structure saas with tools
This commit is contained in:
@@ -0,0 +1,13 @@
|
||||
# Slack Alerting on LiteLLM Gateway
|
||||
|
||||
This folder contains the Slack Alerting integration for LiteLLM Gateway.
|
||||
|
||||
## Folder Structure
|
||||
|
||||
- `slack_alerting.py`: This is the main file that handles sending different types of alerts
|
||||
- `batching_handler.py`: Handles Batching + sending Httpx Post requests to slack. Slack alerts are sent every 10s or when events are greater than X events. Done to ensure litellm has good performance under high traffic
|
||||
- `types.py`: This file contains the AlertType enum which is used to define the different types of alerts that can be sent to Slack.
|
||||
- `utils.py`: This file contains common utils used specifically for slack alerting
|
||||
|
||||
## Further Reading
|
||||
- [Doc setting up Alerting on LiteLLM Proxy (Gateway)](https://docs.litellm.ai/docs/proxy/alerting)
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
@@ -0,0 +1,81 @@
|
||||
"""
|
||||
Handles Batching + sending Httpx Post requests to slack
|
||||
|
||||
Slack alerts are sent every 10s or when events are greater than X events
|
||||
|
||||
see custom_batch_logger.py for more details / defaults
|
||||
"""
|
||||
|
||||
from typing import TYPE_CHECKING, Any
|
||||
|
||||
from litellm._logging import verbose_proxy_logger
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from .slack_alerting import SlackAlerting as _SlackAlerting
|
||||
|
||||
SlackAlertingType = _SlackAlerting
|
||||
else:
|
||||
SlackAlertingType = Any
|
||||
|
||||
|
||||
def squash_payloads(queue):
|
||||
squashed = {}
|
||||
if len(queue) == 0:
|
||||
return squashed
|
||||
if len(queue) == 1:
|
||||
return {"key": {"item": queue[0], "count": 1}}
|
||||
|
||||
for item in queue:
|
||||
url = item["url"]
|
||||
alert_type = item["alert_type"]
|
||||
_key = (url, alert_type)
|
||||
|
||||
if _key in squashed:
|
||||
squashed[_key]["count"] += 1
|
||||
# Merge the payloads
|
||||
|
||||
else:
|
||||
squashed[_key] = {"item": item, "count": 1}
|
||||
|
||||
return squashed
|
||||
|
||||
|
||||
def _print_alerting_payload_warning(
|
||||
payload: dict, slackAlertingInstance: SlackAlertingType
|
||||
):
|
||||
"""
|
||||
Print the payload to the console when
|
||||
slackAlertingInstance.alerting_args.log_to_console is True
|
||||
|
||||
Relevant issue: https://github.com/BerriAI/litellm/issues/7372
|
||||
"""
|
||||
if slackAlertingInstance.alerting_args.log_to_console is True:
|
||||
verbose_proxy_logger.warning(payload)
|
||||
|
||||
|
||||
async def send_to_webhook(slackAlertingInstance: SlackAlertingType, item, count):
|
||||
"""
|
||||
Send a single slack alert to the webhook
|
||||
"""
|
||||
import json
|
||||
|
||||
payload = item.get("payload", {})
|
||||
try:
|
||||
if count > 1:
|
||||
payload["text"] = f"[Num Alerts: {count}]\n\n{payload['text']}"
|
||||
|
||||
response = await slackAlertingInstance.async_http_handler.post(
|
||||
url=item["url"],
|
||||
headers=item["headers"],
|
||||
data=json.dumps(payload),
|
||||
)
|
||||
if response.status_code != 200:
|
||||
verbose_proxy_logger.debug(
|
||||
f"Error sending slack alert to url={item['url']}. Error={response.text}"
|
||||
)
|
||||
except Exception as e:
|
||||
verbose_proxy_logger.debug(f"Error sending slack alert: {str(e)}")
|
||||
finally:
|
||||
_print_alerting_payload_warning(
|
||||
payload, slackAlertingInstance=slackAlertingInstance
|
||||
)
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,92 @@
|
||||
"""
|
||||
Utils used for slack alerting
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
from typing import TYPE_CHECKING, Any, Dict, List, Optional, Union
|
||||
|
||||
from litellm.proxy._types import AlertType
|
||||
from litellm.secret_managers.main import get_secret
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from litellm.litellm_core_utils.litellm_logging import Logging as _Logging
|
||||
|
||||
Logging = _Logging
|
||||
else:
|
||||
Logging = Any
|
||||
|
||||
|
||||
def process_slack_alerting_variables(
|
||||
alert_to_webhook_url: Optional[Dict[AlertType, Union[List[str], str]]]
|
||||
) -> Optional[Dict[AlertType, Union[List[str], str]]]:
|
||||
"""
|
||||
process alert_to_webhook_url
|
||||
- check if any urls are set as os.environ/SLACK_WEBHOOK_URL_1 read env var and set the correct value
|
||||
"""
|
||||
if alert_to_webhook_url is None:
|
||||
return None
|
||||
|
||||
for alert_type, webhook_urls in alert_to_webhook_url.items():
|
||||
if isinstance(webhook_urls, list):
|
||||
_webhook_values: List[str] = []
|
||||
for webhook_url in webhook_urls:
|
||||
if "os.environ/" in webhook_url:
|
||||
_env_value = get_secret(secret_name=webhook_url)
|
||||
if not isinstance(_env_value, str):
|
||||
raise ValueError(
|
||||
f"Invalid webhook url value for: {webhook_url}. Got type={type(_env_value)}"
|
||||
)
|
||||
_webhook_values.append(_env_value)
|
||||
else:
|
||||
_webhook_values.append(webhook_url)
|
||||
|
||||
alert_to_webhook_url[alert_type] = _webhook_values
|
||||
else:
|
||||
_webhook_value_str: str = webhook_urls
|
||||
if "os.environ/" in webhook_urls:
|
||||
_env_value = get_secret(secret_name=webhook_urls)
|
||||
if not isinstance(_env_value, str):
|
||||
raise ValueError(
|
||||
f"Invalid webhook url value for: {webhook_urls}. Got type={type(_env_value)}"
|
||||
)
|
||||
_webhook_value_str = _env_value
|
||||
else:
|
||||
_webhook_value_str = webhook_urls
|
||||
|
||||
alert_to_webhook_url[alert_type] = _webhook_value_str
|
||||
|
||||
return alert_to_webhook_url
|
||||
|
||||
|
||||
async def _add_langfuse_trace_id_to_alert(
|
||||
request_data: Optional[dict] = None,
|
||||
) -> Optional[str]:
|
||||
"""
|
||||
Returns langfuse trace url
|
||||
|
||||
- check:
|
||||
-> existing_trace_id
|
||||
-> trace_id
|
||||
-> litellm_call_id
|
||||
"""
|
||||
# do nothing for now
|
||||
if (
|
||||
request_data is not None
|
||||
and request_data.get("litellm_logging_obj", None) is not None
|
||||
):
|
||||
trace_id: Optional[str] = None
|
||||
litellm_logging_obj: Logging = request_data["litellm_logging_obj"]
|
||||
|
||||
for _ in range(3):
|
||||
trace_id = litellm_logging_obj._get_trace_id(service_name="langfuse")
|
||||
if trace_id is not None:
|
||||
break
|
||||
await asyncio.sleep(3) # wait 3s before retrying for trace id
|
||||
|
||||
_langfuse_object = litellm_logging_obj._get_callback_object(
|
||||
service_name="langfuse"
|
||||
)
|
||||
if _langfuse_object is not None:
|
||||
base_url = _langfuse_object.Langfuse.base_url
|
||||
return f"{base_url}/trace/{trace_id}"
|
||||
return None
|
||||
Reference in New Issue
Block a user