feat: add local Ollama VLM input plugin for multimodal visual reasoning#2467
Open
Wanbogang wants to merge 2 commits intoOpenMind:mainfrom
Open
feat: add local Ollama VLM input plugin for multimodal visual reasoning#2467Wanbogang wants to merge 2 commits intoOpenMind:mainfrom
Wanbogang wants to merge 2 commits intoOpenMind:mainfrom
Conversation
Add VLM_Ollama_Local plugin that captures webcam frames and sends them to a locally running Ollama instance (e.g., llava, moondream) for offline visual reasoning without cloud dependency. - Follows existing FuserInput pattern (vlm_local_yolo, vlm_coco_local) - Uses aiohttp to POST base64-encoded frames to Ollama /api/chat - Supports any Ollama multimodal model via config (default: llava) - Gracefully handles camera failures, API errors, and timeouts - 22 tests with 100% coverage Addresses the llava multimodal gap noted in config/ollama.json5
github-actions
bot
added
robotics
Codecov Report✅ All modified and coverable lines are covered by tests. 📢 Thoughts on this report? Let us know! |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adds
VLM_Ollama_Local, a new input plugin for offline visual reasoningusing a locally running Ollama multimodal model (e.g., llava, moondream).
This addresses the multimodal gap noted in
config/ollama.json5wherellavawas listed as a supported model but no visual input plugin existed.Changes
src/inputs/plugins/vlm_ollama_local.py— new plugintests/inputs/plugins/test_vlm_ollama_local.py— 22 tests, 100% coverageUsage