feat: add llmman as a host-native Ollama-API backend - #258
Open
ericcurtin wants to merge 1 commit into
Open
Conversation
llmman (https://github.com/llmmanorg/llmman) is a local model runner serving the Ollama API on host port 17434. Like dmr/mlx/omlx it has no container image, so a Caddy proxy exposes it on the Harbor network, and a webui cross-file registers it as an Ollama connection. Host lifecycle (start/pull) is left to the user to keep the change small.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds llmman, a host-native local model runner that serves the Ollama API (plus OpenAI/Anthropic-compatible ones) on port 17434.
services/compose.llmman.yml+services/llmman/Caddyfile: acaddy:2-alpineproxy on the harbor network forwarding toHARBOR_LLMMAN_UPSTREAM_URL(defaulthttp://host.docker.internal:17434), same pattern asdmr/mlx/omlx;/healthbacks the compose healthcheck.profiles/default.env:HARBOR_LLMMAN_*block (port35080, next free), incl.HARBOR_LLMMAN_INTERNAL_URLfor cross-files.compose.x.webui.llmman.yml+config.llmman.json: register llmman as an Ollama connection in Open WebUI soharbor up webui llmmanlists models fromllmman pull.serviceMetadata.tsentry (org avatar as logo),docs/2.2.27-Backend-llmman.md, README backend list, one.factsentry.harbor llmman start/pull,harbor launch) intentionally not added; users runllmman servethemselves.Testing:
harbor ls/harbor cmd webui llmmanresolve, composeconfigrenders the service and mount,harbor dev lint --compose --rulesclean,caddy validateOK, proxy verified against livellmman serve(/health,/api/tags,/v1/models),tsc --noEmitinapp/exit 0,.factspasses.