langchain_ollama attach image to prompt

mike_plumbs

I'm expirementing with llama 3.2 vision 11B and I'm having a bit of a rough time attaching an image, wether it's local or online, to the chat. Here's my Python code: import io import base64 import requests from PIL import Image from langchain_ollama import OllamaLLM from langchain_core.prompts import ChatPromptTemplate # Define exit keywords EXIT_KEYWORDS = ["exit", "quit", "stop", "bye", "end"] def encode_image_to_base64(image_path: str) ->...

Originally asked by Za3tour420 on Stack Exchange (stackoverflow) (CC BY-SA 4.0).

uphilltech

Great question — answering as the UphillTech team:

I hope you've found a solution to your problem, but if not, I may have an idea for you. In this article, the author uses ChatOllama instead of OllamaLLM: https://medium.com/@dimosdennis/personal-photo-library-with-langchain-ollama-llava-fully-local-e82edfe07f54 I had a problem similar to the one you describe here and changing it helped me get rid of it! I must admit I haven't gone through all your code, but maybe following the Medium tutorial (for part of it) might help. Good luck ;)

Full answer by Vitally Aberdeen: https://stackoverflow.stackexchange.com/a/79523914 (CC BY-SA 4.0).

Need it done for your business? UphillTech.