[HN Gopher] Show HN: Truss - Serve any ML model without boilerpl...
___________________________________________________________________
Show HN: Truss - Serve any ML model without boilerplate code
Author : philipkiely
Score : 56 points
Date : 2022-07-29 15:06 UTC (7 hours ago)
(HTM) web link (github.com)
(TXT) w3m dump (github.com)
| gorg93 wrote:
| Looks interesting, what if I need to write some logic (pre/post
| prediction) in the prediction server?
| b10_bola wrote:
| Every time that you make a truss to package your model, you can
| add custom pre/post processing to every request/response. We've
| done our best to document it.
| https://truss.baseten.co/reference/structure#model
| https://truss.baseten.co/develop/processing
|
| Take a look at `{truss_name}/model/model.py` to add the code.
|
| Please open up an issue or PR if you think we can improve on
| the documentation!
| jphoward wrote:
| This is likely to share its name with the next Prime Minister of
| the UK...
| ricklamers wrote:
| In this category I'm a big fan of
| https://github.com/bentoml/BentoML
|
| What I like about it is their idiomatic developer experience. It
| reminds me of other Pythonic frameworks like Flask and Django in
| a good way.
|
| I have no affiliation with them whatsoever, just an admirer.
| philth wrote:
| Big fan of projects like BentoML, the whole ML space is powered
| by some truly great projects. What we've tried to do with truss
| is create an experience that is optimizing for simplicity and
| universality. Our roadmap begins to deviate away from projects
| like BentoML, and so creating truss was very much motivated by
| the need to continue this mindset as we march down through that
| roadmap.
|
| context: I am one of the contributors
| d136o wrote:
| Superb product and team.
|
| Worth looking into if you've done any engineering work around
| deploying ML models as a or within a service.
| 0xferruccio wrote:
| This looks promising. It feels like for non ML engineers it's
| very hard to figure out how to use models as part of vanilla CRUD
| codebase.
|
| For instance in a Rails app the ML model services would probably
| be served as a completely external service API generated with
| something like Truss wrapped in a service class that just exposes
| the outputs and handles errors/input validation!
___________________________________________________________________
(page generated 2022-07-29 23:01 UTC)