Found 581 bookmarks
Newest
Building Production-Ready RAG Applications: Jerry Liu
Building Production-Ready RAG Applications: Jerry Liu
Large Language Models (LLM's) are starting to revolutionize how users can search for, interact with, and generate new content. Some recent stacks and toolkit...
·youtube.com·
Building Production-Ready RAG Applications: Jerry Liu
Evaluating ragas: A framework for RAG pipelines
Evaluating ragas: A framework for RAG pipelines
TL;DR ragas is a framework designed to assess the performance of Retrieval Augmented Generation (RAG) pipelines, a type of LLM application that uses external data to enhance its context. While there are tools to build RAG pipelines, evaluating their performance can be challenging. ragas offers tools rooted in recent research to evaluate LLM-generated text, providing insights into RAG pipeline performance. It can also be incorporated into CI/CD for ongoing performance checks.
tiktoken
·blog.takanabe.tokyo·
Evaluating ragas: A framework for RAG pipelines
A Complete Guide for Ragas, the RAG Pipeline for LLM Evaluation – AI StartUps Product Information, Reviews, Latest Updates
A Complete Guide for Ragas, the RAG Pipeline for LLM Evaluation – AI StartUps Product Information, Reviews, Latest Updates
Dive into the world of Ragas, the go-to Retrieval-Augmented Generation (RAG) pipeline evaluator. This comprehensive guide will walk you through its features, metrics, and integrations, making you an expert in evaluating Language Models (LLMs).
·cheatsheet.md·
A Complete Guide for Ragas, the RAG Pipeline for LLM Evaluation – AI StartUps Product Information, Reviews, Latest Updates
facebookresearch/faiss
facebookresearch/faiss
A library for efficient similarity search and clustering of dense vectors.
·github.com·
facebookresearch/faiss
Greg Kamradt on Twitter / X
Greg Kamradt on Twitter / X
visualizing text splitting & chunking strategiesChunkViz .com I thought I remembered a tool to visualize text chunking, but I couldn't find it, so I built oneI didn't realize it would be so visually pleasing to tinker with4 different @LangChainAI splitters featured https://t.co/4VywxHdqAa pic.twitter.com/vN2kdIBgxd— Greg Kamradt (@GregKamradt) December 8, 2023
·x.com·
Greg Kamradt on Twitter / X
Optimizing vector search performance with pgvector - Neon
Optimizing vector search performance with pgvector - Neon
According to the StackOverflow Survey 2023, nearly half of professional developers use Postgres. It’s natural then that the Postgres extension for vector similarity search, pgvector, is one of the most popular options for prototyping  AI-powered applications. But how to properly use pgvector? Is it the right tool for your dataset? Do you need an exact […]
·neon.tech·
Optimizing vector search performance with pgvector - Neon
The architecture of today's LLM applications
The architecture of today's LLM applications
Here’s everything you need to know to build your first LLM app and problem spaces you can start exploring today.
·github.blog·
The architecture of today's LLM applications
Andrej Karpathy on X: "# On the "hallucination problem" I always struggle a bit with I'm asked about the "hallucination problem" in LLMs. Because, in some sense, hallucination is all LLMs do. They are dream machines. We direct their dreams with prompts. The prompts start the dream, and based on the…" / X
Andrej Karpathy on X: "# On the "hallucination problem" I always struggle a bit with I'm asked about the "hallucination problem" in LLMs. Because, in some sense, hallucination is all LLMs do. They are dream machines. We direct their dreams with prompts. The prompts start the dream, and based on the…" / X
·twitter.com·
Andrej Karpathy on X: "# On the "hallucination problem" I always struggle a bit with I'm asked about the "hallucination problem" in LLMs. Because, in some sense, hallucination is all LLMs do. They are dream machines. We direct their dreams with prompts. The prompts start the dream, and based on the…" / X
LLM Visualization
LLM Visualization
A 3D animated visualization of an LLM with a walkthrough.
·bbycroft.net·
LLM Visualization
OpenAI For Finance
OpenAI For Finance
In this series, I discuss possible applications of OpenAI to finance and trading. Specifically we analyze financial audio, documents, and text. We will also ...
·youtube.com·
OpenAI For Finance
"Catching up on the weird world of LLMs" - Simon Willison (North Bay Python 2023)
"Catching up on the weird world of LLMs" - Simon Willison (North Bay Python 2023)
Simon Willison https://pretalx.northbaypython.org/nbpy-2023/talk/L8HPBK Large Language Models are the engines that power AI tools like ChatGPT, Bing and Bard. They are deeply weird, often frustrating and undeniably fascinating pieces of technology. This talk will attempt to summarize everything I've learned about them over the past year: how they are built, what they can do, what they can't do and how we can best tame them and use them to solve interesting problems. LLMs don't have to be large: I'll talk through the latest developments in openly licensed models you can run on your own devices, including on your phone and even in your web browser. I'll also discuss their as-yet unconquered security flaws, and the bewildering ethical implications of how they are trained and what they can damage. North Bay Python is a boutique one-track conference, held in Petaluma, California. Our first events were held in 2017-2019 in a 100 year-old theater in the city's downtown. After a planned one-year break that's turned into almost four years, we're excited to return! This year, we're holding our conference in July, in a barn, on a ranch overlooking the Petaluma River. Produced by NDV: https://youtube.com/channel/UCQ7dFBzZGlBvtU2hCecsBBg?sub_confirmation=1 Sun Jul 30 16:10:00 2023 at Reis River Ranch
·youtube.com·
"Catching up on the weird world of LLMs" - Simon Willison (North Bay Python 2023)
MatthewBerman on Twitter / X
MatthewBerman on Twitter / X
Ever wonder what an LLM actually looks like under the hood? This visualization is mesmerizing. Check it out yourself: https://t.co/Bp9e8r8AzO pic.twitter.com/f2oxoEQnma— MatthewBerman (@MatthewBerman) December 5, 2023
·x.com·
MatthewBerman on Twitter / X
Ksenia Se on Twitter / X
Ksenia Se on Twitter / X
3 free courses to learn more about large language models:1. @cohere LLM University2. @huggingface NLP course3. @LangChainAI and @DeepLearningAI_ LangChain for LLM Application DevelopmentLinks 👇🏼 pic.twitter.com/zllaBVvXZn— Ksenia Se (@Kseniase_) December 2, 2023
·x.com·
Ksenia Se on Twitter / X
BAAI/bge-base-en-v1.5 · Hugging Face
BAAI/bge-base-en-v1.5 · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
·huggingface.co·
BAAI/bge-base-en-v1.5 · Hugging Face