mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-25 02:34:29 +00:00
* feat(litellm_pre_call_utils.py): support forwarding request headers to backend llm api * fix(litellm_pre_call_utils.py): handle custom litellm key header * test(router_code_coverage.py): check if all router functions are dire… (#6186) * test(router_code_coverage.py): check if all router functions are directly tested prevent regressions * docs(configs.md): document all environment variables (#6185) * docs: make it easier to find anthropic/openai prompt caching doc * aded codecov yml (#6207) * fix codecov.yaml * run ci/cd again * (refactor) caching use LLMCachingHandler for async_get_cache and set_cache (#6208) * use folder for caching * fix importing caching * fix clickhouse pyright * fix linting * fix correctly pass kwargs and args * fix test case for embedding * fix linting * fix embedding caching logic * fix refactor handle utils.py * fix test_embedding_caching_azure_individual_items_reordered * (feat) prometheus have well defined latency buckets (#6211) * fix prometheus have well defined latency buckets * use a well define latency bucket * use types file for prometheus logging * add test for LATENCY_BUCKETS * fix prom testing * fix config.yml * (refactor caching) use LLMCachingHandler for caching streaming responses (#6210) * use folder for caching * fix importing caching * fix clickhouse pyright * fix linting * fix correctly pass kwargs and args * fix test case for embedding * fix linting * fix embedding caching logic * fix refactor handle utils.py * refactor async set stream cache * fix linting * bump (#6187) * update code cov yaml * fix config.yml * add caching component to code cov * fix config.yml ci/cd * add coverage for proxy auth * (refactor caching) use common `_retrieve_from_cache` helper (#6212) * use folder for caching * fix importing caching * fix clickhouse pyright * fix linting * fix correctly pass kwargs and args * fix test case for embedding * fix linting * fix embedding caching logic * fix refactor handle utils.py * refactor async set stream cache * fix linting * refactor - use _retrieve_from_cache * refactor use _convert_cached_result_to_model_response * fix linting errors * bump: version 1.49.2 → 1.49.3 * fix code cov components * test(test_router_helpers.py): add router component unit tests * test: add additional router tests * test: add more router testing * test: add more router testing + more mock functions * ci(router_code_coverage.py): fix check --------- Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com> Co-authored-by: yujonglee <yujonglee.dev@gmail.com> * bump: version 1.49.3 → 1.49.4 * (refactor) use helper function `_assemble_complete_response_from_streaming_chunks` to assemble complete responses in caching and logging callbacks (#6220) * (refactor) use _assemble_complete_response_from_streaming_chunks * add unit test for test_assemble_complete_response_from_streaming_chunks_1 * fix assemble complete_streaming_response * config add logging_testing * add logging_coverage in codecov * test test_assemble_complete_response_from_streaming_chunks_3 * add unit tests for _assemble_complete_response_from_streaming_chunks * fix remove unused / junk function * add test for streaming_chunks when error assembling * (refactor) OTEL - use safe_set_attribute for setting attributes (#6226) * otel - use safe_set_attribute for setting attributes * fix OTEL only use safe_set_attribute * (fix) prompt caching cost calculation OpenAI, Azure OpenAI (#6231) * fix prompt caching cost calculation * fix testing for prompt cache cost calc * fix(allowed_model_region): allow us as allowed region (#6234) * test(router_code_coverage.py): check if all router functions are dire… (#6186) * test(router_code_coverage.py): check if all router functions are directly tested prevent regressions * docs(configs.md): document all environment variables (#6185) * docs: make it easier to find anthropic/openai prompt caching doc * aded codecov yml (#6207) * fix codecov.yaml * run ci/cd again * (refactor) caching use LLMCachingHandler for async_get_cache and set_cache (#6208) * use folder for caching * fix importing caching * fix clickhouse pyright * fix linting * fix correctly pass kwargs and args * fix test case for embedding * fix linting * fix embedding caching logic * fix refactor handle utils.py * fix test_embedding_caching_azure_individual_items_reordered * (feat) prometheus have well defined latency buckets (#6211) * fix prometheus have well defined latency buckets * use a well define latency bucket * use types file for prometheus logging * add test for LATENCY_BUCKETS * fix prom testing * fix config.yml * (refactor caching) use LLMCachingHandler for caching streaming responses (#6210) * use folder for caching * fix importing caching * fix clickhouse pyright * fix linting * fix correctly pass kwargs and args * fix test case for embedding * fix linting * fix embedding caching logic * fix refactor handle utils.py * refactor async set stream cache * fix linting * bump (#6187) * update code cov yaml * fix config.yml * add caching component to code cov * fix config.yml ci/cd * add coverage for proxy auth * (refactor caching) use common `_retrieve_from_cache` helper (#6212) * use folder for caching * fix importing caching * fix clickhouse pyright * fix linting * fix correctly pass kwargs and args * fix test case for embedding * fix linting * fix embedding caching logic * fix refactor handle utils.py * refactor async set stream cache * fix linting * refactor - use _retrieve_from_cache * refactor use _convert_cached_result_to_model_response * fix linting errors * bump: version 1.49.2 → 1.49.3 * fix code cov components * test(test_router_helpers.py): add router component unit tests * test: add additional router tests * test: add more router testing * test: add more router testing + more mock functions * ci(router_code_coverage.py): fix check --------- Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com> Co-authored-by: yujonglee <yujonglee.dev@gmail.com> * bump: version 1.49.3 → 1.49.4 * (refactor) use helper function `_assemble_complete_response_from_streaming_chunks` to assemble complete responses in caching and logging callbacks (#6220) * (refactor) use _assemble_complete_response_from_streaming_chunks * add unit test for test_assemble_complete_response_from_streaming_chunks_1 * fix assemble complete_streaming_response * config add logging_testing * add logging_coverage in codecov * test test_assemble_complete_response_from_streaming_chunks_3 * add unit tests for _assemble_complete_response_from_streaming_chunks * fix remove unused / junk function * add test for streaming_chunks when error assembling * (refactor) OTEL - use safe_set_attribute for setting attributes (#6226) * otel - use safe_set_attribute for setting attributes * fix OTEL only use safe_set_attribute * fix(allowed_model_region): allow us as allowed region --------- Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com> Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com> Co-authored-by: yujonglee <yujonglee.dev@gmail.com> * fix(litellm_pre_call_utils.py): support 'us' region routing + fix header forwarding to filter on `x-` headers * docs(customer_routing.md): fix region-based routing example * feat(azure.py): handle empty arguments function call - azure Closes https://github.com/BerriAI/litellm/issues/6241 * feat(guardrails_ai.py): support guardrails ai integration Adds support for on-prem guardrails via guardrails ai * fix(proxy/utils.py): prevent sql injection attack Fixes https://huntr.com/bounties/a4f6d357-5b44-4e00-9cac-f1cc351211d2 * fix: fix linting errors * fix(litellm_pre_call_utils.py): don't log litellm api key in proxy server request headers * fix(litellm_pre_call_utils.py): don't forward stainless headers * docs(guardrails_ai.md): add guardrails ai quick start to docs * test: handle flaky test --------- Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com> Co-authored-by: yujonglee <yujonglee.dev@gmail.com> Co-authored-by: Marcus Elwin <marcus@elwin.com>
50 lines
1.8 KiB
Python
50 lines
1.8 KiB
Python
from typing import List, Literal, Optional
|
|
|
|
from litellm._logging import verbose_logger
|
|
from litellm.integrations.custom_logger import CustomLogger
|
|
from litellm.types.guardrails import GuardrailEventHooks
|
|
|
|
|
|
class CustomGuardrail(CustomLogger):
|
|
|
|
def __init__(
|
|
self,
|
|
guardrail_name: Optional[str] = None,
|
|
supported_event_hooks: Optional[List[GuardrailEventHooks]] = None,
|
|
event_hook: Optional[GuardrailEventHooks] = None,
|
|
**kwargs,
|
|
):
|
|
self.guardrail_name = guardrail_name
|
|
self.supported_event_hooks = supported_event_hooks
|
|
self.event_hook: Optional[GuardrailEventHooks] = event_hook
|
|
|
|
if supported_event_hooks:
|
|
## validate event_hook is in supported_event_hooks
|
|
if event_hook and event_hook not in supported_event_hooks:
|
|
raise ValueError(
|
|
f"Event hook {event_hook} is not in the supported event hooks {supported_event_hooks}"
|
|
)
|
|
super().__init__(**kwargs)
|
|
|
|
def should_run_guardrail(self, data, event_type: GuardrailEventHooks) -> bool:
|
|
metadata = data.get("metadata") or {}
|
|
requested_guardrails = metadata.get("guardrails") or []
|
|
verbose_logger.debug(
|
|
"inside should_run_guardrail for guardrail=%s event_type= %s guardrail_supported_event_hooks= %s requested_guardrails= %s",
|
|
self.guardrail_name,
|
|
event_type,
|
|
self.event_hook,
|
|
requested_guardrails,
|
|
)
|
|
|
|
if (
|
|
self.event_hook
|
|
and self.guardrail_name not in requested_guardrails
|
|
and event_type.value != "logging_only"
|
|
):
|
|
return False
|
|
|
|
if self.event_hook and self.event_hook != event_type.value:
|
|
return False
|
|
|
|
return True
|