Chris Boothe

Quality retrieval has never come from general-purpose storage or SQL databases. Decades of search history (web, enterprise, recommendations) show that good retrieval systems are specialized, with purpose-built ranking. Storing a vector doesn’t cut it. The category ‘vector database’ died, but retrieval infrastructure did not. The value shifts to relevance. The market will reward systems that solve retrieval, not those that expose an ANN index in SQL or cloud object storage.

🚨 Announcement Releasing Unverceled-nextjs, a tooling heavy basic next.js starter-kit utilising OpenNext to deploy to Cloudflare Workers. Comes with Playwright, Vitest, ESLint, Prettier, MarkdownLint, Cspell, Lefthook and so much more! 🫡 github.com/ixahmedxi/unve…

i’m a big fan of Domain Driven Development first i buy the domain and eventually i develop the app

Dearest MCP developers, You can now monetize your MCP in a few lines of code with @stripe, available today. 💸 - Bill subscriptions or usage-based - Works with any client - Supports @Cloudflare's Agents SDK (more to come) MCP, a new AI-native customer channel. Get started. ⤵️

👀

One of the challenges with MCP, especially once remote becomes available is auth! Here's a demo that shows how to connect Claude to your Slack workspace using OAuth + MCP Powered by Cloudflare Workers 🧡 (shoutout to @glenmaddern for figuring out the hard parts of auth so that you won't have to)

Generate PDFs at scale for pennies using Durable Objects and Browser Worker, archived internally on Cloudflare with @honojs Thanks @DhravyaShah, you really helped me with this one 🫶

For anyone who says SEO is dead... After Google released AI Overviews, we saw a 1.32% increase in clicks. That's data from over 400 websites. Yes, it's not much, but AI Overviews didn't kill site traffic. On top of that we are seeing a higher demand for SEO services at my agency NP Digital. But instead of it just being for Google, people are also asking for their content to be optimized for TikTok and Instagram search. And for their product and services to be recommended by ChatGPT. SEO isn't dead, it just changed from "search engine optimization" to "search everywhere optimization".

If you're a non-technical Founder who hired a software development agency. These are some red flags to look for: - The agency is hosting your code on their Github account. - The agency has a "Lead" person, and you don't know who's actually building your product. (cont.)

Optimizing ingest performance is crucial for various PostgreSQL use cases, including application monitoring, application analytics, IoT monitoring, and more. 💪 To improve PostgreSQL insert performance, consider these 13 tips: 1) Use indexes in moderation. 2) Reconsider foreign key constraints. 3) Avoid unnecessary UNIQUE keys. 4) Use separate disks for WAL and data. 5) Use performant disks. 6) Use parallel writes. 7) Insert rows in batches. 8) Properly configure shared_buffers. 9) Run Docker images on Linux hosts. 10) Avoid too many or too small chunks. 11) Avoid “too large” chunks. 12) Write data in loose time order. 13) Watch row width. For more details on how to improve PostgreSQL inserts performance, you can read the full article here: tsdb.co/insertperforma…

USE OPEN-SOURCE LLMS IN POSTGRESQL with @ollama and new open-source extension pgai 🦙 What is Ollama? In contrast to proprietary language models, open-source models are private, free to use (hardware costs aside), can run locally, and can be easily customized for your use case. But getting started with open-source LLMs can be tricky. Enter Ollama. Ollama is the easiest and most popular way to get up and running with open-source language models. It enables easy access and usage of a variety of open-source embedding and generation models, like Llama 3, Mistral, Phi 3, Gemma and more. 🐘 What is pgai? Pgai is an open-source PostgreSQL extension that brings AI models closer to your PostgreSQL data. We built pgai to make AI Engineering (h/t @swyx ) more accessible to developers familiar with PostgreSQL, making it easier for them to build RAG and search. 🧰 What can I do with pgai and Ollama? Embedding creation: You can create embeddings on data in PostgreSQL tables using popular open-source embedding models like BERT, Meta’s llama 3, and Nomic Embed. Pgai stores embeddings in the pgvector data type, making it easy to perform search and RAG with pgvector and pgvectorscale after embeddings are created. RAG and LLM reasoning: You can now perform RAG and LLM reasoning tasks on data in PostgreSQL tables, leveraging state of the art open-source models like Meta’s Llama 3, Mistral, Gemma, Qwen, Phi 3 and more. This unlocks common reasoning tasks like summarization, categorization, and data enrichment, all with a SQL query without leaving the database. (See the blog at the end of this post for three examples with code.) 👏 Big shoutout to @sql_johnpruitt, AI Engineer at @TimescaleDB, who added Ollama support to pgai (in less than a week I might add). 🧑‍💻Very cool! How can I get started? Pgai is open-source under the PostgreSQL license, and free to use on any PostgreSQL database. You can find installation instructions on the pgai GitHub repository (see end of post).  It’s also available on any database service in Timescale’s PostgreSQL cloud platform. 📚Learn more Ollama and pgai explainer blog: tsdb.co/ollamae pgai github repo (⭐s appreciated): github.com/timescale/pgai

This interesting Klarna is exciting it's checkout business. I guess you're either a BNPL provider OR a payment service provider. Not both. cityam.com/klarna-to-exit…

With every yes, comes a stress.

Today, we're announcing something very simple: Sign up with Plaid. That “simple” thing increases end-to-end sign up rates by 10 - 25%, and we're calling it Plaid Layer. Here’s how we give you the Internet’s fastest, highest converting financial onboarding experience 🧵

Product managers: You're not building products, you're building businesses. BIG DIFFERENCE.

Find all the awesome LLM Apps demo with RAG in the following Github Repo. P.S: Don't forget to star the repo to show your support 🌟 github.com/Shubhamsaboo/a…

Product managers need to balance process + gut instinct. Gut instinct isn't bad. It's not made up BS. It comes from honing your craft, deeply understanding the product, listening to users, tracking data and caring. All of that feeds the gut to make better, faster decisions w/o overly relying on methodologies, which ultimately lead to over-processing everything, slower decisions and too much consensus building.

Website Footer Design Best Practices: 27 Things to Put at the Bottom orbitmedia.com/blog/website-f…

Pretty crazy how quickly AI has become a commodity feature embedded into every software tool Everyone has AI compose, a co-pilot, and chat bot The irony? It’s all defensive and bearish if it works. Fewer seats to sell if you don’t need support reps and BDRs

7 years ago👇. Now AI*blockchain is happening, at scale. Anyone curious what's 7 years from now? 👀