mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-03 02:22:24 +00:00
a6f6c64b6e
* feat(ui): adopt the new LiteLLM logo and monogram Swap the bundled admin UI logos for the new brand assets: the primary logo in blue for light mode and white for dark mode, and the monogram for the collapsed sidebar, favicons, and the built-in guardrail cards. /get_image gains a variant=monogram query parameter so the collapsed sidebar can request the monogram while admin-configured UI_LOGO_PATH / UI_LOGO_PATH_DARK logos still take precedence. The bundled light logo moves from JPEG to a transparent PNG. * test(ui): query collapsed sidebar logos by role to stay within the lint budget * fix: point remaining logo consumers at the new bundled assets The Rust gateway UI served /get_image from the removed litellm_logo.jpg, the non-root get_image tests pinned logo.jpg, and a cookbook script read litellm/proxy/logo.jpg. Point them at the monogram and logo.png. * fix(mcp): serve the BYOK OAuth page logo from /get_image The page pointed at /ui/assets/logos/litellm_logo.jpg, which the rebrand removes from the dashboard sources, so the next UI build would drop it. /get_image?variant=monogram is always served by the proxy and follows any admin-configured logo. * fix(ui): invert the LiteLLM monogram on dark guardrail cards The blue monogram has a transparent train cut-out, so on a dark card it read as a muddy blue block. Inverting it yields the brand's white mark, which the logo guidelines prescribe for dark backgrounds. * fix(gateway-ui): serve theme and variant aware logos from the dashboard export The Rust gateway served one monogram for every /get_image request, and the committed export lacked it, so /get_image returned 404 until the next UI release build. Pick the full or monogram logo in light or dark from the query, ship those assets in the dashboard's public dir and the committed export, and drop two comments that restated asserted paths.
49 lines
1.2 KiB
Python
49 lines
1.2 KiB
Python
import base64
|
|
from openai import OpenAI
|
|
import time
|
|
|
|
client = OpenAI(base_url="http://0.0.0.0:4001", api_key="sk-1234")
|
|
|
|
|
|
# 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")
|
|
|
|
|
|
# Path to your image
|
|
image_path = "litellm/proxy/logo.png"
|
|
|
|
# Getting the Base64 string
|
|
base64_image = encode_image(image_path)
|
|
|
|
|
|
response = client.responses.create(
|
|
model="bedrock/us.anthropic.claude-haiku-4-5-20251001-v1:0",
|
|
input=[
|
|
{
|
|
"role": "user",
|
|
"content": [
|
|
{"type": "input_text", "text": "what color is the image"},
|
|
{
|
|
"type": "input_image",
|
|
"image_url": f"data:image/png;base64,{base64_image}",
|
|
},
|
|
],
|
|
}
|
|
],
|
|
)
|
|
|
|
|
|
print(response.output_text)
|
|
print("response1 id===", response.id)
|
|
print("sleeping for 20 seconds...")
|
|
time.sleep(20)
|
|
print("making follow up request for existing id")
|
|
response2 = client.responses.create(
|
|
model="bedrock/us.anthropic.claude-haiku-4-5-20251001-v1:0",
|
|
previous_response_id=response.id,
|
|
input="ok, and what objects are in the image?",
|
|
)
|
|
|
|
print(response2.output_text)
|