mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-26 11:14:04 +00:00
Merge branch 'main' into patch-1
This commit is contained in:
Marc Klingen
GitHub
commit
adf5e61f2e
394 changed files with 91840 additions and 8133 deletions
|
|
@ -1,11 +1,9 @@
|
|||
#### What this does ####
|
||||
# On success, logs events to Langfuse
|
||||
import dotenv, os
|
||||
import requests
|
||||
import requests
|
||||
from datetime import datetime
|
||||
|
||||
dotenv.load_dotenv() # Loading env variables using dotenv
|
||||
import copy
|
||||
import traceback
|
||||
from packaging.version import Version
|
||||
from litellm._logging import verbose_logger
|
||||
|
|
@ -14,12 +12,14 @@ import litellm
|
|||
|
||||
class LangFuseLogger:
|
||||
# Class variables or attributes
|
||||
def __init__(self, langfuse_public_key=None, langfuse_secret=None):
|
||||
def __init__(
|
||||
self, langfuse_public_key=None, langfuse_secret=None, flush_interval=1
|
||||
):
|
||||
try:
|
||||
from langfuse import Langfuse
|
||||
except Exception as e:
|
||||
raise Exception(
|
||||
f"\033[91mLangfuse not installed, try running 'pip install langfuse' to fix this error: {e}\033[0m"
|
||||
f"\033[91mLangfuse not installed, try running 'pip install langfuse' to fix this error: {e}\n{traceback.format_exc()}\033[0m"
|
||||
)
|
||||
# Instance variables
|
||||
self.secret_key = langfuse_secret or os.getenv("LANGFUSE_SECRET_KEY")
|
||||
|
|
@ -34,7 +34,7 @@ class LangFuseLogger:
|
|||
"host": self.langfuse_host,
|
||||
"release": self.langfuse_release,
|
||||
"debug": self.langfuse_debug,
|
||||
"flush_interval": 1,
|
||||
"flush_interval": flush_interval, # flush interval in seconds
|
||||
}
|
||||
|
||||
if Version(langfuse.version.__version__) >= Version("2.6.0"):
|
||||
|
|
@ -42,6 +42,14 @@ class LangFuseLogger:
|
|||
|
||||
self.Langfuse = Langfuse(**parameters)
|
||||
|
||||
# set the current langfuse project id in the environ
|
||||
# this is used by Alerting to link to the correct project
|
||||
try:
|
||||
project_id = self.Langfuse.client.projects.get().data[0].id
|
||||
os.environ["LANGFUSE_PROJECT_ID"] = project_id
|
||||
except:
|
||||
project_id = None
|
||||
|
||||
if os.getenv("UPSTREAM_LANGFUSE_SECRET_KEY") is not None:
|
||||
self.upstream_langfuse_secret_key = os.getenv(
|
||||
"UPSTREAM_LANGFUSE_SECRET_KEY"
|
||||
|
|
@ -84,15 +92,20 @@ class LangFuseLogger:
|
|||
print_verbose(
|
||||
f"Langfuse Logging - Enters logging function for model {kwargs}"
|
||||
)
|
||||
|
||||
litellm_params = kwargs.get("litellm_params", {})
|
||||
metadata = (
|
||||
litellm_params.get("metadata", {}) or {}
|
||||
) # if litellm_params['metadata'] == None
|
||||
prompt = [kwargs.get("messages")]
|
||||
optional_params = kwargs.get("optional_params", {})
|
||||
optional_params = copy.deepcopy(kwargs.get("optional_params", {}))
|
||||
|
||||
optional_params.pop("functions", None)
|
||||
optional_params.pop("tools", None)
|
||||
prompt = {"messages": kwargs.get("messages")}
|
||||
functions = optional_params.pop("functions", None)
|
||||
tools = optional_params.pop("tools", None)
|
||||
if functions is not None:
|
||||
prompt["functions"] = functions
|
||||
if tools is not None:
|
||||
prompt["tools"] = tools
|
||||
|
||||
# langfuse only accepts str, int, bool, float for logging
|
||||
for param, value in optional_params.items():
|
||||
|
|
@ -122,6 +135,11 @@ class LangFuseLogger:
|
|||
):
|
||||
input = prompt
|
||||
output = response_obj["choices"][0]["message"].json()
|
||||
elif response_obj is not None and isinstance(
|
||||
response_obj, litellm.TextCompletionResponse
|
||||
):
|
||||
input = prompt
|
||||
output = response_obj.choices[0].text
|
||||
elif response_obj is not None and isinstance(
|
||||
response_obj, litellm.ImageResponse
|
||||
):
|
||||
|
|
@ -132,6 +150,7 @@ class LangFuseLogger:
|
|||
self._log_langfuse_v2(
|
||||
user_id,
|
||||
metadata,
|
||||
litellm_params,
|
||||
output,
|
||||
start_time,
|
||||
end_time,
|
||||
|
|
@ -160,7 +179,7 @@ class LangFuseLogger:
|
|||
verbose_logger.info(f"Langfuse Layer Logging - logging success")
|
||||
except:
|
||||
traceback.print_exc()
|
||||
print(f"Langfuse Layer Error - {traceback.format_exc()}")
|
||||
verbose_logger.debug(f"Langfuse Layer Error - {traceback.format_exc()}")
|
||||
pass
|
||||
|
||||
async def _async_log_event(
|
||||
|
|
@ -189,7 +208,7 @@ class LangFuseLogger:
|
|||
):
|
||||
from langfuse.model import CreateTrace, CreateGeneration
|
||||
|
||||
print(
|
||||
verbose_logger.warning(
|
||||
"Please upgrade langfuse to v2.0.0 or higher: https://github.com/langfuse/langfuse-python/releases/tag/v2.0.1"
|
||||
)
|
||||
|
||||
|
|
@ -209,8 +228,8 @@ class LangFuseLogger:
|
|||
endTime=end_time,
|
||||
model=kwargs["model"],
|
||||
modelParameters=optional_params,
|
||||
input=input,
|
||||
output=output,
|
||||
prompt=input,
|
||||
completion=output,
|
||||
usage={
|
||||
"prompt_tokens": response_obj["usage"]["prompt_tokens"],
|
||||
"completion_tokens": response_obj["usage"]["completion_tokens"],
|
||||
|
|
@ -223,6 +242,7 @@ class LangFuseLogger:
|
|||
self,
|
||||
user_id,
|
||||
metadata,
|
||||
litellm_params,
|
||||
output,
|
||||
start_time,
|
||||
end_time,
|
||||
|
|
@ -250,16 +270,19 @@ class LangFuseLogger:
|
|||
metadata_tags = metadata.get("tags", [])
|
||||
tags = metadata_tags
|
||||
|
||||
generation_name = metadata.get("generation_name", None)
|
||||
if generation_name is None:
|
||||
# just log `litellm-{call_type}` as the generation name
|
||||
generation_name = f"litellm-{kwargs.get('call_type', 'completion')}"
|
||||
trace_name = metadata.get("trace_name", None)
|
||||
trace_id = metadata.get("trace_id", None)
|
||||
existing_trace_id = metadata.get("existing_trace_id", None)
|
||||
if trace_name is None and existing_trace_id is None:
|
||||
# just log `litellm-{call_type}` as the trace name
|
||||
## DO NOT SET TRACE_NAME if trace-id set. this can lead to overwriting of past traces.
|
||||
trace_name = f"litellm-{kwargs.get('call_type', 'completion')}"
|
||||
|
||||
trace_params = {
|
||||
"name": generation_name,
|
||||
"name": trace_name,
|
||||
"input": input,
|
||||
"user_id": metadata.get("trace_user_id", user_id),
|
||||
"id": metadata.get("trace_id", None),
|
||||
"id": trace_id or existing_trace_id,
|
||||
"session_id": metadata.get("session_id", None),
|
||||
}
|
||||
|
||||
|
|
@ -277,13 +300,13 @@ class LangFuseLogger:
|
|||
clean_metadata = {}
|
||||
if isinstance(metadata, dict):
|
||||
for key, value in metadata.items():
|
||||
# generate langfuse tags
|
||||
if key in [
|
||||
"user_api_key",
|
||||
"user_api_key_user_id",
|
||||
"user_api_key_team_id",
|
||||
"semantic-similarity",
|
||||
]:
|
||||
|
||||
# generate langfuse tags - Default Tags sent to Langfuse from LiteLLM Proxy
|
||||
if (
|
||||
litellm._langfuse_default_tags is not None
|
||||
and isinstance(litellm._langfuse_default_tags, list)
|
||||
and key in litellm._langfuse_default_tags
|
||||
):
|
||||
tags.append(f"{key}:{value}")
|
||||
|
||||
# clean litellm metadata before logging
|
||||
|
|
@ -297,13 +320,55 @@ class LangFuseLogger:
|
|||
else:
|
||||
clean_metadata[key] = value
|
||||
|
||||
if (
|
||||
litellm._langfuse_default_tags is not None
|
||||
and isinstance(litellm._langfuse_default_tags, list)
|
||||
and "proxy_base_url" in litellm._langfuse_default_tags
|
||||
):
|
||||
proxy_base_url = os.environ.get("PROXY_BASE_URL", None)
|
||||
if proxy_base_url is not None:
|
||||
tags.append(f"proxy_base_url:{proxy_base_url}")
|
||||
|
||||
api_base = litellm_params.get("api_base", None)
|
||||
if api_base:
|
||||
clean_metadata["api_base"] = api_base
|
||||
|
||||
vertex_location = kwargs.get("vertex_location", None)
|
||||
if vertex_location:
|
||||
clean_metadata["vertex_location"] = vertex_location
|
||||
|
||||
aws_region_name = kwargs.get("aws_region_name", None)
|
||||
if aws_region_name:
|
||||
clean_metadata["aws_region_name"] = aws_region_name
|
||||
|
||||
if supports_tags:
|
||||
if "cache_hit" in kwargs:
|
||||
if kwargs["cache_hit"] is None:
|
||||
kwargs["cache_hit"] = False
|
||||
tags.append(f"cache_hit:{kwargs['cache_hit']}")
|
||||
clean_metadata["cache_hit"] = kwargs["cache_hit"]
|
||||
trace_params.update({"tags": tags})
|
||||
|
||||
proxy_server_request = litellm_params.get("proxy_server_request", None)
|
||||
if proxy_server_request:
|
||||
method = proxy_server_request.get("method", None)
|
||||
url = proxy_server_request.get("url", None)
|
||||
headers = proxy_server_request.get("headers", None)
|
||||
clean_headers = {}
|
||||
if headers:
|
||||
for key, value in headers.items():
|
||||
# these headers can leak our API keys and/or JWT tokens
|
||||
if key.lower() not in ["authorization", "cookie", "referer"]:
|
||||
clean_headers[key] = value
|
||||
|
||||
clean_metadata["request"] = {
|
||||
"method": method,
|
||||
"url": url,
|
||||
"headers": clean_headers,
|
||||
}
|
||||
|
||||
print_verbose(f"trace_params: {trace_params}")
|
||||
|
||||
trace = self.Langfuse.trace(**trace_params)
|
||||
|
||||
generation_id = None
|
||||
|
|
@ -315,13 +380,26 @@ class LangFuseLogger:
|
|||
"completion_tokens": response_obj["usage"]["completion_tokens"],
|
||||
"total_cost": cost if supports_costs else None,
|
||||
}
|
||||
generation_name = metadata.get("generation_name", None)
|
||||
if generation_name is None:
|
||||
# just log `litellm-{call_type}` as the generation name
|
||||
generation_name = f"litellm-{kwargs.get('call_type', 'completion')}"
|
||||
|
||||
if response_obj is not None and "system_fingerprint" in response_obj:
|
||||
system_fingerprint = response_obj.get("system_fingerprint", None)
|
||||
else:
|
||||
system_fingerprint = None
|
||||
|
||||
if system_fingerprint is not None:
|
||||
optional_params["system_fingerprint"] = system_fingerprint
|
||||
|
||||
generation_params = {
|
||||
"name": generation_name,
|
||||
"id": metadata.get("generation_id", generation_id),
|
||||
"startTime": start_time,
|
||||
"endTime": end_time,
|
||||
"start_time": start_time,
|
||||
"end_time": end_time,
|
||||
"model": kwargs["model"],
|
||||
"modelParameters": optional_params,
|
||||
"model_parameters": optional_params,
|
||||
"input": input,
|
||||
"output": output,
|
||||
"usage": usage,
|
||||
|
|
@ -333,13 +411,15 @@ class LangFuseLogger:
|
|||
generation_params["prompt"] = metadata.get("prompt", None)
|
||||
|
||||
if output is not None and isinstance(output, str) and level == "ERROR":
|
||||
generation_params["statusMessage"] = output
|
||||
generation_params["status_message"] = output
|
||||
|
||||
if supports_completion_start_time:
|
||||
generation_params["completion_start_time"] = kwargs.get(
|
||||
"completion_start_time", None
|
||||
)
|
||||
|
||||
print_verbose(f"generation_params: {generation_params}")
|
||||
|
||||
trace.generation(**generation_params)
|
||||
except Exception as e:
|
||||
print(f"Langfuse Layer Error - {traceback.format_exc()}")
|
||||
verbose_logger.debug(f"Langfuse Layer Error - {traceback.format_exc()}")
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue