Hi, So if I'm understanding correctly, you're not retrieving the text within the PDF from your trigger. Is the PDF scanned? If it's an image-based...

Hi, I believe I can assist with this. The most straightforward solution would be to utilize Gemini Flash 2.5; its reasoning capabilities are quite ben...

What version were you running yesterday when this problem began? I also just realized that downgrading isn't possible on the cloud version. So, that's...

My apologies. I was considering if generating a new AI agent from the node list might resolve the problem. I've encountered some peculiar issues with ...

Could you attempt to rebuild the workflow, or perhaps a test version, within a new workflow?

Just wanted to mention that providing details about the tool and specifying when to invoke it, either within the system prompt or the message prompt, ...

Hi, I'm not entirely sure what you're referring to. Are you perhaps asking about the AI agent node? The input for that node should remain unchange...

Glad to hear it. Also, I recommend reviewing this function calling benchmark. Currently, the OpenAI models lead the list. gorilla.cs.berkeley.ed...

Ah, I understand. The issue might stem from Gemini 1.5 being a less capable model. The LLM is responsible for invoking the tool usage. You can enhan...

Hi, I think I can assist. Could you please share your workflow? Here's a guide.