♊️ GemiNews 🗞️ (dev)

Demo 1: Embeddings + Recommendation Demo 2: Bella RAGa Demo 3: NewRetriever Demo 4: Assistant function calling

🗞️Daily Reading List – April 4, 2024 (#291)

🏷️ Daily Reading List

🗿Semantically Similar Articles (by :title_embedding)

Daily Reading List – April 4, 2024 (#291)

Article Image
2024-04-04 - Richard Seroter (from Richard Seroter Blog)

Today's links look at function calling with LLMs, whether prompt engineering is already tired, and if "platform as product" is back.

Given the fast evolution of technology right now, I wonder if enterprises are doing strategic planning exercises more often. Annual plans don’t work in this climate. As I read the items below, I was thinking about how organizations are adapting! [blog] Deterministic Generative AI with Gemini Function Calling in Java. Sometimes you have to see something over and over again before it clicks. I’ve now read enough about function calling in LLMs to “get” it. Good post here from Abi. [blog] How we built Text-to-SQL at Pinterest. Is natural language about to become the preferred interface into data sources? Maybe, with the help of generative AI. Here’s what Pinterest built. [guide] Infrastructure for a RAG-capable generative AI application using GKE. So good. Learn how to build an AI platform that makes it possible to deploy contextual apps that know about your domain. [article] Is prompt engineering’s party over? That was fast. Will LLMs be better prompts, and are they already better than humans? I wouldn’t hire a dedicated “prompt engineer”, but the tech isn’t ready for the robots to take this on. [article] Aerospike raises $100M for its real-time database platform to capitalize on the AI boom. Done right, a lot of existing data vendors will find new life by legitimately serving AI use cases. Good for Aerospike. [blog] Parsing Invoices using Gemini 1.5 API with Google Apps Script. There are so many creative uses of LLMs, even when applied to “boring” scenarios like processing invoices. Fun example here. [blog] Firebase at Cloud Next ’24. This is the most straight-up dev content I’ve seen at our cloud conference. Learn Flutter and Angular, Go and Android. And go deep on Firebase. [blog] KubeCon EU Paris: The (Re)Emergence of Platform as a Product. I’ve been on the “platform as product” train for many years now, and modern platform engineering embraces that concept. [blog] DNS providers for Google Kubernetes Engine explained. Geeky topic, but there are performance and reliability outcomes that stem from your choices here. ## Want to get this update sent to you every day? Subscribe to my RSS feed or subscribe via email below: Subscribe

🏷️ Daily Reading List
[Blogs] 🌎 https://seroter.com/2024/04/04/daily-reading-list-april-4-2024-291/ [🧠] [v2] article_embedding_description: {:llm_project_id=>"Unavailable", :llm_dimensions=>nil, :article_size=>4406, :llm_embeddings_model_name=>"textembedding-gecko"}
[🧠] [v1/3] title_embedding_description: {:ricc_notes=>"[embed-v3] Fixed on 9oct24. Only seems incompatible at first glance with embed v1.", :llm_project_id=>"unavailable possibly not using Vertex", :llm_dimensions=>nil, :article_size=>4406, :poly_field=>"title", :llm_embeddings_model_name=>"textembedding-gecko"}
[🧠] [v1/3] summary_embedding_description: {:ricc_notes=>"[embed-v3] Fixed on 9oct24. Only seems incompatible at first glance with embed v1.", :llm_project_id=>"unavailable possibly not using Vertex", :llm_dimensions=>nil, :article_size=>4406, :poly_field=>"summary", :llm_embeddings_model_name=>"textembedding-gecko"}
[🧠] As per bug https://github.com/palladius/gemini-news-crawler/issues/4 we can state this article belongs to titile/summary version: v3 (very few articles updated on 9oct24)

🗿article.to_s 

------------------------------
Title: Daily Reading List – April 4, 2024 (#291)
Summary: Today's links look at function calling with LLMs, whether prompt engineering is already tired, and if "platform as product" is back.

[content]
Given the fast evolution of technology right now, I wonder if enterprises are doing strategic planning exercises more often. Annual plans don’t work in this climate. As I read the items below, I was thinking about how organizations are adapting!



[blog] Deterministic Generative AI with Gemini Function Calling in Java. Sometimes you have to see something over and over again before it clicks. I’ve now read enough about function calling in LLMs to “get” it. Good post here from Abi.



[blog] How we built Text-to-SQL at Pinterest. Is natural language about to become the preferred interface into data sources? Maybe, with the help of generative AI. Here’s what Pinterest built.



[guide] Infrastructure for a RAG-capable generative AI application using GKE. So good. Learn how to build an AI platform that makes it possible to deploy contextual apps that know about your domain.



[article] Is prompt engineering’s party over? That was fast. Will LLMs be better prompts, and are they already better than humans? I wouldn’t hire a dedicated “prompt engineer”, but the tech isn’t ready for the robots to take this on.



[article] Aerospike raises $100M for its real-time database platform to capitalize on the AI boom. Done right, a lot of existing data vendors will find new life by legitimately serving AI use cases. Good for Aerospike.



[blog] Parsing Invoices using Gemini 1.5 API with Google Apps Script. There are so many creative uses of LLMs, even when applied to “boring” scenarios like processing invoices. Fun example here.



[blog] Firebase at Cloud Next ’24. This is the most straight-up dev content I’ve seen at our cloud conference. Learn Flutter and Angular, Go and Android. And go deep on Firebase.



[blog] KubeCon EU Paris: The (Re)Emergence of Platform as a Product. I’ve been on the “platform as product” train for many years now, and modern platform engineering embraces that concept.



[blog] DNS providers for Google Kubernetes Engine explained. Geeky topic, but there are performance and reliability outcomes that stem from your choices here.



##



Want to get this update sent to you every day? Subscribe to my RSS feed or subscribe via email below:



		
			
				
					
						Subscribe
					
				
			
		
	
[/content]

Author: Richard Seroter
PublishedDate: 2024-04-04
Category: Blogs
NewsPaper: Richard Seroter Blog
Tags: Daily Reading List
{"id"=>6325,
"title"=>"Daily Reading List – April 4, 2024 (#291)",
"summary"=>"Today's links look at function calling with LLMs, whether prompt engineering is already tired, and if \"platform as product\" is back.",
"content"=>"\n

Given the fast evolution of technology right now, I wonder if enterprises are doing strategic planning exercises more often. Annual plans don’t work in this climate. As I read the items below, I was thinking about how organizations are adapting!

\n\n\n\n

[blog] Deterministic Generative AI with Gemini Function Calling in Java. Sometimes you have to see something over and over again before it clicks. I’ve now read enough about function calling in LLMs to “get” it. Good post here from Abi.

\n\n\n\n

[blog] How we built Text-to-SQL at Pinterest. Is natural language about to become the preferred interface into data sources? Maybe, with the help of generative AI. Here’s what Pinterest built.

\n\n\n\n

[guide] Infrastructure for a RAG-capable generative AI application using GKE. So good. Learn how to build an AI platform that makes it possible to deploy contextual apps that know about your domain.

\n\n\n\n

[article] Is prompt engineering’s party over? That was fast. Will LLMs be better prompts, and are they already better than humans? I wouldn’t hire a dedicated “prompt engineer”, but the tech isn’t ready for the robots to take this on.

\n\n\n\n

[article] Aerospike raises $100M for its real-time database platform to capitalize on the AI boom. Done right, a lot of existing data vendors will find new life by legitimately serving AI use cases. Good for Aerospike.

\n\n\n\n

[blog] Parsing Invoices using Gemini 1.5 API with Google Apps Script. There are so many creative uses of LLMs, even when applied to “boring” scenarios like processing invoices. Fun example here.

\n\n\n\n

[blog] Firebase at Cloud Next ’24. This is the most straight-up dev content I’ve seen at our cloud conference. Learn Flutter and Angular, Go and Android. And go deep on Firebase.

\n\n\n\n

[blog] KubeCon EU Paris: The (Re)Emergence of Platform as a Product. I’ve been on the “platform as product” train for many years now, and modern platform engineering embraces that concept.

\n\n\n\n

[blog] DNS providers for Google Kubernetes Engine explained. Geeky topic, but there are performance and reliability outcomes that stem from your choices here.

\n\n\n\n

##

\n\n\n\n

Want to get this update sent to you every day? Subscribe to my RSS feed or subscribe via email below:

\n\n\n
\n\t\t
\n\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

\n\t\t\t\t\t\tSubscribe\n\t\t\t\t\t

\n\t\t\t\t
\n\t\t\t
\n\t\t
\n\t
",
"author"=>"Richard Seroter",
"link"=>"https://seroter.com/2024/04/04/daily-reading-list-april-4-2024-291/",
"published_date"=>Thu, 04 Apr 2024 23:30:16.000000000 UTC +00:00,
"image_url"=>"https://2.gravatar.com/avatar/2fab44e2f8decc2654cf4cb6b3bef813b072a16c7206880423c14d2e4be6f910?s=96&d=https%3A%2F%2F2.gravatar.com%2Favatar%2Fad516503a11cd5ca435acc9bb6523536%3Fs%3D96",
"feed_url"=>"https://seroter.com/2024/04/04/daily-reading-list-april-4-2024-291/",
"language"=>nil,
"active"=>true,
"ricc_source"=>"feedjira::v1",
"created_at"=>Fri, 05 Apr 2024 07:23:10.828797000 UTC +00:00,
"updated_at"=>Mon, 21 Oct 2024 18:52:43.753344000 UTC +00:00,
"newspaper"=>"Richard Seroter Blog",
"macro_region"=>"Blogs"}
Edit this article
Back to articles