MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 88 callersFunctionl
({href:e,variant:o,className:s,children:u})
litellm/proxy/_experimental/out/_next/static/chunks/2rtlqswx6sz6u.js:1
↓ 88 callersFunctionmethod
()
litellm-rust/crates/gateway-forward/tests/roundtrip.rs:43
↓ 88 callersMethodsearch
( self, query: str, agents: Sequence[AgentResponse], top_k: int, embed: Embedder, embedding_model: str
litellm/proxy/agent_endpoints/agent_search.py:111
↓ 87 callersFunction_make_guardrail
(**overrides)
tests/unit/proxy/guardrails/guardrail_hooks/test_straiker.py:50
↓ 87 callersMethodadd_standard_logging_guardrail_information_to_request_data
Builds `StandardLoggingGuardrailInformation` and adds it to the request metadata so it can be used for logging to DataDog, Langfuse, etc.
litellm/integrations/custom_guardrail.py:1560
↓ 87 callersMethodcollect
(self)
tests/unit/integrations/test_prometheus_metrics_endpoint.py:34
↓ 87 callersMethodfind_unique
(self, where)
tests/unit/proxy/mcp_server/test_mcp_env_vars.py:1208
↓ 87 callersMethoditer_lines
(self)
tests/e2e/e2e_http.py:218
↓ 87 callersMethodresolve
(self, replies: Sequence[object])
litellm/caching/redis_batch.py:95
↓ 87 callersMethodsetdefault
(self, key: str, default: object = None)
tests/unit/proxy/test_budget_reservation.py:2192
↓ 87 callersMethodtransform_response
( self, model, raw_response, model_response, logging_obj, requ
tests/unit/llms/custom_httpx/test_llm_http_handler.py:4707
↓ 86 callersFunction_note
(name: str, replacement: str)
litellm/router_deprecated.py:79
↓ 86 callersMethodpath
(&self)
litellm-rust/crates/model-catalog/src/error.rs:210
↓ 86 callersMethodtransform_responses_api_request
( self, model: str, input: str | ResponseInputParam, response_api_optional_req
litellm/llms/sail/responses/transformation.py:32
↓ 85 callersFunctionA
()
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 85 callersMethodarray
()
litellm/proxy/_experimental/out/_next/static/chunks/2j7hjtph8n74b.js:1
↓ 85 callersMethodas_bytes
(self)
tests/rust-python-harness/shared/parity/fixtures/cassette.py:30
↓ 85 callersFunctionencode_url_path_segment
Percent-encode one user-controlled URL path segment. ``urllib.parse.quote(..., safe="")`` intentionally leaves RFC 3986 unreserved characters
litellm/litellm_core_utils/url_utils.py:113
↓ 85 callersMethodpoll
()
tests/code_coverage_tests/test_e2e_metadata.py:272
↓ 85 callersMethodpost_call_failure_hook
Allows users to raise custom exceptions/log when a call fails, without having to deal with parsing Request body. Callbacks can return
litellm/proxy/utils.py:4081
↓ 85 callersMethodsafeParse
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2j7hjtph8n74b.js:1
↓ 85 callersMethodtext
(self)
tests/e2e/e2e_http.py:216
↓ 84 callersFunction_logging_obj
()
tests/unit/proxy/guardrails/guardrail_hooks/test_straiker.py:65
↓ 84 callersMethodaembedding
( self, model: str, input: list, model_response: EmbeddingResponse, pr
tests/unit/llms/test_custom_llm.py:273
↓ 84 callersMethodfetchone
(self)
tests/unit/litellm_proxy_extras/test_litellm_proxy_extras_utils.py:756
↓ 84 callersMethodis_empty
(&self)
litellm-rust/crates/llms-types/src/providers/anthropic/beta.rs:449
↓ 84 callersMethodset
(self, name: str, value: str, nx: bool, ex: int | None)
tests/unit/integrations/test_prometheus_services.py:253
↓ 83 callersFunctionanthropic_messages_pt
format messages for anthropic 1. Anthropic supports roles like "user" and "assistant" (system prompt sent separately). Models flagged
litellm/litellm_core_utils/prompt_templates/factory.py:3007
↓ 83 callersMethodinto_iter
(self)
litellm-rust/crates/llms-types/src/providers/anthropic/beta.rs:476
↓ 83 callersFunctionrequire_attributes
(value: object, shape: type[_Shape], *names: str)
litellm/litellm_core_utils/core_helpers.py:176
↓ 82 callersMethod_replace
(self, entries: list[Entry])
litellm/router_rust/surface/model_list.py:323
↓ 82 callersFunctionassert_translation
( case: TranslationTestCase, gateway: Gateway, provider: SharedProvider, *, headers: Mappi
tests/integration/translation/runner.py:37
↓ 82 callersMethodclose
(self)
litellm/llms/custom_httpx/http_handler.py:827
↓ 82 callersFunctiongetProxyBaseUrl
()
ui/litellm-dashboard/src/components/networking.tsx:227
↓ 82 callersMethodget_complete_url
Get the complete URL for the CometAPI call. Returns: str: The complete URL for the API call.
litellm/llms/cometapi/chat/transformation.py:87
↓ 82 callersFunctionj
litellm/proxy/_experimental/out/_next/static/chunks/0r8bcbns1_gw5.js:1
↓ 82 callersMethodopenai
(self, key: str)
tests/e2e/llm_translation/sdk_clients.py:44
↓ 82 callersMethodrequest_multipart
( self, path: str, fields: Mapping[str, str], files: Mapping[str, tuple[str, b
tests/integration/_support/client.py:128
↓ 82 callersMethodrun
(self)
litellm/timeout.py:103
↓ 82 callersMethodtake
(&self)
litellm-rust/crates/python-bridge/src/redis/breaker.rs:101
↓ 81 callersMethodacompletion
(**kwargs)
tests/unit/integrations/test_shadow_eval_logger.py:1669
↓ 81 callersMethodasync_log_success_event
( self, kwargs: Mapping[str, object], response_obj: object, start_time: datetime, end_time: datetime
tests/unit/proxy/hooks/test_autorouter_baseline_cache.py:198
↓ 81 callersFunctioni
(i)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 81 callersMethodupdate
Update an existing API key's parameters. Args: models: Optional[List[str]] = None, aliases: Optional[Dict[st
litellm/proxy/client/keys.py:235
↓ 80 callersFunction_patch_inspection_post
(g: CiscoAIDefenseGuardrail, post_mock: Any)
tests/unit/proxy/guardrails/guardrail_hooks/_cisco_ai_defense_test_utils.py:56
↓ 80 callersMethodand
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2j7hjtph8n74b.js:1
↓ 80 callersFunctiondecrypt_value_helper
( value: str, key: str, # this is just for debug purposes, showing the k,v pair that's invalid. not a
litellm/proxy/common_utils/encrypt_decrypt_utils.py:258
↓ 80 callersMethodnon_proxy_admin_allowed_routes_check
Checks if Non Proxy Admin User is allowed to access the route
litellm/proxy/auth/route_checks.py:313
↓ 79 callersMethodformat
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 79 callersMethodnext
()
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 79 callersMethodok
(self)
tests/e2e/e2e_http.py:200
↓ 79 callersMethodregister
(self, request_nonce: str, backend: Responder, classifier: Responder | None = None)
tests/integration/_support/safeguards_rig.py:242
↓ 79 callersMethoduser
(self)
tests/integration/authorization/test_team_admin_gate.py:73
↓ 78 callersMethodasync_get_cache
( self, key, parent_otel_span: Span | None = None, local_only: bool = False,
litellm/caching/dual_cache.py:253
↓ 78 callersMethodconcat
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 78 callersMethodcount
(self, where=None)
tests/unit/proxy/proxy_server/test_routes_model_info.py:2218
↓ 78 callersFunctionek
litellm/proxy/_experimental/out/_next/static/chunks/2hk8n3azev--d.js:1
↓ 78 callersMethodget_model_list
(self, model_name=None, team_id=None)
tests/unit/proxy/pass_through_endpoints/test_llm_pass_through_endpoints.py:7841
↓ 78 callersFunctionnonce
()
tests/integration/_support/safeguards_rig.py:111
↓ 78 callersFunctionupstream
Starts an upstream that answers its n-th request with the n-th response and 404s after.
litellm-rust/crates/inference-messages/tests/support/mod.rs:29
↓ 77 callersFunction_register
(redirect_uris, token_exchange_available=True)
tests/unit/proxy/mcp_server/test_gateway_dcr_flow.py:104
↓ 77 callersMethodfind_unique
( self, *, where: Mapping[str, object], include: Mapping[str, object] | None = None )
litellm/proxy/auth/auth_checks.py:254
↓ 77 callersFunctionm
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/0r8bcbns1_gw5.js:1
↓ 77 callersMethodmodel_dump
(self, **kwargs)
litellm/types/llms/base.py:75
↓ 77 callersFunctionn
(e)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 77 callersMethodrun
( self, cmd: Sequence[str], *, env: Mapping[str, str] | None = None, c
tests/unit/llms/pi/harness/test_transformation.py:152
↓ 77 callersFunctionsleep
(_: float)
tests/unit/llms/soniox/realtime/test_soniox_realtime_transformation.py:709
↓ 76 callersFunction_bridge_server
(**overrides)
tests/unit/proxy/mcp_server/test_discoverable_endpoints.py:5581
↓ 76 callersMethodbody
The Anthropic error envelope Python's `AnthropicExceptionMapping` builds: an upstream body already in that shape passes through, any other has its mes
litellm-rust/crates/gateway-inference/src/error.rs:113
↓ 76 callersMethodfetchall
(self)
tests/unit/litellm_proxy_extras/test_litellm_proxy_extras_utils.py:952
↓ 76 callersFunctionfresh
A scripted outcome that raises a new error per call.
tests/unit/test_router/core/retries_health_helpers.py:27
↓ 76 callersMethodgroup
(self)
tests/e2e/idp.py:122
↓ 76 callersMethodmanagement_headers
(self, caller_key: str | None = None, *, transport: Transport | None = None)
tests/e2e/proxy_client.py:484
↓ 76 callersMethodmutate
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 76 callersFunctionx
(e,t,a,n)
litellm/proxy/_experimental/out/_next/static/chunks/2rtlqswx6sz6u.js:1
↓ 75 callersFunction_bedrock_converse_messages_pt
Converts given messages from OpenAI format to Bedrock format - Roles must alternate b/w 'user' and 'model' (same as anthropic -> merge conse
litellm/litellm_core_utils/prompt_templates/factory.py:5498
↓ 75 callersMethodadd
Append one model's outcome to the per-test results list. Use this when a single test exercises multiple Claude tiers concurrently and
tests/e2e/claude_code/conftest.py:96
↓ 75 callersFunctionanthropic_labels
(request: Request)
tests/integration/providers/_cache_control_marks_support.py:270
↓ 75 callersMethodcount_tokens
( self, model_to_use: str, messages: object, contents: object, deploym
tests/unit/proxy/test_proxy_token_counter.py:1693
↓ 75 callersMethoddelete_key
(self, key: str)
tests/e2e/logging/logging_client.py:334
↓ 75 callersMethodhandle_llm_api_exception
Raises ProxyException (OpenAI API compatible) if an exception is raised
litellm/proxy/common_request_processing.py:4612
↓ 75 callersFunctionin_fresh_context
Run ``fn`` in its own context so one test's destinations never leak.
tests/unit/integrations/otel/test_otel_v2_destinations.py:119
↓ 75 callersMethodmodel_dump
(self)
litellm/proxy/management_endpoints/ui_sso.py:244
↓ 75 callersMethodpre_call_hook
(self, user_api_key_dict, data, call_type, guardrails_only=False)
tests/unit/proxy/openai_files_endpoint/test_batch_guardrails.py:583
↓ 75 callersFunctionreplace
(s,o,i)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 75 callersMethodselect
(e,t,r,n)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 75 callersFunctionwithin
(future: impl Future<Output = T>)
litellm-rust/crates/gateway-forward/tests/support/mod.rs:31
↓ 74 callersMethodasearch
`_asearch_with_fallbacks`: the search tool name (``search_tool_name``, else ``model``) routes as the model; the factory wrapper drops ``custom
litellm/router_rust/invoke/endpoints.py:2357
↓ 74 callersMethodcalls_to
(self, op: str | None = None)
tests/unit/test_router/core/scripted_host.py:303
↓ 74 callersFunctioncommon_checks
Common checks across jwt + key-based auth. 1. If team is blocked 1.1. If project is blocked 2. If team can call model 2.2 If pro
litellm/proxy/auth/auth_checks.py:1137
↓ 74 callersMethodexpose
(&self)
litellm-rust/crates/secret-value/src/secret_value.rs:14
↓ 74 callersMethodget_custom_headers
( *, user_api_key_dict: UserAPIKeyAuth, call_id: str | None = None, model_id:
litellm/proxy/common_request_processing.py:2384
↓ 74 callersMethodget_local
(self, entry: RateLimitEntry)
tests/unit/redis/stores/fake_rate_limits.py:129
↓ 74 callersMethodis_empty
(&self)
litellm-rust/crates/router-core/src/fallback.rs:141
↓ 74 callersMethodlist
(e,t={},r)
litellm/proxy/_experimental/out/_next/static/chunks/2hk8n3azev--d.js:11
↓ 74 callersFunctionp
()
litellm/proxy/_experimental/out/_next/static/chunks/2rtlqswx6sz6u.js:1
↓ 74 callersFunctionrequire_successful_call
A call that should have succeeded but didn't is a hard failure, never a skip: if the proxy can't make a call it's expected to, the test must fail.
tests/e2e/e2e_http.py:254
↓ 74 callersFunctionresponses_api_bridge_check
( model: str, custom_llm_provider: str, web_search_options: OpenAIWebSearchOptions | None = None,
litellm/responses/bridge_check.py:151
↓ 74 callersFunctiont
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:8
↓ 74 callersMethodto_str
(self, pretty: bool = False)
litellm/litellm_core_utils/tokenizer.py:260
← previousnext →501–600 of 202,479, ranked by callers