What's Changed
* [UI] View top models by spend by krrishdholakia in https://github.com/BerriAI/litellm/pull/2257
* [FEAT] Use Base64 images with vertex_ai/gemini-pro-vision by ishaan-jaff in https://github.com/BerriAI/litellm/pull/2263
* [FEAT] add groq api pricing, models by ishaan-jaff in https://github.com/BerriAI/litellm/pull/2268
* fix: change actual github action for a call to discord RESTful API by DanielChico in https://github.com/BerriAI/litellm/pull/2262
Feature - Pass Base64 encoded images to `vertex_ai/gemini-pro-vision`
Docs: https://docs.litellm.ai/docs/providers/vertex#gemini-pro-vision
python
import litellm
def encode_image(image_path):
import base64
with open(image_path, "rb") as image_file:
return base64.b64encode(image_file.read()).decode("utf-8")
image_path = "cached_logo.jpg"
Getting the base64 string
base64_image = encode_image(image_path)
response = litellm.completion(
model="vertex_ai/gemini-pro-vision",
messages=[
{
"role": "user",
"content": [
{"type": "text", "text": "Whats in this image?"},
{
"type": "image_url",
"image_url": {
"url": "data:image/jpeg;base64," + base64_image
},
},
],
}
],
)
print(response)
New Contributors
* DanielChico made their first contribution in https://github.com/BerriAI/litellm/pull/2262
**Full Changelog**: https://github.com/BerriAI/litellm/compare/v1.28.1...v1.28.2