Retrieval in LangChain
Build better AI apps with flexible retrieval methods in LangChain. Use any retriever—from semantic to hybrid—to create personalized ChatGPT for your data.
The latest blog posts to take off on Hacker News. 6,299 posts.
Build better AI apps with flexible retrieval methods in LangChain. Use any retriever—from semantic to hybrid—to create personalized ChatGPT for your data.
The Siderwin research project tested a new method of steelmaking that uses direct electrolysis of iron oxide in a pilot plant in France. The steelmaker ArcelorMittal now announced that it wants to commercialize the technology.
Johns Hopkins Medicine study adds to evidence that T cell-driven changes in the gut may affect brain function associated with depressive symptoms
Moore, who set the course for the future of the semiconductor industry, devoted his later years to philanthropy.
*the full story is now on the official clearspace blog
We're reversing course. After taking in feedback from the community, we’re no longer sunsetting the Free Team plan.
To learn how optimizing compilers are made, I built one targeting the 6502 architecture . In a bizarre twist, my compiler generates faster code than GCC, LLVM, and every other compiler I compared it to.
Responding to the French National Assembly’s decision to permit the use of mass video surveillance technology powered by Artificial Intelligence (AI) during the 2024 Olympics, Mher Hakobyan, Amnesty International’s Advocacy Advisor on AI Regulation, said: “France’s decision to allow the use of mass surveillance…
I hated writing in high school.
The Let’s Encrypt team is excited to announce that ACME Renewal Information (ARI) is live in production! ARI makes it possible for our subscribers to handle certificate revocation and renewal as easily and automatically as the process of getting a certificate in the first place. With ARI, Let’s Encrypt can signal to…
An update on our findings, the actions we’ve taken, and technical details of the bug.
In another episode of “I’ve been a web designer for how long and am only now learning about this?” let’s talk about CSS system colors. Background On my blog, I…
The TodoMVC implemented in Kobold weighs about 30kb when gzipped over the wire, out of which the gzipped Wasm blob is under 20kb. There are no tricks there . I haven't replaced the default allocator, nor have I minified the JavaScript (although I probably should).
Is software done now? Processing the the ChatGPT Plugins announcement.
Introducing 'Hello Dolly,' a project to democratize AI by integrating ChatGPT and open models, making advanced AI accessible to everyone.
An not-for-profit roundup of affordable PCB manufacturers. Originally published in 2023 and last updated January 2026.
I always got fascinated by heap memory. Questions such as How heap memory is obtained from kernel? How efficiently memory is managed? Is it managed by kernel or by library or by application itself?…
[…] Embedded in Academia : Why Take a Compiler Course? – Seconded, or whatever – my compiler course was briefer than I'd have liked but many of my peers didn't take it and I spent ages explaining what I thought where simple concepts to them when working on group projects and the like. […]
The embarrassing investor meltdown surrounding Silicon Valley Bank should drive us to consider new models.
At approximately 05:00 UTC on March 24, out of an abundance of caution, we replaced our RSA SSH host key used to secure Git operations for GitHub.com.
Series Introduction In this series of articles I would like to share with you a set of ideas that are meant to help non-technical people build a better intuition as to what the current software and…
Hacker News displays comments in a tree. This can be frustrating if you want to keep track of a particular conversation, as you constantly have to seek through the tree to find the latest comment.
I wrote about my language learning startup, Readlang , back in 2014 , and then again in 2016 , both times attracting attention on Hacker News, where my story of a struggling one-man startup seemed to resonate. Well, it’s now 7 years later, and a bunch has happened since, so it’s time for an update…
React starter kits (Vite, Next, Astro, Remix, React Router) which help React developers to start a React project in 2025 ...
Low-rank adaptation (LoRA) is a technique for fine-tuning models that has some advantages over previous methods: