Skip to content

feat(lore): raise memory limit to 2G for transformer NER #17

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
amitpaz1 merged 1 commit into from
Jul 3, 2026
Merged

feat(lore): raise memory limit to 2G for transformer NER #17

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 8 additions & 1 deletion docker-compose.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,7 @@ services:
- JWT_SECRET=${JWT_SECRET:?set JWT_SECRET in .env (copy from .env.example)}
- AGENTGATE_URL=http://agentgate:3002
- LORE_ENABLED=true
- LORE_MODE=remote
- LORE_API_URL=http://lore:8765
- LORE_API_KEY=${LORE_API_KEY:?set LORE_API_KEY in .env (copy from .env.example)}
volumes:
Expand Down Expand Up @@ -96,6 +97,10 @@ services:
# stack is usable without a manual POST /v1/org/init. MUST be the same
# value AgentLens uses to call Lore (shared .env var).
- LORE_API_KEY=${LORE_API_KEY:?set LORE_API_KEY in .env (copy from .env.example)}
# spaCy model for graph entity extraction. Default en_core_web_trf
# (transformer NER, best quality — needs ~1.5GB RAM, see limit below).
# Dial down to en_core_web_lg or en_core_web_sm for a smaller footprint.
- LORE_GRAPH_SPACY_MODEL=${LORE_GRAPH_SPACY_MODEL:-en_core_web_trf}
volumes:
- lore-data:/app/data
networks:
Expand All @@ -113,7 +118,9 @@ services:
deploy:
resources:
limits:
memory: 256M
# transformer NER (en_core_web_trf) loads torch + RoBERTa (~1.5GB).
# Lower to 512M if LORE_GRAPH_SPACY_MODEL is set to en_core_web_sm/lg.
memory: 2G

lore-db:
image: pgvector/pgvector:pg16
Expand Down
Loading