorrow’s workshop exploring the potential of a public AI assistant with @StanfordOVAL
. Watch the livestream at 8:30 am PT: https://
bit.ly/42VoWA0 -
Closed Labs Restrict Top Models APIs, Open Source Becomes Critical
By
–
@SullyOmarr called it – closed labs will not release top models via apis for much longer Open source even more important to allow a developer ecosystem to flourish
-

Sakana AI joins public interest AI partnership at Paris summit
By
–
Sakana AIは、パリのAIアクションサミットで発表された、公益目的のAIを促進する新たなパートナーシップの支援メンバーとなりました。オープンソースをベースとした開発をこれからも進めてまいります。 #AIActionSummit https://
currentai.org/latest-updates
/launchpressrelease
…