[FIX] Call MCP tools with audio as inputs#1998
Open
frascuchon wants to merge 3 commits intohuggingface:mainfrom
Open
[FIX] Call MCP tools with audio as inputs#1998frascuchon wants to merge 3 commits intohuggingface:mainfrom
frascuchon wants to merge 3 commits intohuggingface:mainfrom
Conversation
Collaborator
|
Did you try locally? because for audio upload to work a model needs to be configured with audio MIME types which is not the case today. |
Author
|
Hi. Yes, I've tried locally. This PR attempts to address only the issue that occurs when calling an MPC tool with an audio file URL. Currently, the tool call is failing due to an unexpected input format. I did not work with multi-modal models. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
When calling a configured Gradio MCP server tool that has audio references (URLs), the tool call constantly fails due to an input format issue. This PR handles audio inputs to allow calling remote Gradio MCP tools with referred audio URLs (direct audio file uploading is not implemented)
Additionally, this PR allows configuring the default MCP tool timeout by environment variable.