Problem sending image to 3.2 vision models

SambaNova Devs Hackathons
1

Can anyone help me with a problem when sending an image to vision models? Is there a specific configuration in the code for it to receive it in a specific format? Could someone help me and give me an example?

1 Like
3

Hi @deyvidhblack, Welcome to the community.
Can you please try this example code:

import openai
import base64

# Function to encode the image
def encode_image(image_path):
  with open(image_path, "rb") as image_file:
    return base64.b64encode(image_file.read()).decode('utf-8')


client = openai.OpenAI(
    api_key='Your_sambanova_api_key',
    base_url="https://api.sambanova.ai/v1",
)

# Path to your image
image_path = "/Users/omkarg/Downloads/IMG_2117.jpg"

# Getting the base64 string
base64_image = encode_image(image_path)

response = client.chat.completions.create(
  model="Llama-3.2-11B-Vision-Instruct",
  messages=[
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "What is in this image?",
        },
        {
          "type": "image_url",
          "image_url": {
            "url":  f"data:image/jpeg;base64,{base64_image}"
          },
        },
      ],
    }
  ],
)

print(response.choices[0].message.content)

Please let us know if you face any errors.
Thanks & Regards