homelab/stack
1
0
Fork 0
Code Issues 275 Pull Requests 2 Actions Packages Projects 1 Releases Wiki Activity

llm: ollama compose service + model bake-off #564

New Issue
Closed
opened 2026-07-16 19:26:07 +00:00 by kert · 1 comment
kert commented 2026-07-16 19:26:07 +00:00
Owner
Copy Link

Stand up Ollama as a compose service (nvidia runtime, like notebooks/zotero) and pick models.

Scope

  • ollama service: nvidia runtime, model volume, healthcheck, OLLAMA_KEEP_ALIVE idle unload so the shared 3060 frees VRAM
  • bake off embedding models: nomic-embed-text vs bge-m3 (retrieval quality on a comment sample, dims, speed)
  • bake off instruct models for tagging with per-host sizing: 3060 12GB (8B Q4 floor) / 4090 24GB / 5080 16GB
  • record decisions in the spec

Acceptance

  • service healthy in compose; models pull on first use; VRAM released after idle
  • spec updated with chosen models + eval numbers

Spec: docs/superpowers/specs/2026-07-16-llm-module-design.md

Stand up Ollama as a compose service (nvidia runtime, like notebooks/zotero) and pick models. **Scope** - [ ] `ollama` service: nvidia runtime, model volume, healthcheck, `OLLAMA_KEEP_ALIVE` idle unload so the shared 3060 frees VRAM - [ ] bake off embedding models: nomic-embed-text vs bge-m3 (retrieval quality on a comment sample, dims, speed) - [ ] bake off instruct models for tagging with per-host sizing: 3060 12GB (8B Q4 floor) / 4090 24GB / 5080 16GB - [ ] record decisions in the spec **Acceptance** - service healthy in compose; models pull on first use; VRAM released after idle - spec updated with chosen models + eval numbers Spec: `docs/superpowers/specs/2026-07-16-llm-module-design.md`
kert added this to the P33: LLM Foundation — Ollama, pgvector, embedding index milestone 2026-07-16 19:26:07 +00:00
kert added the llminfra labels 2026-07-16 19:26:07 +00:00
kert commented 2026-07-17 19:37:20 +00:00
Author
Owner
Copy Link

Done in P33 — merged to main as 14d279b (branch llm-p33). Pilot docket CMS-2017-0092 indexed end-to-end with exact search; full test gate green at 99.75%.

Done in P33 — merged to main as 14d279b (branch llm-p33). Pilot docket CMS-2017-0092 indexed end-to-end with exact search; full test gate green at 99.75%.
kert closed this issue 2026-07-17 19:37:20 +00:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
api
REST API (FastAPI)
 auth
Authentication and authorization
 bib
Bibliography, Zotero, citations
 ci
CI/CD pipelines and Woodpecker plugins
 cli
CLI commands and UX
 cloud
Cloud provider abstraction (AWS, GCP, Azure, self-hosted)
 config
Configuration and wiring
 data
Data loading, CCLF, BCDA, seeds
 databricks
Databricks jobs and deployment
 docs
Documentation and generated references
 image:api
image:docs
image:mc
image:notebooks
image:zotero
infra
lakehouse
Nessie, Polaris, Trino, Iceberg
 llm
llm module — local RAG over comments + Zotero corpus
 notebooks
marimo notebook errors (auto-filed by nb-watcher/nb-integration)
 packaging
Python packaging, optional deps, build system
 pfs
pipeline
Pipeline execution and validation
 pipeline:ci
pipeline:deploy
pipeline:harden
pipeline:infra-ci
pipeline:rebuild-all
pipeline:release
qpp
quality
Testing, coverage, error handling
 step:build
step:deploy
step:hadolint
step:lint
step:publish
step:scan
step:test
step:validate
styles
Charts, figures, visual theming
 tree
Project directory structure and file organization
No Label infra llm
Milestone
No items
No Milestone P33: LLM Foundation — Ollama, pgvector, embedding index
Projects
Clear projects
No project
Assignees
Clear assignees
kert renovate-bot
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: homelab/stack#564
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?