Better proc group logging and concurrency (#810)

- Silence pika, cassandra etc. logging at INFO (too much chatter) 
- Add per processor log tags so that logs can be understood in
  processor group.
- Deal with RabbitMQ lag weirdness
- Added more processor group examples
This commit is contained in:
cybermaggedon 2026-04-15 14:52:01 +01:00 committed by GitHub
parent ce3c8b421b
commit 2bf4af294e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
20 changed files with 1021 additions and 647 deletions

View file

@ -0,0 +1,31 @@
# Embeddings. Memory-hungry — fastembed loads an ML model at startup.
# Keep isolated from other groups so its memory footprint and restart
# latency don't affect siblings.
_defaults: &defaults
pubsub_backend: rabbitmq
rabbitmq_host: localhost
log_level: INFO
processors:
- class: trustgraph.embeddings.fastembed.Processor
params:
<<: *defaults
id: embeddings
concurrency: 1
- class: trustgraph.embeddings.document_embeddings.Processor
params:
<<: *defaults
id: document-embeddings
- class: trustgraph.embeddings.graph_embeddings.Processor
params:
<<: *defaults
id: graph-embeddings
- class: trustgraph.embeddings.row_embeddings.Processor
params:
<<: *defaults
id: row-embeddings