Trying to get llama3.2-vision working with a form

[Steve_Warburton]

Information on your n8n setup

• n8n version: 1.71.0
• **Database (default: SQLite):**default
• **n8n EXECUTIONS_PROCESS setting (default: own, main):**default
• **Running n8n via (Docker, npm, n8n cloud, desktop app):**npm
• **Operating system:**Windows

Attached workflow

error

generations
0
0
text:```json\n{\n    "action": "Final Answer",\n    "action_input": "I couldn't find any information about an image description in the previous response, please try again."\n}\n```

The json from the form is

[

{

"instructions": "what is in the image",

"image1": [

{

"filename": "house1.jpeg",

"mimetype": "image/jpeg",

"size": 157183

}

],

"submittedAt": "2025-01-29T07:46:45.780-05:00",

"formMode": "test"

}

]

What am I missing here please.

[Sebas]

This will get you on your way, I have been using Basic LLM chain to do image analyses with llama3.2-vision

if this gets you running then hit the ‘solution’ button, thx