feat: document llmman as a local AI server alternative to Ollama - #8990
Open
ericcurtin wants to merge 1 commit into
Open
ericcurtin wants to merge 1 commit into
ericcurtin wants to merge 1 commit into
Conversation
Contributor
Reviewer's guide (collapsed on small PRs)Reviewer's GuideThis documentation-focused PR exposes llmman as a selectable Ollama-compatible server through the existing Local AI configuration, adds an explicit warning about its missing embedding endpoint, and updates user-facing provider text without introducing a second implementation. File-Level Changes
Tips and commandsInteracting with Sourcery
Customizing Your ExperienceAccess your dashboard to:
Getting Help
|
|
|
![sourcery-ai[bot]](https://avatars.githubusercontent.com/in/48477?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Hey - I've found 1 issue
Prompt for AI Agents
Please address the comments from this code review:
## Individual Comments
### Comment 1
<location path="frontend/appflowy_flutter/lib/workspace/application/settings/ai/ollama_setting_bloc.dart" line_range="236" />
<code_context>
content: serverUrl,
- hintText: 'http://localhost:11434',
+ hintText:
+ '$kDefaultOllamaServerUrl (Ollama) or $kDefaultLlmmanServerUrl (llmman)',
settingType: SettingType.serverUrl,
),
</code_context>
<issue_to_address>
**issue (broader_impact):** Pointing the setting at llmman does not provide a usable chat-only configuration: `update_local_ai_setting` validates both the chat and embedding models through `/api/tags`, and the embedding scheduler continues to call Ollama `/api/embed`. A llmman setup without the required embedding model is rejected when the URL is saved, while a setup that passes model validation fails when indexing or search invokes embeddings, so the UI hint and documentation present llmman as a drop-in without explaining that the existing Local AI path can block or fail the entire configuration.
**Triggers:** When a user configures llmman with its supported chat models and attempts to save the setting or use local AI search/indexing.
**Suggested fix:** Either allow a chat-only llmman configuration without requiring the embedding model, or explicitly state in the UI that llmman cannot currently be used for AppFlowy Local AI until the embedding path is implemented.
```suggestion
'$kDefaultOllamaServerUrl (Ollama); llmman cannot currently be used for AppFlowy Local AI until the embedding path is implemented',
```
</issue_to_address>Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.
| content: serverUrl, | ||
| hintText: 'http://localhost:11434', | ||
| hintText: | ||
| '$kDefaultOllamaServerUrl (Ollama) or $kDefaultLlmmanServerUrl (llmman)', |
Contributor
There was a problem hiding this comment.
issue (broader_impact): Pointing the setting at llmman does not provide a usable chat-only configuration: update_local_ai_setting validates both the chat and embedding models through /api/tags, and the embedding scheduler continues to call Ollama /api/embed. A llmman setup without the required embedding model is rejected when the URL is saved, while a setup that passes model validation fails when indexing or search invokes embeddings, so the UI hint and documentation present llmman as a drop-in without explaining that the existing Local AI path can block or fail the entire configuration.
Triggers: When a user configures llmman with its supported chat models and attempts to save the setting or use local AI search/indexing.
Suggested fix: Either allow a chat-only llmman configuration without requiring the embedding model, or explicitly state in the UI that llmman cannot currently be used for AppFlowy Local AI until the embedding path is implemented.
Suggested change
| '$kDefaultOllamaServerUrl (Ollama) or $kDefaultLlmmanServerUrl (llmman)', | |
| '$kDefaultOllamaServerUrl (Ollama); llmman cannot currently be used for AppFlowy Local AI until the embedding path is implemented', |
llmman (https://github.com/llmmanorg/llmman) serves the Ollama API on port 17434, so Local AI already works against it by changing the server url, but nothing in the app made that discoverable. - Add kDefaultOllamaServerUrl / kDefaultLlmmanServerUrl and show both in the server url hint. - Note on LocalAISetting.ollama_server_url that any Ollama-API server works; mention llmman next to Ollama in the en-US settings text.
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.
Adds llmman, a local model runner that serves the Ollama API on port 17434, as a documented alternative to Ollama for Local AI.
ollama_setting_bloc.dart: addkDefaultOllamaServerUrl/kDefaultLlmmanServerUrland show both in the server-url hint. The existingOllamaSettingBlocand RustLocalAIControllerare reused unchanged, so there is no second provider code path.controller.rs: doc comment onLocalAISetting.ollama_server_urlnoting any Ollama-API server works.en-US.json: mention llmman alongside Ollama inaiSettingsDescription(source locale only; others are managed via Fink).Testing:
rustfmt --check(reporustfmt.toml) oncontroller.rsclean;en-US.jsonparses;dart formatleaves the edited lines unchanged. Not run:flutter analyze/flutter test(no pinned Flutter SDK locally).PR Checklist
Summary by Sourcery
Support llmman as an alternative Ollama-compatible local AI server.
New Features:
Enhancements:
Documentation: