feat: Add vision provider support for multi-modal image recognition#1397
Closed
yufan001 wants to merge 1 commit intoHKUDS:mainfrom
Closed
feat: Add vision provider support for multi-modal image recognition#1397yufan001 wants to merge 1 commit intoHKUDS:mainfrom
yufan001 wants to merge 1 commit intoHKUDS:mainfrom
Conversation
- Add vision provider configuration in schema.py for dedicated vision model API - Update gateway() to initialize vision_provider when vision_model is configured - Enables using different API endpoints for vision vs text-only requests - Supports multi-modal LLMs like qwen3-vl-plus, claude-3, gpt-4-vision Related to issue #223 (Multi-Modal Support: Images, Voice, and Video) This implements Phase 1 (Vision) configuration support for the gateway mode.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
This PR adds vision provider configuration support for multi-modal image recognition in nanobot.
Changes
visionprovider configuration field inconfig/schema.pygateway()function incli/commands.pyto initializevision_providerwhenvision_modelis configuredMotivation
Users may want to use different API providers/endpoints for:
This implementation allows configuring a separate
visionprovider in config.json:{ "providers": { "custom": { "apiKey": "...", "apiBase": "https://dashscope.aliyuncs.com/v1" }, "vision": { "apiKey": "...", "apiBase": "https://apis.iflow.cn/v1" } }, "agents": { "defaults": { "visionModel": "qwen3-vl-plus" } } }Related Issue
Related to #223 (Multi-Modal Support: Images, Voice, and Video)
This implements Phase 1 (Vision) configuration support for the gateway mode, complementing the existing Feishu image download support (commit 49cc0c5).