I actually like writing sql! It's fun. Like a puzzle like Tetris. That will every now and then give you nothing but Z blocks because you screwed up your partitions.
CODE
-
Keras 3 with JAX Significantly Faster Than PyTorch
By
–
It is not uncommon for Keras 3 + JAX to be 3-5x faster than PyTorch models pulled from research repos on GitHub or from Hugging Face. Though the typical figure is more like 30% faster.
-
KerasCV Segment Anything: Zero-shot Image Segmentation with Prompt Points
By
–
KerasCV now includes a Segment Anything implementation, which enables you to do image segmentation using only "prompt points". No training data needed. With the JAX backend, it runs ~5x faster on GPU than the original PyTorch implementation. Told you JAX was fast. Guide:
-
Copilot Eliminates Need to Learn JavaScript and HTML
By
–
Copilot has fulfilled my dream of literally never having to learn javascript or html for the rest of my life and I am thrilled with the results.
-
Data Augmentation via Embedding Cone Sampling with Vec2Text
By
–
this was a neat little read. the idea is to do data augmentation with embeddings. they randomly sample around an embedding and then decode with vec2text. there is a trick to randomly sampling while not leaving the embedding manifold; they try to sample within an embedding "cone"
-
LangChain LCEL Chain Inspection Tools Released
By
–
LCEL Chain Inspection Need a better understanding of that long chain? We've recently added two methods to better inspect ANY chain created with LangChain Expression Language: View any chain as a graph
See all the prompts associated with a chain https://
python.langchain.com/docs/expressio
n_language/how_to/inspect
… -
Challenges of Deploying RAG Applications in Enterprise Environments
By
–
The most common use of LLMs in enterprise is building RAG (retrieval augmented generation) applications on a custom knowledge base, which are difficult to put in production. Some of the challenges are: •Parsing docs and PDFs (most open-source libraries struggle with this)
-
Information Extraction from Files Using LLMs
By
–
Information Extraction using LLMs This great blog walks through how to create an app that allows you to: Upload a file of your choice
Specify the schema you want to extract And then it pulls out all that info! Blog: https://
pub.towardsai.net/demystifying-i
nformation-extraction-using-llm-f1a551f01f66
… Full code links in blog! -
LangChain Community Growth Visualization Over Time
By
–
Our community is awesome!
— LangChain (@LangChain) 4 janvier 2024
Incredible to see this animation of the LangChain GitHub repository over time
Thank you to everyone who shows up!! Can you spot yourself? https://t.co/jTt7jGcdFjOur community is awesome! Incredible to see this animation of the LangChain GitHub repository over time Thank you to everyone who shows up!! Can you spot yourself?
-
Advanced Retrieval for RAG with Chroma Course
By
–
New short course on advanced retrieval for RAG (retrieval augmented generation)!
— Andrew Ng (@AndrewYNg) 4 janvier 2024
RAG fetches relevant documents to give context to an LLM. In Advanced Retrieval for AI with Chroma, taught by @trychroma founder @atroyn, you’ll learn:
(i) Query expansion using an LLM to rewrite… pic.twitter.com/7MHX4HT09VNew short course on advanced retrieval for RAG (retrieval augmented generation)! RAG fetches relevant documents to give context to an LLM. In Advanced Retrieval for AI with Chroma, taught by @trychroma founder @atroyn
, you’ll learn:
(i) Query expansion using an LLM to rewrite