hamilton

you’d just built it yourself. It seems like it’s just sending a JSON message over a queue or HTTP API and the worker receives it and runs the task. Maybe it’s way harder than I’m envisioning (but I don’t think so because I’ve already written most of it). I guess that’s one thing I’m not clear on with Bruin, can I run workers if different physical locations and have them carry out the tasks in the right order? Or is this more of a centralized thing (meaning even if its K8s or Dask or Ray, those are all run in a cluster which happens to be distributed, but they’re all machines sitting in the same subnet, which isn’t the definition of a “distributed task” I’m going for. [1] https://github.com/DAGWorks-Inc/hamilton

Asset/transform catalog, e.g. search & find if feature transforms/metrics/datasets/models exist and where they’re used. While the UI currently only self-populates for Hamilton dataflows, we’re looking to expand to other frameworks (we’d love your feedback!). Check out the following video for an overview: https://www.youtube.com/watch?v=0VIVSeN7Ij8, as well as the documentation: https://hamilton.dagworks.io/en/latest/concepts/ui/. We’re looking for feedback/adopters – feel free to reach out if you have any questions!

rs and used printlines to debug. We found that everyone wanted the ability to pull up the state of an application at a given point, poke at it to debug/tweak code, and use for later testing/evaluation. People integrating with LLMOps tools fared slightly better, but these tend to focus solely on API calls to test & evaluate prompts, and left the problem of logically modeling/checkpointing unsolved. Having platform tooling backgrounds, we felt that a good abstraction would help improve the experience. These problems all got easier to think about when we modeled applications a state machines composed of “actions” designed for introspection (for more read https://blog.dagworks.io/p/burr-develop-stateful-ai-applicat...). We don’t want to limit what people can write, but we do want to constrain it just enough that the framework provides value and doesn’t get in the way. This led us to design Burr with the following core functionalities: 1. BYOF. Burr allows you to bring your own frameworks/delegate to any python code, like LangChain, LlamaIndex, Hamilton, etc. inside of “actions”. This provides you with the flexibility to mix and match so you’re not limited. 2. Pluggability. Burr comes with APIs to allow you to save/load (i.e. checkpoint) application state, run custom code before/after action execution, and add in your own telemetry provider (e.g. langfuse, datadog, DAGWorks, etc.). 3. UI. Burr comes with its own UI (following the python batteries included ethos) that you can run locally, with the intent to connect with your development/debugging workflow. You can see your application as it progresses and inspect its state at any given point. The above functionalities lend themselves well to building many types of applications quickly and flexibly using the tools you want. E.g. conversational RAG bots, text based games, human in the loop workflows, text to SQL bots, etc. Start with LangChain and then easily transition to your custom code or another framework without having to rewrite much of your application. Side note: we also see Burr as useful outside of interactive GenAI/LLMs applications, e.g. building hyper-parameter optimization routines for chunking and embeddings & orchestrating simulations. We have a swath of improvements planned. We would love feedback, contributions, & help prioritizing. Typescript support, more ergonomic UX + APIs for annotation and test/eval curation, as well as integrations with common telemetry frameworks and capture of finer grained information from frameworks like LangChain, LlamaIndex, Hamilton, etc… Re: the name Burr, you may recognize us as the authors of Hamilton (github.com/dagworks-inc/hamilton), named after Alexander Hamilton (the creator of the federal reserve). While Aaron Burr killed him in a duel, we see Burr being a complement, rather than killer to Hamilton ! That’s all for now. Please don’t hesitate to open github issues/discussions or join our discord https://discord.gg/6Zy2DwP4f3 to chat with us there. We’re still very early and would love to get your feedback!

ing the application? There's no right answer, other than "it depends". To that end - we've come up with a post showing how one might use Hamilton (https://github.com/dagWorks-Inc/hamilton) to easily create a workflow to ingest data into a vector database that I think has a great production story. https://open.substack.com/pub/dagworks/p/building-a-maintain... Note: Hamilton can cover your MLOps as well as LLMOps needs; you'll invariably be connecting LLM applications with traditional data/ML pipelines because LLMs don't solve everything -- but that's a post for another day.