The best Hacker News stories from Show from the past day
Latest posts:
Show HN: BetterOCR combines and corrects multiple OCR engines with an LLM
Show HN: Is It Toxic To? – Check if a plant is toxic to your pets
All information is from the ASPCA's list of toxic plants (<a href="https://www.aspca.org/pet-care/animal-poison-control/toxic-and-non-toxic-plants" rel="nofollow noreferrer">https://www.aspca.org/pet-care/animal-poison-control/toxic-a...</a>)
Show HN: Is It Toxic To? – Check if a plant is toxic to your pets
All information is from the ASPCA's list of toxic plants (<a href="https://www.aspca.org/pet-care/animal-poison-control/toxic-and-non-toxic-plants" rel="nofollow noreferrer">https://www.aspca.org/pet-care/animal-poison-control/toxic-a...</a>)
Show HN: Encrypt and upload files to IPFS from browser
Hi HN, I'm building ThirdCloud with the goal to replace Google Drive for everyone: more private, cheaper & maybe better UI/UX.<p>So far, I've successfully implemented the main feature, which involves uploading and downloading files. Files are encrypted before being sent to IPFS network.<p>Would like to hear your thoughts on this proof of concept.
Show HN: Demystifying Advanced RAG Pipelines
I've built an advanced RAG (Retrieval-Augmented Generation) pipeline from scratch to demystify the complex mechanics of modern LLM-powered Question Answering systems. This repository features:<p>-- An implementation of a sub-question query engine from scratch to answer complex user questions.<p>-- Illustrative explanations that unveil the inner workings of the system.<p>-- An analysis of the challenges I faced while working with the system, like prompt engineering and cost estimation.<p>-- Qualitative comparison with similar frameworks like LlamaIndex, offering a broader perspective.<p>Key Takeaway: While Modern QA pipelines with advanced RAG abstractions may seem complex, they are fundamentally powered by a series of LLM calls with meticulous prompt design. Hoping that this repository provides intuitive insights for building more robust and efficient RAG systems. All feedback is warmly welcomed!
Show HN: Demystifying Advanced RAG Pipelines
I've built an advanced RAG (Retrieval-Augmented Generation) pipeline from scratch to demystify the complex mechanics of modern LLM-powered Question Answering systems. This repository features:<p>-- An implementation of a sub-question query engine from scratch to answer complex user questions.<p>-- Illustrative explanations that unveil the inner workings of the system.<p>-- An analysis of the challenges I faced while working with the system, like prompt engineering and cost estimation.<p>-- Qualitative comparison with similar frameworks like LlamaIndex, offering a broader perspective.<p>Key Takeaway: While Modern QA pipelines with advanced RAG abstractions may seem complex, they are fundamentally powered by a series of LLM calls with meticulous prompt design. Hoping that this repository provides intuitive insights for building more robust and efficient RAG systems. All feedback is warmly welcomed!
Show HN: WireHole combines WireGuard, Pi-hole, and Unbound with an easy UI
WireHole offers a unified docker-compose project that integrates WireGuard, PiHole, and Unbound, complete with a user interface. This solution is designed to empower users to swiftly set up and manage either a full or split-tunnel WireGuard VPN. It features ad-blocking capabilities through PiHole and enhanced DNS caching and privacy options via Unbound. The intuitive UI makes deployment and ongoing management straightforward, providing a comprehensive VPN solution with added privacy features.
Show HN: WireHole combines WireGuard, Pi-hole, and Unbound with an easy UI
WireHole offers a unified docker-compose project that integrates WireGuard, PiHole, and Unbound, complete with a user interface. This solution is designed to empower users to swiftly set up and manage either a full or split-tunnel WireGuard VPN. It features ad-blocking capabilities through PiHole and enhanced DNS caching and privacy options via Unbound. The intuitive UI makes deployment and ongoing management straightforward, providing a comprehensive VPN solution with added privacy features.
Show HN: WireHole combines WireGuard, Pi-hole, and Unbound with an easy UI
WireHole offers a unified docker-compose project that integrates WireGuard, PiHole, and Unbound, complete with a user interface. This solution is designed to empower users to swiftly set up and manage either a full or split-tunnel WireGuard VPN. It features ad-blocking capabilities through PiHole and enhanced DNS caching and privacy options via Unbound. The intuitive UI makes deployment and ongoing management straightforward, providing a comprehensive VPN solution with added privacy features.
Show HN: OpenSign – Open source alternative to DocuSign
Show HN: OpenSign – Open source alternative to DocuSign
Show HN: OpenSign – Open source alternative to DocuSign
Show HN: OpenSign – Open source alternative to DocuSign
Show HN: Pākiki Proxy – An intercepting proxy for penetration testing
Hey HN,
I've been working on an intercepting proxy for penetration testing over the last few years in my spare time.<p>Some points of difference from the existing tools:<p>* The UIs are built using the native platform frameworks, meaning they look and behave like other applications on the desktop.<p>* It has a fully embedded and integrated Python scripting engine.<p>* It’s fully native meaning it’s nicer on system resources.<p>* It has a number of built in scripts to automate reconnaissance, content discovery, authorisation checks, etc.<p>* The core of it is open source.<p>I'm really keen to get any feedback!
Show HN: Pākiki Proxy – An intercepting proxy for penetration testing
Hey HN,
I've been working on an intercepting proxy for penetration testing over the last few years in my spare time.<p>Some points of difference from the existing tools:<p>* The UIs are built using the native platform frameworks, meaning they look and behave like other applications on the desktop.<p>* It has a fully embedded and integrated Python scripting engine.<p>* It’s fully native meaning it’s nicer on system resources.<p>* It has a number of built in scripts to automate reconnaissance, content discovery, authorisation checks, etc.<p>* The core of it is open source.<p>I'm really keen to get any feedback!
Show HN: Pākiki Proxy – An intercepting proxy for penetration testing
Hey HN,
I've been working on an intercepting proxy for penetration testing over the last few years in my spare time.<p>Some points of difference from the existing tools:<p>* The UIs are built using the native platform frameworks, meaning they look and behave like other applications on the desktop.<p>* It has a fully embedded and integrated Python scripting engine.<p>* It’s fully native meaning it’s nicer on system resources.<p>* It has a number of built in scripts to automate reconnaissance, content discovery, authorisation checks, etc.<p>* The core of it is open source.<p>I'm really keen to get any feedback!
Show HN: Biblos – Semantic Bible Embedded Vector Search and Claude LLM
Introducing Biblos, a simple tool for semantic search and summarization of Bible passages. Leveraging Chroma for vector search with BAAI BGE embeddings, semantically find related verses across the Bible. The tool employs Anthropic's Claude LLM model for generating high-quality summaries of retrieved passages, contextualizing your search topic. Built on a Retrieval Augmented Generation (RAG) architecture, the app implements a simple Streamlit Web UI using Python. Deployed using render.com, the app is available at <a href="https://biblos.app" rel="nofollow noreferrer">https://biblos.app</a><p>Note: Search by just topic/keywords, e.g. "Kingdom of Heaven", for broader results!
Show HN: Biblos – Semantic Bible Embedded Vector Search and Claude LLM
Introducing Biblos, a simple tool for semantic search and summarization of Bible passages. Leveraging Chroma for vector search with BAAI BGE embeddings, semantically find related verses across the Bible. The tool employs Anthropic's Claude LLM model for generating high-quality summaries of retrieved passages, contextualizing your search topic. Built on a Retrieval Augmented Generation (RAG) architecture, the app implements a simple Streamlit Web UI using Python. Deployed using render.com, the app is available at <a href="https://biblos.app" rel="nofollow noreferrer">https://biblos.app</a><p>Note: Search by just topic/keywords, e.g. "Kingdom of Heaven", for broader results!
Show HN: Biblos – Semantic Bible Embedded Vector Search and Claude LLM
Introducing Biblos, a simple tool for semantic search and summarization of Bible passages. Leveraging Chroma for vector search with BAAI BGE embeddings, semantically find related verses across the Bible. The tool employs Anthropic's Claude LLM model for generating high-quality summaries of retrieved passages, contextualizing your search topic. Built on a Retrieval Augmented Generation (RAG) architecture, the app implements a simple Streamlit Web UI using Python. Deployed using render.com, the app is available at <a href="https://biblos.app" rel="nofollow noreferrer">https://biblos.app</a><p>Note: Search by just topic/keywords, e.g. "Kingdom of Heaven", for broader results!
Show HN: ScratchDB – Open-Source Snowflake on ClickHouse
Hello! For the past year I’ve been working on a fully-managed data warehouse built on Clickhouse. I built this because I was frustrated with how much work was required to run an OLAP database in prod: re-writing my app to do batch inserts, managing clusters and needing to look up special CREATE TABLE syntax every time I made a change. I found pricing for other warehouses confusing (what is a “credit” exactly?) and worried about getting capacity-planning wrong.<p>I was previously building accounting software for firms with millions of transactions. I desperately needed to move from Postgres to an OLAP database but didn’t know where to start. I eventually built abstractions around Clickhouse: My application code called an insert() function but in the background I had to stand up Kafka for streaming, bulk loading, DB drivers, Clickhouse configs, and manage schema changes.<p>This was all a big distraction when all I wanted was to save data and get it back. So I decided to build a better developer experience around it. The software is open-source: <a href="https://github.com/scratchdata/ScratchDB">https://github.com/scratchdata/ScratchDB</a> and and the paid offering is a hosted version: <a href="https://www.scratchdb.com/">https://www.scratchdb.com/</a>.<p>It's called “ScratchDB” because the idea is to make it easy to get started from scratch. It’s a massively simpler abstraction on top of Clickhouse.<p>ScratchDB provides two endpoints [1]: one to insert data and another to query. When you send any JSON, it automatically creates tables and columns based on the structure [2]. Because table creation is automated, you can just start sending data and the system will just work [3]. It also means you can use Scratch as any webhook destination without prior setup [4,5]. When you query, just pass SQL as a query param and it returns JSON.<p>It handles streaming and bulk loading data. When data is inserted, I append it to a file on disk, which is then bulk loaded into Clickhouse. The overall goal is for the platform to automatically handle managing shards and replicas.<p>The whole thing runs on regular servers. Hetzner has become our cloud of choice, along with Backblaze B2 and SQS. It is written in Go. From an architecture perspective I try to keep things simple - want folks to make economical use of their servers.<p>So far ScratchDB has ingested about 2 TB of data and 4,000 requests/second on about $100 worth of monthly server costs.<p>Feel free to download it and play around - if you’re interested in this stuff then I’d love to chat! Really looking for feedback on what is hard about analytical databases and what would make the developer experience easier!<p>[1] <a href="https://scratchdb.com/docs">https://scratchdb.com/docs</a><p>[2] <a href="https://scratchdb.com/blog/flatten-json/">https://scratchdb.com/blog/flatten-json/</a><p>[3] <a href="https://scratchdb.com/blog/scratchdb-email-signups/">https://scratchdb.com/blog/scratchdb-email-signups/</a><p>[4] <a href="https://scratchdb.com/blog/stripe-data-ingest/">https://scratchdb.com/blog/stripe-data-ingest/</a><p>[5] <a href="https://scratchdb.com/blog/shopify-data-ingest/">https://scratchdb.com/blog/shopify-data-ingest/</a>