Show HN: Poozle – open-source Plaid for LLMs https://ift.tt/CeNyARq

Show HN: Poozle – open-source Plaid for LLMs Hi HN, We’re Harshith, Manoj, and Manik Poozle ( https://ift.tt/oqBK0nw ) provides a single API that helps businesses achieve accurate LLM responses by providing real-time customer data from different SAAS tools (e.g Notion, Salesforce, Jira, Shopify, Google Ads etc). Why we built Poozle: As we were talking to more AI companies who need to integrate with their customers’ data we realised managing all SAAS tools data and keeping them up-to-date is a huge infra of ETL, Auth management, Webhooks and many more things before you take it to production. It struck us – why not streamline this process and allow companies to prioritise their core product? How it works: Poozle makes user authorization seamless using our drop-in component (Poozle Link) and handles both API Key and OAuth dance. Post-authentication developers can use our Unified model to fetch data to their LLMs (no need to sync data separately and then normalise at your end). Poozle keeps data updated in real time while giving you options to choose sync intervals. Even if the source doesn’t support webhooks, we’ve got you covered. Currently, we support Unified API for 3 categories - Ticketing, Documentation and Email. You can watch a demo of Poozle ( https://ift.tt/zctsT7f)... We just got started a month ago and we’re eager to get feedback and keep building. Let us know what you think in the comments : ) https://ift.tt/oqBK0nw August 18, 2023 at 11:57PM

Show HN: AI chatbot to reduce support costs by 80% https://ift.tt/3jTPhV0

Show HN: AI chatbot to reduce support costs by 80% Hey, HN! We have developed a bot for technical support. The task was set to reach the next level of chatbots. The thing is that nowadays bots too often redirect customers to support staff when a question was not found in the bot's presets database or the customer requires some kind of interaction with the company (for example, wants to buy a product). We have succeeded in reducing the percentage of situations where the bot transfers the customer to the operator. At the same time, it can still ask for help from a real person if the case requires it. 1. the bot is capable of answering complex questions that require analyzing the company's knowledge base (especially the technical part). 2. the possibility to leave a request for some action was introduced. For example, a customer can leave a request for connection to a tariff plan . An example of such a bot for the fictitious company BananaCom is given on the site, you can test it. After the request is made, the company receives the necessary information. Of course, if the client really wants to talk to an employee, he will be transferred to the employee. When to transfer to employees is a matter to be discussed with the individual company, so now a bot on the site will try to answer all your questions. We did a lot of work before the product was ready, we can't reveal all the secrets, but for connoisseurs we'll give you a hint: https://ift.tt/Wg40zMU https://ift.tt/sFtLx0c August 18, 2023 at 11:47PM

Show HN: ChatGPT: craft the right question, unlock the best answer https://ift.tt/Lgwn6kF

Show HN: ChatGPT: craft the right question, unlock the best answer https://ift.tt/zEUb2dv August 18, 2023 at 05:01PM

Show HN: An Open-Source Collaborative Database Development Tool https://ift.tt/1kgx2RD

Show HN: An Open-Source Collaborative Database Development Tool A couple of years ago, we had an interesting idea. When a development team within an organization consists of around 10 members or fewer, controlling the risks associated with database changes might be achieved through trust and real-time communication. However, as the team grows, the responsibilities within the team become more specialized. Imagine a scenario where different branches of the business exist, each with its own set of developers, team leads, testers, testing leads, DBAs, and more. Relying solely on traditional communication methods becomes increasingly challenging when it comes to managing change risks. Envision a platform where a change request goes through a sequence of checks: it's first reviewed by colleagues familiar with the business, then approved by the business lead, followed by scrutiny from the database lead, and finally assessed for security by the security lead. Does this approach effectively control the risk associated with that change when it's executed? In 2019, we embarked on building the first piece of this puzzle: ODC. Fast forward to today, after more than three years of development, ODC has evolved from a specialized developer tool designed for OceanBase (OB) into an enterprise-grade collaborative control platform, with plans to support multiple data sources. And today, we are thrilled to announce that we are open-sourcing our project. You can find the entire four-year code history on GitHub ( https://ift.tt/8FsTp3N ). We're excited to hear your thoughts on this concept and whether you identify any potential challenges or opportunities that lie ahead. Your insights will play a crucial role in shaping the future of this project. Looking forward to your feedback! https://ift.tt/8FsTp3N August 18, 2023 at 04:06PM

Show HN: Kantankanban – A CLI to track to-do's, custom lists, and more https://ift.tt/29T5xGt

Show HN: Kantankanban – A CLI to track to-do's, custom lists, and more https://ift.tt/xoEuipl August 18, 2023 at 12:13PM

Show HN: Clean Stash – Start Organizing Your Screenshots (Testflight App) https://ift.tt/eyIKa9f

Show HN: Clean Stash – Start Organizing Your Screenshots (Testflight App) Hi HN! Today I'm launching Clean Stash - an iPhone app to organize your screenshots, as an open beta (Testflight). Here's why I built it: I take a lot of screenshots. Like a lot, and of all different use cases. Sometimes of smart marketing copy that I want to use myself, a visual I want to use in a future mood board, a sneaker I want to buy, a linkedIn post I want to quickly reference, places I want to travel...you get the point. In reality, these get lost in my phone's "Screenshots" folder. Now over 2,3k of them. I've even found myself taking screenshots of screenshots only to have them surface as more recent as I scroll. I probably have more screenshots than pictures of my kids (pls don't judge). I wanted a keep all these screenshots in one place, and given back to me in an actionable way. That's why I spent a few weeks building a solution, and today I think it's ready enough for you to use. I'd love to hear how you find this app useful, and what you'd like to have next. Feel free to add your comments below. https://ift.tt/GY0eUWu August 17, 2023 at 03:51PM

Show HN : Low code cloud document database https://ift.tt/xTrSvBR

Show HN : Low code cloud document database Low code cloud document database https://slyce-io.co.uk/ August 17, 2023 at 03:43PM

Show HN: Interactive exercises for GNU grep, sed and awk https://ift.tt/W9lYgOy

Show HN: Interactive exercises for GNU grep, sed and awk Hello! For the past few months, I've been using a Python framework called Textual to create TUI apps for interactive exercises. Released the app for GNU awk earlier today, so thought I'd create a post here. If you already know how to manage Python packages, you can use the following command to get all the three apps: pip install grepexercises sedexercises awkexercises `pipx` should also work, but I haven't tested it. The GitHub repo has the source code as well as more detailed installation instructions. You can use alternative CLI tools to solve these exercises as well. For example, Perl instead of GNU awk or ripgrep instead of GNU grep and so on. Hope you find these TUI apps useful. I'd highly appreciate your feedback. Happy learning :) https://ift.tt/0F6BmUt August 17, 2023 at 03:43PM

Show HN: I resurrected one of the top dead Show HNs https://ift.tt/DYSr14m

Show HN: I resurrected one of the top dead Show HNs OneView was first posted to HN in 2017, but died sometime around late 2019. Using the web archive I cobbled together something that works. According to this[0], oneview is the #5 top dead show hn. [0] https://ift.tt/c74B1pl... https://ift.tt/6efxIOP August 17, 2023 at 08:26PM

Show HN: Strich – Barcode scanning for web apps https://ift.tt/AHpBEI9

Show HN: Strich – Barcode scanning for web apps Hi, I'm Alex - the creator of STRICH ( https://strich.io ), a barcode scanning library for web apps. Barcode scanning in web apps is nothing new. In my previous work experience, I've had the opportunity to use both high-end commercial offerings (e.g. Scandit) and OSS libraries like QuaggaJS or ZXing-JS in a wide range of customer projects, mainly in logistics. I became dissatisfied with both. The established commercial offerings had five- to six-figure license fees and the developer experience was not always optimal. The web browser as a platform also seemed not to be the main priority for these players. The open source libraries are essentially unmaintained and not suitable for commercial use due to the lack of support. Also the recognition performance is not enough for some cases - for a detailed comparison see https://ift.tt/A6s1hx9 Having dabbled a bit in Computer Vision topics before, and armed with an understanding of the market situation, I set out to build an alternative to fill the gap between the two worlds. After almost two years of on-and-off development and 6 months of piloting with a key customer, STRICH launched at beginning of this year. STRICH is built exclusively for web browsers running on smartphones. I believe the vast majority of barcode scanning apps are in-house line of business apps that benefit from distribution outside of app stores and a single codebase with abundant developer resources. Barcode scanning in web apps is efficient and avoids platform risk and unnecessary costs associated with developing and publishing native apps. https://strich.io August 17, 2023 at 06:54PM

Show HN: How to use LLMs to generate accurate SQL for real-world data https://ift.tt/HKxfM2s

Show HN: How to use LLMs to generate accurate SQL for real-world data Hey HN, We are Zain and Ashish, founders of Vanna AI. We recently embarked on an experiment to see if large language models (specifically LLMs) could help in generating SQL queries for real-world datasets. We initially started this project as a web app but realized that it was most useful and had broadest applicability as a Python package since you can then incorporate it into an existing workflow (Jupyter notebook, Slackbot, etc). We've had some good success with customer datasets but we've generally heard a lot of skepticism so we decided to write a paper about the methodology we're using and how various LLMs compare. Let us know if you have any questions or requests. The underlying Python package is open source. There is a server component to store and retrieve metadata but by next week there will be a fully open-source and locally runnable version. Cheers! https://ift.tt/sBSP2iM August 17, 2023 at 05:47PM

Show HN: Rules – Shortcuts Automation Based on Calendar Events https://ift.tt/xRodmnN

Show HN: Rules – Shortcuts Automation Based on Calendar Events Read and thought once too often that "This would be trivial if Calendar Events were triggers for Personal Shortcuts Automations". So decided to create a Mac app for it. The app works similar to Rules in Mail: - Specify some conditions (e.g. Calendar is "Work", Location contains "zoom") - Choose shortcuts to run on events that meet the conditions - you can have multiple actions, each with a different offset and custom input Good to know: - The app can only trigger automations while your Mac is awake (missed actions can be triggered on wake up) - The free version offers full functionality, but is limited to a max of 2 rules. Pro is a one-time purchase - All your data stays on device + no ads or data collection I would appreciate any feedback, especially what automations you might use the app for https://ift.tt/PQEk98i August 17, 2023 at 02:23PM

Show HN: Marqo – Vectorless Vector Search https://ift.tt/KElYeRn

Show HN: Marqo – Vectorless Vector Search Marqo is an end-to-end vector search engine. It contains everything required to integrate vector search into an application in a single API. Here is a code snippet for a minimal example of vector search with Marqo: mq = marqo.Client() mq.create_index("my-first-index") mq.index("my-first-index").add_documents([{"title": "The Travels of Marco Polo"}]) results = mq.index("my-first-index").search(q="Marqo Polo") Why Marqo? Vector similarity alone is not enough for vector search. Vector search requires more than a vector database - it also requires machine learning (ML) deployment and management, preprocessing and transformations of inputs as well as the ability to modify search behavior without retraining a model. Marqo contains all these pieces, enabling developers to build vector search into their application with minimal effort. Why not X, Y, Z vector database? Vector databases are specialized components for vector similarity. They are “vectors in - vectors out”. They still require the production of vectors, management of the ML models, associated orchestration and processing of the inputs. Marqo makes this easy by being “documents in, documents out”. Preprocessing of text and images, embedding the content, storing meta-data and deployment of inference and storage is all taken care of by Marqo. We have been running Marqo for production workloads with both low-latency and large index requirements. Marqo features: - Low-latency (10’s ms - configuration dependent), large scale (10’s - 100’s M vectors). - Easily integrates with LLM’s and other generative AI - augmented generation using a knowledge base. - Pre-configured open source embedding models - SBERT, Huggingface, CLIP/OpenCLIP. - Pre-filtering and lexical search. - Multimodal model support - search text and/or images. - Custom models - load models fine tuned from your own data. - Ranking with document meta data - bias the similarity with properties like popularity. - Multi-term multi-modal queries - allows per query personalization and topic avoidance. - Multi-modal representations - search over documents that have both text and images. - GPU/CPU/ONNX/PyTorch inference support. See some examples here: Multimodal search: [1] https://ift.tt/kW23Eb4... Refining image quality and identifying unwanted content: [2] https://ift.tt/YNfGxM7... Question answering over transcripts of speech: [3] https://ift.tt/7UmAtTY Question and answering over technical documents and augmenting NPC's with a backstory: [4] https://ift.tt/YWq6yQL... https://ift.tt/it82kNa August 16, 2023 at 07:31PM

Show HN: Prompt-Compose.js Use Axioms and Compositions to Build Modular Prompts https://ift.tt/aeFS05G

Show HN: Prompt-Compose.js Use Axioms and Compositions to Build Modular Prompts This JS library provides basic axioms for building and managing GPT prompts. It helps you build small and reusable prompt components and then let you compose them together to build larger ones. https://ift.tt/45swZMu August 16, 2023 at 05:49PM

Show HN: List of public sites blocking ChatGPT Bot https://ift.tt/3xKt5Sf

Show HN: List of public sites blocking ChatGPT Bot Following on from this post ( https://ift.tt/MO0jHRn ), I was intrigued to find which big sites would follow suit, so I started collating a list of them. Interestingly, it's also now being included in codebases by default (like Mastodon). https://ift.tt/sS0gZwR August 16, 2023 at 12:40PM

Show HN: PotterScript – Wizarding world programming language https://ift.tt/jwyLDEh

Show HN: PotterScript – Wizarding world programming language hey everyone, I've build a simple language for learning purposes and I thought it was a funny idea to make it with a Harry Potter theme, hope you like it! https://ift.tt/4jc1nlp August 15, 2023 at 12:46AM

Show HN: Watermelon – Source-available passive documentation search engine https://ift.tt/pqdbsiN

Show HN: Watermelon – Source-available passive documentation search engine Hey there HN! We're a pair of devs and we are looking to get feedback for our source-available passive documentation search engine. Passive documentation is the code context devs are generating as they talk about code in systems such as GitHub, Slack, Notion and Jira. Our search engine serves both our IDE extension (for individuals) and GitHub app (for teams). As devs we know that there are certain PRs that stay unmerged for weeks or even months, not because of the technical complexity, but because of the debate that they produce around changes in the business logic: "Will this change really improve our metrics?" We know that non-technical stakeholders (managers and designers) can bring a more holistic view to these debates but code review is too technical for them. So we decided to build this with the premise of "let's contextualize devs with business logic". We’re starting with a GitHub app that contextualizes Pull Requests with pieces of related passive documentation. Our big vision is to build a copilot for engineering leaders, starting by automating code review. If we're already indexing passive documentation tied to a new PR, we suspect that we can provide a "first health check" to a PR and say whether or not it's meeting the business requirements. Here's the repo if you want to check it out: https://ift.tt/f53AqtT And here's a blog post explaining why we made our search engine source-available: https://ift.tt/rHKGt1I... Please give us your feedback! Thanks. https://ift.tt/f53AqtT August 14, 2023 at 08:17PM

Show HN: Code-vault, Developers handbook – recipes for BASH, Docker and more https://ift.tt/HiT7sLS

Show HN: Code-vault, Developers handbook – recipes for BASH, Docker and more https://ift.tt/yGRzkoK August 16, 2023 at 03:10AM

Show HN: Lottielab – create and edit animations in the browser https://ift.tt/pFe7L6i

Show HN: Lottielab – create and edit animations in the browser Hello, HN! Today we released Lottielab, a web-based animation tool, to the public as an open beta. Lottielab is a good fit for product animations - small, loopable animations that live in your product or website and typically use the JSON-based Lottie vector animation format. Today, the dominant tool for editing and exporting Lottie animations is Adobe After Effects. AE is a 30-year-old visual effects tool that’s not fit for this purpose, with a steep learning curve and a patchwork of error-prone Lottie export plugins. With Lottielab, we are aiming to reduce the friction of creating and editing product animations by providing an easy-to-use editor with out-of-the-box support for import and export of the Lottie format and many others (GIF/MP4 rendering included, so you're not limited to just Lottie). Feel free to play around with the tool and let me know what you think - I'm here to answer your questions. Happy animating! https://ift.tt/B1otbzl August 16, 2023 at 02:36AM

Show HN: Lottielab – Create product animations in the browser easily https://ift.tt/xY7gdhL

Show HN: Lottielab – Create product animations in the browser easily Hi HN! Today we are releasing Lottielab, a web-based animation tool, to the public as an open beta. The main tool for editing and exporting Lottie animations today is Adobe After Effects, a 30-year-old visual effects tool that’s not fit for this purpose, has a steep learning curve, and requires a patchwork of error-prone plugins. With Lottielab, we are aiming to reduce the friction of creating and editing product animations by providing an easy-to-use editor with out-of-the-box support for import and export of the Lottie format and many others. Feel free to play around with the tool and let me know what you think - I'm here to answer your questions. Happy animating! https://ift.tt/B1otbzl August 15, 2023 at 05:58PM