feat(ai): complete AI stack — Ollama + Open WebUI + SD + Perplexica#313
Open
Problemsolver0070 wants to merge 1 commit intoillbnm:masterfrom
Open
feat(ai): complete AI stack — Ollama + Open WebUI + SD + Perplexica#313Problemsolver0070 wants to merge 1 commit intoillbnm:masterfrom
Problemsolver0070 wants to merge 1 commit intoillbnm:masterfrom
Conversation
- Rewrite stacks/ai/docker-compose.yml with all 4 required services: Ollama (0.3.12), Open WebUI (v0.3.32), Stable Diffusion, Perplexica - Add GPU auto-adaptive deployment via GPU_RUNTIME env var (nvidia/rocm/cpu) using Docker deploy.resources - Add Perplexica AI search engine service - Add Authentik OIDC integration for Open WebUI - Add scripts/detect-gpu.sh for GPU detection and config recommendation - Add stacks/ai/.env.example with all configurable parameters - All services have healthchecks, Traefik labels, proper networking Generated/reviewed with: claude-opus-4-6 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Closes #6 — [BOUNTY $220] AI Stack — 本地 AI 服务
0.3.12) — LLM inference engine with GPU supportv0.3.32) — Chat interface with Authentik OIDCuniversonic/stable-diffusion-webui:9.2.0) — Image generationv1.9.1) — AI-powered search engineGPU_RUNTIME=nvidia|rocm|cpuvia Docker deploy resourcesscripts/detect-gpu.sh— Auto-detects GPU and recommends config.env.example— All tuning params (parallelism, models, secrets)All services have healthchecks, Traefik labels, Authentik middleware, and proper volume mounts.
Test Plan
docker compose configvalidates successfullyGPU_RUNTIME=cpustarts all services without GPUGPU_RUNTIME=nvidiapasses GPU to Ollama and SDdocker exec ollama ollama pull llama3.2succeedshttps://ai.${DOMAIN}https://search.${DOMAIN}Generated/reviewed with: claude-opus-4-6
🤖 Generated with Claude Code
Reviewed/verified with: GPT-5.3 Codex