The best Hacker News stories from Show from the past day
Latest posts:
Show HN: OpenLLMetry – OpenTelemetry-based observability for LLMs
Hey HN, Nir, Gal and Tomer here. We’re open-sourcing a set of extensions we’ve built on top of OpenTelemetry that provide visibility into LLM applications - whether it be prompts, vector DBs and more. Here’s the repo: <a href="https://github.com/traceloop/openllmetry">https://github.com/traceloop/openllmetry</a>.<p>There’s already a decent number of tools for LLM observability, some open-source and some not. But what we found was missing for all of them is that they were closed-protocol by design, vendor-locking you to use their observability platform or their proprietary framework for running your LLMs.<p>It’s still early in the gen-AI space so we think it’s the right time to define an open protocol for observability. So we built OpenLLMetry. It extends OpenTelemetry and provides instrumentations for LLM-specific libraries which automatically monitor and trace prompts, token usage, embeddings, etc.<p>Two key benefits with OpenTelemetry are (1) you can trace your entire system execution, not just the LLM (so you can see how requests to DBs, or other calls affect the overall result); and (2) you can connect to any monitoring platform—no need to adopt new tools. Install the SDK and plug it into Datadog, Sentry, or both. Or switch between them easily.<p>We’ve already built instrumentations for LLMs like OpenAI, Anthropic and Cohere, vector DBs like Pinecone and LLM Frameworks like LangChain and Haystack. And we’ve built an SDK that makes it easy to use all of these instrumentations in case you’re not too familiar with OpenTelemetry.<p>Everything is written in Python (with Typescript around the corner) and licensed with Apache-2.0.<p>We’re using this SDK for our own platform (Traceloop), but our hope is that OpenLLMetry can evolve and thrive independently, giving everyone (including our users) the power of choice. We’ll be working with the OpenTelemetry community to get this to become a first-class citizen of OpenTelemetry.<p>Would love to hear your thoughts and opinions!<p>Check it out -<p>Docs: <a href="https://www.traceloop.com/docs/python-sdk/introduction">https://www.traceloop.com/docs/python-sdk/introduction</a><p>Github: <a href="https://github.com/traceloop/openllmetry">https://github.com/traceloop/openllmetry</a>
Show HN: OpenLLMetry – OpenTelemetry-based observability for LLMs
Hey HN, Nir, Gal and Tomer here. We’re open-sourcing a set of extensions we’ve built on top of OpenTelemetry that provide visibility into LLM applications - whether it be prompts, vector DBs and more. Here’s the repo: <a href="https://github.com/traceloop/openllmetry">https://github.com/traceloop/openllmetry</a>.<p>There’s already a decent number of tools for LLM observability, some open-source and some not. But what we found was missing for all of them is that they were closed-protocol by design, vendor-locking you to use their observability platform or their proprietary framework for running your LLMs.<p>It’s still early in the gen-AI space so we think it’s the right time to define an open protocol for observability. So we built OpenLLMetry. It extends OpenTelemetry and provides instrumentations for LLM-specific libraries which automatically monitor and trace prompts, token usage, embeddings, etc.<p>Two key benefits with OpenTelemetry are (1) you can trace your entire system execution, not just the LLM (so you can see how requests to DBs, or other calls affect the overall result); and (2) you can connect to any monitoring platform—no need to adopt new tools. Install the SDK and plug it into Datadog, Sentry, or both. Or switch between them easily.<p>We’ve already built instrumentations for LLMs like OpenAI, Anthropic and Cohere, vector DBs like Pinecone and LLM Frameworks like LangChain and Haystack. And we’ve built an SDK that makes it easy to use all of these instrumentations in case you’re not too familiar with OpenTelemetry.<p>Everything is written in Python (with Typescript around the corner) and licensed with Apache-2.0.<p>We’re using this SDK for our own platform (Traceloop), but our hope is that OpenLLMetry can evolve and thrive independently, giving everyone (including our users) the power of choice. We’ll be working with the OpenTelemetry community to get this to become a first-class citizen of OpenTelemetry.<p>Would love to hear your thoughts and opinions!<p>Check it out -<p>Docs: <a href="https://www.traceloop.com/docs/python-sdk/introduction">https://www.traceloop.com/docs/python-sdk/introduction</a><p>Github: <a href="https://github.com/traceloop/openllmetry">https://github.com/traceloop/openllmetry</a>
Show HN: OpenLLMetry – OpenTelemetry-based observability for LLMs
Hey HN, Nir, Gal and Tomer here. We’re open-sourcing a set of extensions we’ve built on top of OpenTelemetry that provide visibility into LLM applications - whether it be prompts, vector DBs and more. Here’s the repo: <a href="https://github.com/traceloop/openllmetry">https://github.com/traceloop/openllmetry</a>.<p>There’s already a decent number of tools for LLM observability, some open-source and some not. But what we found was missing for all of them is that they were closed-protocol by design, vendor-locking you to use their observability platform or their proprietary framework for running your LLMs.<p>It’s still early in the gen-AI space so we think it’s the right time to define an open protocol for observability. So we built OpenLLMetry. It extends OpenTelemetry and provides instrumentations for LLM-specific libraries which automatically monitor and trace prompts, token usage, embeddings, etc.<p>Two key benefits with OpenTelemetry are (1) you can trace your entire system execution, not just the LLM (so you can see how requests to DBs, or other calls affect the overall result); and (2) you can connect to any monitoring platform—no need to adopt new tools. Install the SDK and plug it into Datadog, Sentry, or both. Or switch between them easily.<p>We’ve already built instrumentations for LLMs like OpenAI, Anthropic and Cohere, vector DBs like Pinecone and LLM Frameworks like LangChain and Haystack. And we’ve built an SDK that makes it easy to use all of these instrumentations in case you’re not too familiar with OpenTelemetry.<p>Everything is written in Python (with Typescript around the corner) and licensed with Apache-2.0.<p>We’re using this SDK for our own platform (Traceloop), but our hope is that OpenLLMetry can evolve and thrive independently, giving everyone (including our users) the power of choice. We’ll be working with the OpenTelemetry community to get this to become a first-class citizen of OpenTelemetry.<p>Would love to hear your thoughts and opinions!<p>Check it out -<p>Docs: <a href="https://www.traceloop.com/docs/python-sdk/introduction">https://www.traceloop.com/docs/python-sdk/introduction</a><p>Github: <a href="https://github.com/traceloop/openllmetry">https://github.com/traceloop/openllmetry</a>
Show HN: See library availabilities for your Goodreads want-to-read list
This is a Goodreads + Libby app integration which shows you the library availability for each of the books on your Goodreads want to read list.<p>Basically, I got sick of manually looking up each book on my Want to Read list on the Libby app to see if it was available or how long the wait was. So I made this site which easily gathers all that info for me.<p>At this point, I'm scraping Goodreads to figure out the "Want to Read" list. Libby provides a nice API though.<p>Any feedback is appreciated!! I also have a substack that I'm going to use to post updates, so follow along there if you're interested :) projecttbr.substack.com
Show HN: See library availabilities for your Goodreads want-to-read list
This is a Goodreads + Libby app integration which shows you the library availability for each of the books on your Goodreads want to read list.<p>Basically, I got sick of manually looking up each book on my Want to Read list on the Libby app to see if it was available or how long the wait was. So I made this site which easily gathers all that info for me.<p>At this point, I'm scraping Goodreads to figure out the "Want to Read" list. Libby provides a nice API though.<p>Any feedback is appreciated!! I also have a substack that I'm going to use to post updates, so follow along there if you're interested :) projecttbr.substack.com
Show HN: See library availabilities for your Goodreads want-to-read list
This is a Goodreads + Libby app integration which shows you the library availability for each of the books on your Goodreads want to read list.<p>Basically, I got sick of manually looking up each book on my Want to Read list on the Libby app to see if it was available or how long the wait was. So I made this site which easily gathers all that info for me.<p>At this point, I'm scraping Goodreads to figure out the "Want to Read" list. Libby provides a nice API though.<p>Any feedback is appreciated!! I also have a substack that I'm going to use to post updates, so follow along there if you're interested :) projecttbr.substack.com
Show HN: See library availabilities for your Goodreads want-to-read list
This is a Goodreads + Libby app integration which shows you the library availability for each of the books on your Goodreads want to read list.<p>Basically, I got sick of manually looking up each book on my Want to Read list on the Libby app to see if it was available or how long the wait was. So I made this site which easily gathers all that info for me.<p>At this point, I'm scraping Goodreads to figure out the "Want to Read" list. Libby provides a nice API though.<p>Any feedback is appreciated!! I also have a substack that I'm going to use to post updates, so follow along there if you're interested :) projecttbr.substack.com
Show HN: Obligator – An OpenID Connect server for self-hosters
Show HN: Obligator – An OpenID Connect server for self-hosters
Show HN: Obligator – An OpenID Connect server for self-hosters
Show HN: Obligator – An OpenID Connect server for self-hosters
Show HN: SingleAPI – Convert the Internet into your own API
Hi! I created a universal data API that uses headless browsers and GPT to extract any data from the web in JSON format. I started this project because I needed some API to do data enrichment to get company data (headcount, investment rounds, etc.). Once I did the first version, I quickly realized that there can be many use cases for such a tool: data enrichment, web scraping, data validation, etc.<p>Thanks!
Show HN: eBPF tool to monitor disk usage, perform actions
Show HN: Standalone Jdk.compiler, Java Compiler Framework and Tree API
With this standalone compiler, you can rely on all Java 11 javac features to be available, even when using newer Java versions. Specifically, this allows you to:<p>- compile code even if your Java environment isn't a full JDK (Java JRE, for example!)<p>- target Java 1.7 for compilation without any warnings or restrictions.<p>- use the Compiler Tree API without resorting to --add-opens trickery that may eventually fail in newer Java releases<p>- build a modified compiler with additional features or custom tweaks<p>I made this after finding that the otherwise superb "jsweet" Java-to-JavaScript transpiler failed to build and run with Java 16 or newer. Surprisingly, I couldn't find any prior work other than "proper" standalone compilers like Eclipse's ecj that would properly work with modern Java runtimes.<p>I'm excited to see what can be done now that we have this scaffolding.
Building an app to learn languages with short stories
Hi HN! I wrote a post about the things I have been working on for Webbu, an app to learn languages via short stories. Initially, a few HN readers tried the app, so I wanted to share some more details of what I'm doing and would love to hear any feedback you have.
Show HN: I learned to code and built a crypto analytics platform
Hey everyone!<p>I am an enthusiast trader and a year ago I had this idea to create a free-to-use website that would feature all the most essential tools that traders would use on a daily basis.<p>So I learned to code and build it—I did everything including design, texts, code, and SEO—which took me 12 months to launch and a year and a half to make it look like it currently does.<p>I was into marketing and design before, but I didn't know barely anything about coding. The website is built using Next.js, Tailwind CSS, and Typescript with Framer Motion animations and lots of APIs.<p>I’m actively working on the project and in the following months I will release a huge update that will feature a renewed interface and access to real time on chain data and analytics.<p>Feel free to ask any questions and thanks a lot for reading this, it means a lot to me. Any feedback and your opinions would be highly appreciated.
Show HN: I learned to code and built a crypto analytics platform
Hey everyone!<p>I am an enthusiast trader and a year ago I had this idea to create a free-to-use website that would feature all the most essential tools that traders would use on a daily basis.<p>So I learned to code and build it—I did everything including design, texts, code, and SEO—which took me 12 months to launch and a year and a half to make it look like it currently does.<p>I was into marketing and design before, but I didn't know barely anything about coding. The website is built using Next.js, Tailwind CSS, and Typescript with Framer Motion animations and lots of APIs.<p>I’m actively working on the project and in the following months I will release a huge update that will feature a renewed interface and access to real time on chain data and analytics.<p>Feel free to ask any questions and thanks a lot for reading this, it means a lot to me. Any feedback and your opinions would be highly appreciated.
Show HN: I learned to code and built a crypto analytics platform
Hey everyone!<p>I am an enthusiast trader and a year ago I had this idea to create a free-to-use website that would feature all the most essential tools that traders would use on a daily basis.<p>So I learned to code and build it—I did everything including design, texts, code, and SEO—which took me 12 months to launch and a year and a half to make it look like it currently does.<p>I was into marketing and design before, but I didn't know barely anything about coding. The website is built using Next.js, Tailwind CSS, and Typescript with Framer Motion animations and lots of APIs.<p>I’m actively working on the project and in the following months I will release a huge update that will feature a renewed interface and access to real time on chain data and analytics.<p>Feel free to ask any questions and thanks a lot for reading this, it means a lot to me. Any feedback and your opinions would be highly appreciated.
Show HN: REST Alternative to GraphQL and tRPC
Show HN: REST Alternative to GraphQL and tRPC