monogon VS haystack

It's somewhere in my git stack :).

Until I get to publishing it, the proto/gRPC definitions for node management are a good enough start: https://github.com/monogon-dev/monogon/blob/main/metropolis/...

And the top level API to actually deploy workloads is plain Kubernetes.

Monogon, a fully remote, self-funded and engineer-led technology company, is hiring software engineers to work on Metropolis, an open source [1], secure, distributed cluster operating system based on Linux and Kubernetes.

Metropolis runs on a fleet of bare metal or cloud machines and provides users with a hardened, production ready Kubernetes - without the overhead of traditional Linux distributions or configuration management systems. It does away with the scripting/YAML duct tape and configuration drift inherent to traditional deployments, and instead provides a stable, API-driven, secure and vendor-lock-in-free platform for companies to build their products upon.

We're looking for senior candidates who can design, implement and verify complex systems that will make up part of Metropolis. We offer a kind and honest work environment in which we prioritize quality over quantity. You'll be the fourth member of a team working on an ambitious, industry-challenging product.

Our ideal candidate is a generalist with deeper knowledge in one or more of the following areas:

- Distributed systems;

- Software engineering of systems built to last;

- Security engineering, especially experience with secure boot chains;

- Low-level programming and debugging (C, Linux Kernel, …);

- Kubernetes, especially practical experience of running bare-metal production deployments;

- Platform development, ie. running a 'Company A' style infrastructure/DevOps team [2].

Our codebase is mostly Go (including pid1!), so knowledge of the language is a plus, but not a requirement (given the seniority of the position, we expect any candidate to be able to ramp up on Go within a few weeks).

To get in touch, email me at at nexantic.com.

[1] - https://github.com/monogon-dev/monogon

[2] - https://rachelbythebay.com/w/2020/05/19/abc/

- Platform development, ie. running a 'Company A' style infrastructure/DevOps team [2].

Our codebase is mostly Go (including pid1!), so knowledge of the language is a plus, but not a requirement (given the seniority of the position, we expect any candidate to be able to ramp up on Go within a few weeks).

To get in touch, email me at at nexantic.com.

[1] - https://github.com/monogon-dev/monogon

I was confused for a bit but there is no relation to https://haystack.deepset.ai/

View on GitHub

4. Haystack by Deepset | Github | tutorial

Haystack can be classified as an end-to-end framework for building applications powered by various NLP technologies, including but not limited to generative AI. While it doesn't directly focus on building generative models from scratch, it provides a robust platform for:

But if you want an API that you can use to develop your own flow, Haystack from Deepset could be worth a look.

Haystack for production. We cannot afford breaking changes in our production apps. Its stable, documentation is excellent and did I mention its' STABLE!??

I recently conducted some experiments with Llama2 and Haystack (https://github.com/deepset-ai/haystack), the NLP/LLM framework.

The notebook can be helpful for those trying to load Llama2 on Colab.

1) Installed Transformers from the main branch (and other libraries)