LLMStack – Self-Hosted, Low-Code Platform to Build AI Experiences
LLMStack is a low-code platform that can be used to build LLM apps, chatbots and integrate AI experiences into existing products/workflows. It comes with everything out of the box that one needs to build LLM apps locally. It can also be used in a multi-tenant setting, making it available for everyone to use in an enterprise. Some highlights of the platform: - Chain multiple LLM models allowing for complex pipelines - Includes a vector database and necessary connectors to help enrich LLM responses with private data - App templates tailored to specific use cases to quickly build LLM apps…
What it does
In the maker’s words, at launch
LLMStack is a low-code platform that can be used to build LLM apps, chatbots and integrate AI experiences into existing products/workflows. It comes with everything out of the box that one needs to build LLM apps locally. It can also be used in a multi-tenant setting, making it available for everyone to use in an enterprise. Some highlights of the platform: - Chain multiple LLM models allowing for complex pipelines - Includes a vector database and necessary connectors to help enrich LLM responses with private data - App templates tailored to specific use cases to quickly build LLM apps in minutes - Collaborative app editing and prompt engineering capabilities - Streaming APIs, Slack and Discord integrations - Multi-tenant ready for enterprise deployments with user management, org level keys etc., - Ability to use local open-source LLMs like Llama2 etc using LocalAI (https://localai.io) Background: We started as a closed source prompt management platform early this year (https://trypromptly.com) and eventually landed as an Enterprise LLM apps platform. In the process, we learned how hard it is to sell a horizontal SaaS platform. That combined with the concerns around data privacy (both with us hosting data as well sending data to model providers like OpenAI), we found a lot of enterprises hesitant to signup for Promptly. We added the ability for the users to host their own vector databases which helped a bit. With the current pace of performance improvements in open source LLMs, enterprises now have the ability to run LLMs entirely locally or in their private clouds without suffering the loss in quality of output. This made us realize we can make Promptly self-hostable so enterprises can have a low-code apps platform on locally running LLMs without sending any data out. LLMStack came out of this realization. Promptly is now powered by LLMStack which is entirely being developed in the open. Anyone can bring up LLMStack locally and have an experience similar to Promptly. We still have paid plans on Promptly for customers who don't want to deal with installations and offer on-prem installation support to enterprises that want to use LLMStack similar to Supabase, Airbyte etc. Our current focus with LLMStack is to make it work really well with open-source models. Happy to answer any questions.
Does the same job
all alternatives →
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, August 2023
the whole month →
Lottielab▲871Create and ship lottie animations to sites and apps faster
Dev tools · 2023 · lottielab.com
- LC
Outlines is a Python library that focuses on text generation with large language models. Brandon and I are not LLM experts and started the project a few months ago because we wanted to understand better how the generation process works. Our original background is probabilistic, relational and symbolic programming. Recently we came up with a fast way to generate text that matches a regex (https://blog.normalcomputing.ai/posts/2023-07-27-regex-guide...). The basic idea is simple: regular expressions have an equivalent Deterministic-Finite Automaton (DFA) representation. We…
AI · 2023 · github.com