model routing: cost/latency ranking with ranked fallback list#849
Open
adilhafeez wants to merge 8 commits intomainfrom
Open
model routing: cost/latency ranking with ranked fallback list#849adilhafeez wants to merge 8 commits intomainfrom
adilhafeez wants to merge 8 commits intomainfrom
Conversation
…urn ranked model list
- MetricsSource::DigitalOceanPricing variant: fetch public DO Gen-AI pricing, normalize as lowercase(creator)/model_id, cost = input + output per million
- cost_metrics endpoint format updated to { "model": { "input_per_million": X, "output_per_million": Y } }
- Startup errors: prefer:cheapest requires cost source, prefer:fastest requires prometheus
- Startup warning: models with no pricing/latency data ranked last
- One-per-type enforcement: digitalocean_pricing; error if cost_metrics + digitalocean_pricing both configured
- cost_snapshot() / latency_snapshot() on ModelMetricsService for startup checks
- Demo config updated to v0.4.0 top-level routing_preferences with cheapest + fastest policies
- docker-compose.yaml + prometheus.yaml + metrics_server.py for demo latency metrics
- Schema and docs updated
…on missing data at request time
adilhafeez
changed the title
…ne in config.yaml
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
routing_preferences(v0.4.0+) with candidate model list andselection_policy/routing/v1/*returns rankedmodels[]array; client usesmodels[0], falls back on 429/5xxselection_policy.prefer:cheapest,fastest,random,nonemodel_metrics_sources:cost_metrics,prometheus_metrics,digitalocean_pricing(public DO catalog withmodel_aliases)fixes #848