[HN Gopher] Designing Pareto-optimal RAG workflows with syftr
___________________________________________________________________
Designing Pareto-optimal RAG workflows with syftr
Author : roma_glushko
Score : 49 points
Date : 2025-05-28 14:01 UTC (3 days ago)
(HTM) web link (www.datarobot.com)
(TXT) w3m dump (www.datarobot.com)
| roma_glushko wrote:
| A new OSS framework uses multi-objective Bayesian Optimization to
| efficiently search for Pareto-optimal RAG workflows, balancing
| cost, accuracy, and latency across configurations that would be
| impossible to test manually.
| roma_glushko wrote:
| Useful links:
|
| Github: https://github.com/datarobot/syftr
|
| Paper: https://arxiv.org/abs/2505.20266
| diabolicalrobot wrote:
| I am a member of the syftr team. Please feel free to ask
| questions.
| djoldman wrote:
| Given section A7 in your paper:
| https://arxiv.org/pdf/2505.20266
|
| ...would it be accurate to say that syftr finds Pareto-optimal
| choices across cost, accuracy, and latency, where accuracy is
| decided by an LLM whose assessments are 90% correlated to that
| of human labelers?
|
| Are there 3 objectives: cost, accuracy, and latency or 2: cost
| and accuracy?
| andriyvel wrote:
| looks interesting!
| jstummbillig wrote:
| and exhausting.
| charcircuit wrote:
| It sounds impossible to be paretooptimal for complicated
| problems. How do you know GPT-4o-mini would be optimal. I feel
| like there is always room on the table for a potential
| GPT-5o-mini to be more optimal. The solution space of possible
| gen ai models is gigantic, so we can only improve our solution
| over time and never find the most optimal one.
| brianbelljr wrote:
| Yes, maybe theoretically. Practically though you will have to
| ship your agent with the LLMs that are available today and you
| will need to pick one. I don't think the authors were trying to
| solve for like "best forever",probably wasn't their intent. For
| that I think you would need some kind of proof which sort of
| says that some kind of theoretical maximum is reached, and a
| proof like that is not a thing in _most_ applied computer
| science fields.
| simianwords wrote:
| Interesting but I'm a bit lost. You are optimising but how do you
| know the ground truth of "good" and "bad"? Do you manually run
| the workflow and then decide based on a predefined metric?
|
| Or do you rely on generic benchmarks?
| viraptor wrote:
| https://github.com/datarobot/syftr/blob/main/docs/datasets.m...
|
| You need custom QA pairs for custom scenarios.
___________________________________________________________________
(page generated 2025-05-31 23:00 UTC)