forked from phoenix/litellm-mirror
* refactor: move gemini translation logic inside the transformation.py file easier to isolate the gemini translation logic * fix(gemini-transformation): support multiple tool calls in message body Merges https://github.com/BerriAI/litellm/pull/6487/files * test(test_vertex.py): add remaining tests from https://github.com/BerriAI/litellm/pull/6487 * fix(gemini-transformation): return tool calls for multiple tool calls * fix: support passing logprobs param for vertex + gemini * feat(vertex_ai): add logprobs support for gemini calls * fix(anthropic/chat/transformation.py): fix disable parallel tool use flag * fix: fix linting error * fix(_logging.py): log stacktrace information in json logs Closes https://github.com/BerriAI/litellm/issues/6497 * fix(utils.py): fix mem leak for async stream + completion Uses a global executor pool instead of creating a new thread on each request Fixes https://github.com/BerriAI/litellm/issues/6404 * fix(factory.py): handle tool call + content in assistant message for bedrock * fix: fix import * fix(factory.py): maintain support for content as a str in assistant response * fix: fix import * test: cleanup test * fix(vertex_and_google_ai_studio/): return none for content if no str value * test: retry flaky tests * (UI) Fix viewing members, keys in a team + added testing (#6514) * fix listing teams on ui * LiteLLM Minor Fixes & Improvements (10/28/2024) (#6475) * fix(anthropic/chat/transformation.py): support anthropic disable_parallel_tool_use param Fixes https://github.com/BerriAI/litellm/issues/6456 * feat(anthropic/chat/transformation.py): support anthropic computer tool use Closes https://github.com/BerriAI/litellm/issues/6427 * fix(vertex_ai/common_utils.py): parse out '$schema' when calling vertex ai Fixes issue when trying to call vertex from vercel sdk * fix(main.py): add 'extra_headers' support for azure on all translation endpoints Fixes https://github.com/BerriAI/litellm/issues/6465 * fix: fix linting errors * fix(transformation.py): handle no beta headers for anthropic * test: cleanup test * fix: fix linting error * fix: fix linting errors * fix: fix linting errors * fix(transformation.py): handle dummy tool call * fix(main.py): fix linting error * fix(azure.py): pass required param * LiteLLM Minor Fixes & Improvements (10/24/2024) (#6441) * fix(azure.py): handle /openai/deployment in azure api base * fix(factory.py): fix faulty anthropic tool result translation check Fixes https://github.com/BerriAI/litellm/issues/6422 * fix(gpt_transformation.py): add support for parallel_tool_calls to azure Fixes https://github.com/BerriAI/litellm/issues/6440 * fix(factory.py): support anthropic prompt caching for tool results * fix(vertex_ai/common_utils): don't pop non-null required field Fixes https://github.com/BerriAI/litellm/issues/6426 * feat(vertex_ai.py): support code_execution tool call for vertex ai + gemini Closes https://github.com/BerriAI/litellm/issues/6434 * build(model_prices_and_context_window.json): Add 'supports_assistant_prefill' for bedrock claude-3-5-sonnet v2 models Closes https://github.com/BerriAI/litellm/issues/6437 * fix(types/utils.py): fix linting * test: update test to include required fields * test: fix test * test: handle flaky test * test: remove e2e test - hitting gemini rate limits * Litellm dev 10 26 2024 (#6472) * docs(exception_mapping.md): add missing exception types Fixes https://github.com/Aider-AI/aider/issues/2120#issuecomment-2438971183 * fix(main.py): register custom model pricing with specific key Ensure custom model pricing is registered to the specific model+provider key combination * test: make testing more robust for custom pricing * fix(redis_cache.py): instrument otel logging for sync redis calls ensures complete coverage for all redis cache calls * (Testing) Add unit testing for DualCache - ensure in memory cache is used when expected (#6471) * test test_dual_cache_get_set * unit testing for dual cache * fix async_set_cache_sadd * test_dual_cache_local_only * redis otel tracing + async support for latency routing (#6452) * docs(exception_mapping.md): add missing exception types Fixes https://github.com/Aider-AI/aider/issues/2120#issuecomment-2438971183 * fix(main.py): register custom model pricing with specific key Ensure custom model pricing is registered to the specific model+provider key combination * test: make testing more robust for custom pricing * fix(redis_cache.py): instrument otel logging for sync redis calls ensures complete coverage for all redis cache calls * refactor: pass parent_otel_span for redis caching calls in router allows for more observability into what calls are causing latency issues * test: update tests with new params * refactor: ensure e2e otel tracing for router * refactor(router.py): add more otel tracing acrosss router catch all latency issues for router requests * fix: fix linting error * fix(router.py): fix linting error * fix: fix test * test: fix tests * fix(dual_cache.py): pass ttl to redis cache * fix: fix param * fix(dual_cache.py): set default value for parent_otel_span * fix(transformation.py): support 'response_format' for anthropic calls * fix(transformation.py): check for cache_control inside 'function' block * fix: fix linting error * fix: fix linting errors --------- Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com> --------- Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com> * ui new build * Add retry strat (#6520) Signed-off-by: dbczumar <corey.zumar@databricks.com> * (fix) slack alerting - don't spam the failed cost tracking alert for the same model (#6543) * fix use failing_model as cache key for failed_tracking_alert * fix use standard logging payload for getting response cost * fix kwargs.get("response_cost") * fix getting response cost * (feat) add XAI ChatCompletion Support (#6373) * init commit for XAI * add full logic for xai chat completion * test_completion_xai * docs xAI * add xai/grok-beta * test_xai_chat_config_get_openai_compatible_provider_info * test_xai_chat_config_map_openai_params * add xai streaming test --------- Signed-off-by: dbczumar <corey.zumar@databricks.com> Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com> Co-authored-by: Corey Zumar <39497902+dbczumar@users.noreply.github.com>
105 lines
3 KiB
Python
105 lines
3 KiB
Python
import json
|
|
import logging
|
|
import os
|
|
import traceback
|
|
from datetime import datetime
|
|
from logging import Formatter
|
|
|
|
set_verbose = False
|
|
|
|
if set_verbose is True:
|
|
logging.warning(
|
|
"`litellm.set_verbose` is deprecated. Please set `os.environ['LITELLM_LOG'] = 'DEBUG'` for debug logs."
|
|
)
|
|
json_logs = bool(os.getenv("JSON_LOGS", False))
|
|
# Create a handler for the logger (you may need to adapt this based on your needs)
|
|
log_level = os.getenv("LITELLM_LOG", "DEBUG")
|
|
numeric_level: str = getattr(logging, log_level.upper())
|
|
handler = logging.StreamHandler()
|
|
handler.setLevel(numeric_level)
|
|
|
|
|
|
class JsonFormatter(Formatter):
|
|
def __init__(self):
|
|
super(JsonFormatter, self).__init__()
|
|
|
|
def formatTime(self, record, datefmt=None):
|
|
# Use datetime to format the timestamp in ISO 8601 format
|
|
dt = datetime.fromtimestamp(record.created)
|
|
return dt.isoformat()
|
|
|
|
def format(self, record):
|
|
json_record = {
|
|
"message": record.getMessage(),
|
|
"level": record.levelname,
|
|
"timestamp": self.formatTime(record),
|
|
}
|
|
|
|
if record.exc_info:
|
|
json_record["stacktrace"] = self.formatException(record.exc_info)
|
|
|
|
return json.dumps(json_record)
|
|
|
|
|
|
# Create a formatter and set it for the handler
|
|
if json_logs:
|
|
handler.setFormatter(JsonFormatter())
|
|
else:
|
|
formatter = logging.Formatter(
|
|
"\033[92m%(asctime)s - %(name)s:%(levelname)s\033[0m: %(filename)s:%(lineno)s - %(message)s",
|
|
datefmt="%H:%M:%S",
|
|
)
|
|
|
|
handler.setFormatter(formatter)
|
|
|
|
verbose_proxy_logger = logging.getLogger("LiteLLM Proxy")
|
|
verbose_router_logger = logging.getLogger("LiteLLM Router")
|
|
verbose_logger = logging.getLogger("LiteLLM")
|
|
|
|
# Add the handler to the logger
|
|
verbose_router_logger.addHandler(handler)
|
|
verbose_proxy_logger.addHandler(handler)
|
|
verbose_logger.addHandler(handler)
|
|
|
|
|
|
def _turn_on_json():
|
|
handler = logging.StreamHandler()
|
|
handler.setFormatter(JsonFormatter())
|
|
|
|
# Define a list of the loggers to update
|
|
loggers = [verbose_router_logger, verbose_proxy_logger, verbose_logger]
|
|
|
|
# Iterate through each logger and update its handlers
|
|
for logger in loggers:
|
|
# Remove all existing handlers
|
|
for h in logger.handlers[:]:
|
|
logger.removeHandler(h)
|
|
|
|
# Add the new handler
|
|
logger.addHandler(handler)
|
|
|
|
|
|
def _turn_on_debug():
|
|
verbose_logger.setLevel(level=logging.DEBUG) # set package log to debug
|
|
verbose_router_logger.setLevel(level=logging.DEBUG) # set router logs to debug
|
|
verbose_proxy_logger.setLevel(level=logging.DEBUG) # set proxy logs to debug
|
|
|
|
|
|
def _disable_debugging():
|
|
verbose_logger.disabled = True
|
|
verbose_router_logger.disabled = True
|
|
verbose_proxy_logger.disabled = True
|
|
|
|
|
|
def _enable_debugging():
|
|
verbose_logger.disabled = False
|
|
verbose_router_logger.disabled = False
|
|
verbose_proxy_logger.disabled = False
|
|
|
|
|
|
def print_verbose(print_statement):
|
|
try:
|
|
if set_verbose:
|
|
print(print_statement) # noqa
|
|
except Exception:
|
|
pass
|