MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 114 callersFunctionread_request_body
Safely read the request body and parse it as JSON. Parameters: - request: The request object to read the body from Returns: - d
litellm/proxy/common_utils/http_parsing_utils.py:265
↓ 114 callersMethodutcnow
(cls)
tests/unit/proxy/common_utils/test_reset_budget_job.py:4067
↓ 113 callersFunction_logger
(legacy_compat=True, team_metadata_keys=None)
tests/unit/integrations/otel/test_otel_v2_logger.py:129
↓ 113 callersFunction_one
(make_core: MakeCore, **arguments: object)
tests/unit/test_router/core/test_construction_precall_characterization.py:55
↓ 113 callersMethodget_allowed_tools_for_server
Get list of allowed tool names for a specific server based on key/team permissions. Follows same inheritance logic as get_allowed_mcp
litellm/proxy/mcp_server/auth/user_api_key_auth_mcp.py:3244
↓ 112 callersFunctionmcp_peer
( transport: Literal["http", "sse"] = "http", *, rich: bool = False, on_slow: Callable[[], None] | None =
tests/integration/_support/mcp.py:278
↓ 112 callersFunctiontool_calls
(peer: McpPeer)
tests/integration/mcp/test_mcp_user_env_vars.py:82
↓ 111 callersFunction_codes
(tmp_path, source)
tests/unit/test_check_type_discipline.py:26
↓ 111 callersMethodfrom_standard_logging_payload
(cls, payload: StandardLoggingPayload)
litellm/integrations/otel/model/payloads.py:154
↓ 111 callersFunctionrecord_vcr_outcome
Call from the post-yield section of an autouse fixture per test.
tests/_vcr_conftest_common.py:1746
↓ 111 callersMethodtime
(self)
tests/_support/clock_loops.py:14
↓ 110 callersMethodany
(self)
litellm-rust/crates/llms/src/base_llm/messages/context.rs:21
↓ 110 callersMethoddeployments
( self, model_name: str | None = None, *, source: Literal["group"] = "group",
litellm/router_api.py:426
↓ 110 callersMethoditems
(self)
litellm/router_strategy/budget_limiter.py:121
↓ 109 callersFunctioncomplete
(core: RouterCore, model: str = "a", **request: object)
tests/unit/test_router/core/fallbacks_helpers.py:27
↓ 109 callersMethoddecode
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2hk8n3azev--d.js:1
↓ 108 callersMethodload
(*, access_group_id: str, **_: object)
tests/unit/proxy/mcp_server/auth/test_user_api_key_auth_mcp.py:11708
↓ 107 callersMethodempty
(cls, bounds: tuple[float, ...])
litellm/telemetry/histogram.py:21
↓ 107 callersFunctioninstall_live_call_probe
Activate the live-call socket probe for non-VCR-marked tests. Call this from inside the per-test autouse ``_vcr_outcome_gate`` fixture *befor
tests/_vcr_conftest_common.py:1803
↓ 107 callersMethodparse
(self)
tests/unit/llms/azure/test_azure.py:27
↓ 107 callersMethodunion
(self, other: Self)
litellm-rust/crates/llms-types/src/providers/anthropic/beta.rs:461
↓ 107 callersMethodwarning
The warning a set value earns, or `None` when the setting is read, refused or already met.
litellm-rust/crates/redis-resolve/src/keys.rs:84
↓ 106 callersMethodparse
(self)
tests/integration/providers/test_provider_lookup_status.py:278
↓ 106 callersMethodsend
(&mut self, bytes: impl AsRef<[u8]>)
litellm-rust/crates/gateway-forward/tests/support/mod.rs:196
↓ 106 callersFunctionwrite_rows
(query: LiteralString, parameters: tuple[str, ...], *, database_url: str | None = None)
tests/integration/_support/database.py:24
↓ 105 callersMethoddrain
(self)
tests/integration/routing/test_video_poll_routing_wire.py:107
↓ 105 callersFunctionnew_marker
()
tests/integration/providers/_cache_control_marks_support.py:53
↓ 104 callersFunctionmake_handler
Factory for test handlers with standard defaults.
tests/unit/proxy/guardrails/guardrail_hooks/test_panw_prisma_airs.py:120
↓ 103 callersFunction_marker
()
tests/integration/providers/test_malformed_tools_wire.py:96
↓ 103 callersMethodappend
(self, value: object)
litellm/router_rust/surface/indexes.py:101
↓ 103 callersMethodcontains
(&self, key: &str)
litellm-rust/crates/redis-store/src/request.rs:45
↓ 103 callersMethoddelete_model
(self, model_id: str)
tests/e2e/logging/logging_client.py:483
↓ 103 callersMethodget_allowed_mcp_servers
(self, user_api_key_auth: UserAPIKeyAuth)
tests/unit/proxy/mcp_server/test_server_resolution.py:58
↓ 103 callersMethodsend
Sends one command on its own, the way the `RedisCache` method behind it sends it.
litellm-rust/crates/redis-client/src/client.rs:89
↓ 102 callersFunctiondate
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 102 callersFunctiongenerate_mock_mcp_server_db_record
Generate a mock MCP server record from database
tests/unit/proxy/management_endpoints/test_mcp_management_endpoints.py:51
↓ 102 callersFunctionget_compiled_pattern
Get a compiled regex pattern by name. Args: pattern_name: Name of the prebuilt pattern Returns: Compiled regex pattern
litellm/proxy/guardrails/guardrail_hooks/litellm_content_filter/patterns.py:100
↓ 102 callersMethodkey
(self)
tests/integration/routing/test_vllm_passthrough_stream_usage_settings.py:51
↓ 102 callersMethodlstrip
(self)
litellm/litellm_core_utils/tokenizer.py:409
↓ 101 callersMethoddecode
(self, tokens: Sequence[int], errors: str = "replace")
litellm/litellm_core_utils/tokenizer.py:156
↓ 101 callersMethoddecode
(self)
litellm/llms/bedrock/common_utils.py:2549
↓ 101 callersMethodinsert
(&self, key: K, value: V)
litellm-rust/crates/secrets-types/src/cache.rs:62
↓ 100 callersFunction_mock_logging
()
tests/unit/litellm_core_utils/test_realtime_streaming.py:41
↓ 100 callersMethodprocess_input_messages
(self, data, guardrail_to_apply, litellm_logging_obj)
tests/unit/proxy/utils/proxy_logging/test_guardrail_pipeline.py:3646
↓ 100 callersMethodsplice
(e,t,n)
litellm/proxy/_experimental/out/_next/static/chunks/14v3irtjifjt2.js:1
↓ 100 callersMethodtext
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 99 callersMethodlock
( &self, )
litellm-rust/crates/inference-ocr/tests/support/mod.rs:155
↓ 99 callersFunctiono
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 99 callersMethodraise_for_status
(self)
litellm/proxy/guardrails/guardrail_hooks/pillar/pillar.py:61
↓ 98 callersMethodasync_post_call_streaming_iterator_hook
(self, user_api_key_dict, response, request_data)
tests/unit/proxy/guardrails/test_deferred_guardrail_logging.py:987
↓ 97 callersFunction_make_guardrail
Helper to construct a guardrail with test defaults.
tests/unit/proxy/guardrails/guardrail_hooks/test_microsoft_purview.py:22
↓ 97 callersMethodadd_litellm_callback
Add a callback to litellm.callbacks Ensures no duplicates are added.
litellm/litellm_core_utils/logging_callback_manager.py:66
↓ 97 callersMethodextend
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2hk8n3azev--d.js:14
↓ 97 callersFunctioni
({href:e,className:t})
litellm/proxy/_experimental/out/_next/static/chunks/30kytutlzx6eq.js:1
↓ 96 callersMethodadd
(team_id: str, user_info: NewUserResponse | LiteLLM_UserTable)
tests/unit/proxy/management_endpoints/test_ui_sso.py:6814
↓ 96 callersMethodall
In the order ``_select_pre_routing_strategy`` searches them.
litellm/router_rust/steps/prerouting.py:204
↓ 96 callersMethodcreate_model
(self, model_name: str, litellm_params: LiteLLMParamsBody)
tests/e2e/logging/logging_client.py:479
↓ 96 callersFunctionencode_video_id_with_provider
Encode provider and model_id into video_id using base64.
litellm/types/videos/utils.py:63
↓ 96 callersFunctionr
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2rtlqswx6sz6u.js:1
↓ 95 callersMethodadd
(self, input_tokens: int, output_tokens: int, cost: float)
tests/unit/harness/core_fakes.py:113
↓ 95 callersMethodgroup
(self, name: str, *, field: str = "info")
tests/unit/proxy/batches_endpoints/test_litellm_executed_batches.py:264
↓ 94 callersMethodbase_process_llm_request
Run the request, sending SSE keepalives while the upstream is still silent. Everything below this point, the upstream call included, happens
litellm/proxy/common_request_processing.py:3126
↓ 94 callersMethodfill
(&mut self)
litellm-rust/crates/gateway-forward/tests/support/mod.rs:286
↓ 94 callersMethodflush_queue
Snapshot, send, and drain in one consistent step. Overrides the base implementation so the same snapshot drives both the HTTP send an
litellm/integrations/rubrik.py:1082
↓ 93 callersMethodadd
(self, value: float | None)
litellm/telemetry/histogram.py:24
↓ 93 callersMethodapi_base
(self)
tests/integration/_support/upstream.py:870
↓ 93 callersMethodasync_pre_call_hook
(self, user_api_key_dict, cache, data, call_type)
tests/unit/proxy/test_proxy_utils.py:3257
↓ 93 callersMethodflatten
(e=e=>e.message)
litellm/proxy/_experimental/out/_next/static/chunks/2j7hjtph8n74b.js:1
↓ 93 callersFunctionre
litellm/proxy/_experimental/out/_next/static/chunks/1f2vcab0yti03.js:2
↓ 93 callersMethodroute
(self, scenario_id: str, suffix: str)
tests/integration/providers/test_provider_lookup_status.py:165
↓ 92 callersFunction_llm_response
Build a fake acompletion response with the given message content.
tests/unit/router_strategy/test_complexity_router.py:2679
↓ 92 callersFunctiona
(e)
litellm/proxy/_experimental/out/_next/static/chunks/0r8bcbns1_gw5.js:1
↓ 92 callersMethodchunk_parser
(self, chunk: dict)
litellm/llms/cohere/common_utils.py:130
↓ 92 callersMethodcount
(litellm_params: dict[str, str])
tests/unit/llms/openai/test_openai_workload_identity.py:1751
↓ 92 callersFunctionfield
(name: &str, value: Option<&str>)
litellm-rust/crates/cache-response/tests/caching.rs:8
↓ 92 callersMethodopen
(cls, prisma: "PrismaClient")
litellm/repositories/database.py:19
↓ 91 callersFunction_make_guardrail
( inspection_type="chat", event_hook="pre_call", *, name="t", api_key="x", default_on=
tests/unit/proxy/guardrails/guardrail_hooks/_cisco_ai_defense_test_utils.py:228
↓ 91 callersFunctiond
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2s7apn3nfa3q3.js:1
↓ 91 callersFunctionhandle_exception_on_proxy
Returns an Exception as ProxyException, this ensures all exceptions are OpenAI API compatible
litellm/proxy/utils.py:9822
↓ 91 callersMethoditer
(&self)
litellm-rust/crates/llms-types/src/providers/anthropic/beta.rs:457
↓ 91 callersMethodslice
(e,t=this.content.size,n=!1)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 91 callersMethodstatus
(self)
tests/unit/proxy/roi_calculator/test_sync.py:559
↓ 90 callersMethodadd
(s,o)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 90 callersFunctionchat_stream
A stream of ``texts`` (one chunk each). With ``error``, raises it after ``fail_after`` chunks (default: after every text chunk, before the fi
tests/unit/test_router/core/streaming_helpers.py:161
↓ 90 callersMethodexists
(self, name: str)
tests/e2e/migrations/database.py:71
↓ 90 callersFunctionget_litellm_params
( api_key: str | None = None, force_timeout=600, azure=False, logger_fn=None, verbose=Fals
litellm/litellm_core_utils/get_litellm_params.py:172
↓ 90 callersFunctionhandleResponse
(resp *http.Response, action string)
terraform/provider/litellm/resource_team.go:558
↓ 90 callersMethodlist
List all API keys with optional filtering and pagination. Args: page (Optional[int]): Page number for pagination
litellm/proxy/client/keys.py:41
↓ 90 callersFunctionscratch_database
(prefix: str = "integration")
tests/integration/_support/database.py:30
↓ 89 callersFunctionMixin
(...s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 89 callersMethodget_provider_responses_api_config
( provider: LlmProviders | str, model: str | None = None, api_base: str | None = None,
litellm/utils.py:10638
↓ 89 callersFunctionhandleError
(errorData: string | any)
ui/litellm-dashboard/src/components/networking.tsx:438
↓ 89 callersMethodload_yaml
(self, mapping: Mapping[str, JsonValue])
litellm/proxy/config_resolvers/settings_store.py:54
↓ 89 callersMethodnext
( &self, py: Python<'py>, outcome: Option<Bound<'py, PyAny>>, )
litellm-rust/crates/python-bridge/src/router/mod.rs:1091
↓ 89 callersFunctionserver_error
(model: str = "gpt-4o")
tests/unit/test_router/core/scripted_host.py:137
↓ 89 callersFunctiontest
()
tests/unit/proxy/management_endpoints/test_key_generate_prisma.py:236
↓ 89 callersMethodupdate
(self, *, where: dict[str, str], data: dict[str, object])
tests/unit/proxy/mcp_server/test_db_credentials.py:506
↓ 89 callersMethodupdate_environment
( self, prisma_client: PrismaClient | None, user_api_key_cache: UserApiKeyCache,
litellm/proxy/auth/handle_jwt.py:287
↓ 88 callersFunctionbuilder
uvicorn closes a client connection that sits idle for `--keepalive_timeout` between requests. Without the same limit, a client that vanishes without c
litellm-rust/crates/gateway-forward/src/server.rs:96
↓ 88 callersMethoddiscard
(self, key: str, payload: bytes)
tests/e2e/provider_cache.py:127
← previousnext →401–500 of 202,479, ranked by callers