Feat/web chat multimodal#178
Merged
Merged
Conversation
Axum's DefaultBodyLimit is 2 MB. A base64-encoded image or audio clip on /api/chat easily exceeds that (base64 inflates ~33%), so anything beyond a small thumbnail returned `413: Failed to buffer the request body: length limit exceeded`. The Windows test slipped through only because the sample image was ~175 KB; a normal photo trips it immediately. Apply DefaultBodyLimit::max(64 MB) to both the API and UI routers — large enough for images and reasonable audio clips, still bounded against abuse.
Promote the multimodal MVP to the 0.6.0 release and document it.
* engine/Cargo.toml: 0.6.0-beta.8 → 0.6.0.
* README:
- "What's ready today" table: Engine → v0.6.0; new Multimodal row
(vision validated on Linux + Windows CUDA, audio experimental/CLI);
Chat UI gains image attachment.
- Engine key features: add the multimodal bullet.
- New "Multimodal: vision + audio" subsection with CLI + Chat UI usage,
plus an honest scope note (vision solid; audio experimental upstream;
multimodal loads sequential; web UI = images only for now; Q4 quality
bounds; Linux libnccl.so.2 dependency; vendored llama-cpp-rs pre-release).
- Roadmap Phase 1: mark multimodal shipped; add planned embeddings
endpoint for Ollama/OpenAI API parity.
Honest status: vision is runtime-validated on Linux + Windows CUDA (image
OCR + scene description, Chat UI and CLI). Audio understanding works via the
CLI but is experimental upstream and is not yet wired into the web UI.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
No description provided.