EtiennePerot
File generation with the run code tool
Is your feature request related to a problem? Please describe. The run code action seems to handle file generation perfectly. The run code tool does not. But there does seem to be some code in the tool to support this? Am I doing something wrong?
Describe the solution you'd like When the run code tool runs, it generates files the same way as the action.
Describe alternatives you've considered Using the action, which works.
You're not doing anything wrong; the tool currently doesn't have this functionality that the function does. The rationale for having it this way in the tool was that the tool is for the LLM itself to use, so any generated files are irrelevant to the user. But it's true that there are use-cases where that rationale does not hold. So this is a valid feature request.
Ah, I was basically using the tool in the same way as what someone would use the action button for. Like "Make me a QR code" and then have it output a QR code in the chat.
Makes sense. I think it is a different and valid use-case, but not sure how to best support it. With Open WebUI's recent "code execution status" UI support, would it be satisfactory if files were shown on the code execution status dialog (which you have to click for), rather than in chat? I ask because showing things directly in the chat also makes them part of the conversation context, which is duplicated tokens for the case of the tool (because the tool's output is already effectively part of the LLM's system message). So it wastes context window space when also displayed in the chat. Alternatively, perhaps this can be introduced as a tool parameter, exposed to the LLM either as a boolean ("show the code output to the user? y/n"), or as a separate tool name ("execute_code_internally" vs "execute_code_visible_to_user").
That would work, yes. I think it might even be better?
There could also perhaps be some integration with the artifacts feature? Though not sure how much that applies or what it actually supports.
I think this functionality would also be amazingly useful for tools and functions.
For example, we have a tool that performs OCR with output as a markdown, html or json file. Sometimes these can be very large making display as an artifact on in the prompt unwieldy.
The ideal output would be to be able to output a download URL in the chat interface
Perhaps the URL could be using the files API endpoint?
I understand the API using the files endpoint is currently files in the RAG database. So if the endpoint was used to make files available as a URL, some sort of differentiated treatment would be required. Perhaps another location could be used as the uploads folder is for RAG, where files are stored, given an ID and made available
