mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-25 10:44:24 +00:00
* fix(generic_api_callback.py): remove requests lib usage * fix(budget_manager.py): remove requests lib usgae * fix(main.py): cleanup requests lib usage * fix(utils.py): remove requests lib usage * fix(argilla.py): fix argilla test * fix(athina.py): replace 'requests' lib usage with litellm module * fix(greenscale.py): replace 'requests' lib usage with httpx * fix: remove unused 'requests' lib import + replace usage in some places * fix(prompt_layer.py): remove 'requests' lib usage from prompt layer * fix(ollama_chat.py): remove 'requests' lib usage * fix(baseten.py): replace 'requests' lib usage * fix(codestral/): replace 'requests' lib usage * fix(predibase/): replace 'requests' lib usage * refactor: cleanup unused 'requests' lib imports * fix(oobabooga.py): cleanup 'requests' lib usage * fix(invoke_handler.py): remove unused 'requests' lib usage * refactor: cleanup unused 'requests' lib import * fix: fix linting errors * refactor(ollama/): move ollama to using base llm http handler removes 'requests' lib dep for ollama integration * fix(ollama_chat.py): fix linting errors * fix(ollama/completion/transformation.py): convert non-jpeg/png image to jpeg/png before passing to ollama
72 lines
2.6 KiB
Python
72 lines
2.6 KiB
Python
import json
|
|
import traceback
|
|
from datetime import datetime, timezone
|
|
|
|
import litellm
|
|
|
|
|
|
class GreenscaleLogger:
|
|
def __init__(self):
|
|
import os
|
|
|
|
self.greenscale_api_key = os.getenv("GREENSCALE_API_KEY")
|
|
self.headers = {
|
|
"api-key": self.greenscale_api_key,
|
|
"Content-Type": "application/json",
|
|
}
|
|
self.greenscale_logging_url = os.getenv("GREENSCALE_ENDPOINT")
|
|
|
|
def log_event(self, kwargs, response_obj, start_time, end_time, print_verbose):
|
|
try:
|
|
response_json = response_obj.model_dump() if response_obj else {}
|
|
data = {
|
|
"modelId": kwargs.get("model"),
|
|
"inputTokenCount": response_json.get("usage", {}).get("prompt_tokens"),
|
|
"outputTokenCount": response_json.get("usage", {}).get(
|
|
"completion_tokens"
|
|
),
|
|
}
|
|
data["timestamp"] = datetime.now(timezone.utc).strftime(
|
|
"%Y-%m-%dT%H:%M:%SZ"
|
|
)
|
|
|
|
if type(end_time) is datetime and type(start_time) is datetime:
|
|
data["invocationLatency"] = int(
|
|
(end_time - start_time).total_seconds() * 1000
|
|
)
|
|
|
|
# Add additional metadata keys to tags
|
|
tags = []
|
|
metadata = kwargs.get("litellm_params", {}).get("metadata", {})
|
|
for key, value in metadata.items():
|
|
if key.startswith("greenscale"):
|
|
if key == "greenscale_project":
|
|
data["project"] = value
|
|
elif key == "greenscale_application":
|
|
data["application"] = value
|
|
else:
|
|
tags.append(
|
|
{"key": key.replace("greenscale_", ""), "value": str(value)}
|
|
)
|
|
|
|
data["tags"] = tags
|
|
|
|
if self.greenscale_logging_url is None:
|
|
raise Exception("Greenscale Logger Error - No logging URL found")
|
|
|
|
response = litellm.module_level_client.post(
|
|
self.greenscale_logging_url,
|
|
headers=self.headers,
|
|
data=json.dumps(data, default=str),
|
|
)
|
|
if response.status_code != 200:
|
|
print_verbose(
|
|
f"Greenscale Logger Error - {response.text}, {response.status_code}"
|
|
)
|
|
else:
|
|
print_verbose(f"Greenscale Logger Succeeded - {response.text}")
|
|
except Exception as e:
|
|
print_verbose(
|
|
f"Greenscale Logger Error - {e}, Stack trace: {traceback.format_exc()}"
|
|
)
|
|
pass
|