MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 13 callersMethodrespond
(self, request: httpx.Request)
tests/unit/llms/anthropic/chat/test_anthropic_chat_handler.py:4365
↓ 13 callersFunctionreturn_raw_request
Return the json str of the request This is currently in BETA, and tested for `/chat/completions` -> `litellm.completion` calls.
litellm/utils.py:12000
↓ 13 callersMethodroute_matches_wildcard_pattern
Check if route matches the wildcard pattern eg. pattern: "/scim/v2/*" route: "/scim/v2/Users" - returns: Tr
litellm/proxy/auth/route_checks.py:655
↓ 13 callersMethodrows
(self)
tests/integration/providers/_idle_upstream_support.py:675
↓ 13 callersMethodrun
(&self, pipeline: &Pipeline)
litellm-rust/crates/redis-client/src/client.rs:178
↓ 13 callersMethodsameMarkup
(e)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 13 callersFunctionsanitize_oci_schema
Recursively remove OCI-incompatible fields from a JSON schema. Strips ``title`` keys, removes ``None``-valued ``default`` entries, normalises
litellm/llms/oci/common_utils.py:615
↓ 13 callersMethodscope
(self, operation: F)
litellm-rust/crates/python-bridge/src/redis/events.rs:41
↓ 13 callersMethodsdk
(self, prefix: str)
tests/integration/compatibility/test_fine_tuning_jobs.py:189
↓ 13 callersFunctionseal_state
(value: JsonValue, *, purpose: str, expires_at: int, now: int)
litellm/proxy/mcp_server/state_tokens.py:51
↓ 13 callersMethodserialize
Encode a value for DualCache / Redis (``json.dumps``-safe). If ``model_type`` is set, the payload is validated with that model, then
litellm/proxy/common_utils/cache_pydantic_utils.py:44
↓ 13 callersMethodsession_update_rejection
The error for a session.update this session cannot apply, or None when it applies.
litellm/llms/bedrock/realtime/transformation.py:529
↓ 13 callersMethodset_cache
``litellm_owned_client`` marks a client litellm built, so it may be closed once evicted.
litellm/caching/llm_caching_handler.py:56
↓ 13 callersMethodset_cache
(self, key: str, value: tuple[object, ...], *, ttl: float)
tests/unit/router_strategy/test_least_busy.py:596
↓ 13 callersFunctionsetup_for
(ctx: SessionContext)
tests/unit/llms/pi/harness/test_transformation.py:234
↓ 13 callersMethodsign_request
( self, headers: dict, optional_params: dict, request_data: dict, api_
litellm/llms/oci/chat/transformation.py:493
↓ 13 callersFunctionslug_for_test
Directory name for one test's interactions: a readable tail plus a short digest of the full node id, so same-named methods in different classes or
tests/e2e/fixture_bundle.py:120
↓ 13 callersFunctionspawn_logging_task
( running_loop: asyncio.AbstractEventLoop, coroutine: Coroutine[object, object, object], *, task_name: str
litellm/responses/streaming_iterator.py:225
↓ 13 callersFunctionstart_provider_edge
Boot an edge server on an OS-assigned port in a daemon thread. ``advertise_host`` is what api_base URLs name (it differs from the bind host wh
tests/e2e/provider_edge.py:1181
↓ 13 callersFunctionstore_engine
( poster, store: FileTokenStore, *, reader: Mapping[str, str] | None = None, clock: FakeCl
tests/unit/llms/base_llm/auth/test_shared_token_store.py:58
↓ 13 callersMethodstored_fallbacks
(self)
tests/unit/proxy/test_fallback_management_endpoints.py:312
↓ 13 callersFunctionstripHash
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 13 callersMethodsubmit
(self, fn: Callable[_P, _T], /, *args: _P.args, **kwargs: _P.kwargs)
litellm/litellm_core_utils/thread_pool_executor.py:47
↓ 13 callersFunctiontC
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2j7hjtph8n74b.js:5
↓ 13 callersFunctionteam
(id: &str)
litellm-rust/crates/redis-store/tests/spend_counters.rs:41
↓ 13 callersFunctionteamInfoCall
(accessToken: string, teamID: string | null, options?: { keyLimit?: number })
ui/litellm-dashboard/src/components/networking.tsx:1189
↓ 13 callersFunctionteam_admin_permissions
Grant team admins ``fields`` proxy-wide for the block, then restore the prior grant.
tests/integration/_support/client.py:347
↓ 13 callersMethodteam_key
(self, variables: Mapping[str, str])
tests/integration/observability/test_otel_team_sampling_across_pods.py:177
↓ 13 callersFunctionteam_metadata
(candidate: Gateway, team: str)
tests/integration/management/test_scim_group_pathless_patch.py:50
↓ 13 callersMethodthen
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/1f2vcab0yti03.js:2
↓ 13 callersMethodtitle
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 13 callersMethodto_http_exception
Convert this upstream-auth error into an ``HTTPException`` that preserves the upstream status code and any ``WWW-Authenticate`` challe
litellm/proxy/mcp_server/exceptions.py:59
↓ 13 callersFunctionto_litellm_batch
(batch: XAIBatch, endpoint: str = DEFAULT_BATCH_ENDPOINT)
litellm/llms/xai/batches/transformation.py:194
↓ 13 callersFunctiontool_search
(**fields: JsonValue)
tests/integration/providers/test_chat_completions_tool_search_wire.py:73
↓ 13 callersMethodtransform
(self, message: Mapping[str, JsonValue])
litellm/llms/meta/realtime/transformation.py:321
↓ 13 callersMethodtransform_anthropic_to_bedrock_count_tokens
Transform request to Bedrock CountTokens format. Supports both Converse and InvokeModel input types. Input (Anthropic format
litellm/llms/bedrock/count_tokens/transformation.py:108
↓ 13 callersMethodtransform_file_content_response
( self, raw_response: httpx.Response, logging_obj: LiteLLMLoggingObj, litellm_
litellm/llms/xai/files/transformation.py:244
↓ 13 callersMethodtransform_generate_content_request
( self, model: str, contents: GenerateContentContentListUnionDict, tools: Tool
litellm/llms/gemini/google_genai/transformation.py:346
↓ 13 callersMethodtransform_list_files_request
( self, purpose: str | None, optional_params: Mapping[str, object], litellm_pa
litellm/llms/xai/files/transformation.py:203
↓ 13 callersMethodtransform_request
( self, input: str, inference_params: dict[str, object], # mutable-ok: mirrors overri
litellm/llms/bedrock/embed/amazon_nova_transformation.py:207
↓ 13 callersFunctiontruncate_base64_in_messages
Return a copy of *messages* with long base64 data-URI payloads replaced by human-readable size placeholders.
litellm/litellm_core_utils/logging_utils.py:130
↓ 13 callersFunctionunavailable
(ids: Sequence[str], reason: str)
tests/integration/_support/safeguards_rig.py:394
↓ 13 callersMethodupdate_headers_with_optional_anthropic_beta
Update headers with optional anthropic beta.
litellm/llms/anthropic/chat/transformation.py:2376
↓ 13 callersFunctionupdate_messages_with_model_file_ids
Updates messages with model file ids. For managed files (unified file IDs), uses model_file_id_mapping if it resolves the id, otherwise
litellm/litellm_core_utils/prompt_templates/file_id_utils.py:50
↓ 13 callersFunctionupdate_response_metadata
Updates response metadata including hidden params and timing metrics Updates response metadata, adds the following: - response._hidde
litellm/litellm_core_utils/llm_response_utils/response_metadata.py:275
↓ 13 callersFunctionupdate_spend
Batch write updates to db. Triggered every minute. NOTE: This job now skips tag spend updates, which are handled by a separate sche
litellm/proxy/utils.py:8875
↓ 13 callersMethodupsert
(self, *, where: Mapping[str, object], data: Mapping[str, object])
litellm/proxy/utils.py:377
↓ 13 callersMethodupstream_body
(self, questions: Sequence[Mapping[str, JsonValue]])
tests/integration/providers/test_decisions_box_deployment_flag_wire.py:109
↓ 13 callersFunctionusd
(value: number)
ui/litellm-dashboard/src/app/(dashboard)/cost-optimization/_components/costOptimizationUtils.ts:8
↓ 13 callersFunctionusePath
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 13 callersFunctionuseSyntaxTheme
(light: SyntaxTheme)
ui/litellm-dashboard/src/hooks/useSyntaxTheme.ts:7
↓ 13 callersMethoduse_real_langfuse_client
Point the logger at an export channel whose spans land in memory.
tests/unit/integrations/test_langfuse.py:129
↓ 13 callersFunctionversion
Show the LiteLLM Proxy CLI and server version.
litellm/proxy/client/cli/main.py:235
↓ 13 callersFunctionvertex_model
(gateway: Gateway, scenario: Scenario, url: str, backend: str = "gemini-2.5-flash")
tests/integration/providers/_vertex_batch_rows.py:75
↓ 13 callersFunctionvisitor_visit
(s,o,{keyMap:i=Ku,...a}={})
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 13 callersFunctionwebsocket_close_reason
(message: str, fallback: str)
litellm/litellm_core_utils/realtime_errors.py:32
↓ 13 callersMethodwrite
(self, file_path: str, content: str)
litellm/llms/deepagents/harness/sandbox_backend.py:235
↓ 13 callersMethodwrite
(self, data: bytes)
tests/unit/harness/sandbox/test_docker.py:23
↓ 13 callersFunctionwrite_token_file
(directory: Path, content: str, name: str = "identity-token")
tests/unit/llms/anthropic/test_anthropic_wif.py:122
↓ 13 callersFunctionww
(e)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:333
↓ 12 callersFunctionEt
(t)
litellm/proxy/_experimental/out/_next/static/chunks/0cz1d0mv5g_q7.js:1
↓ 12 callersFunctionG
(s,o,i)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 12 callersFunctionWr
(t)
litellm/proxy/_experimental/out/_next/static/chunks/0cz1d0mv5g_q7.js:1
↓ 12 callersFunctionX
litellm/proxy/_experimental/out/_next/static/chunks/2j7hjtph8n74b.js:1
↓ 12 callersMethod__init__
(self, trace_id="trace-nova-sonic")
tests/unit/llms/bedrock/realtime/test_bedrock_realtime_handler.py:220
↓ 12 callersMethod__init__
(self)
tests/unit/llms/anthropic/chat/guardrail_translation/test_anthropic_guardrail_handler.py:3316
↓ 12 callersMethod__init__
(self)
tests/unit/llms/custom_httpx/test_llm_http_handler.py:1132
↓ 12 callersFunction_acquire
(**overrides)
tests/unit/integrations/langfuse/test_langfuse_sdk.py:733
↓ 12 callersMethod_acquire
(self, keys: list[str], args: list[object])
tests/unit/proxy/hooks/test_parallel_request_limiter_v3.py:8394
↓ 12 callersFunction_alias
()
tests/integration/spend/test_daily_activity_key_alias_probes.py:51
↓ 12 callersFunction_answer
(marker: str)
tests/integration/providers/test_bedrock_mantle_claude_chat_wire.py:61
↓ 12 callersFunction_answer
(tag: str)
tests/integration/providers/test_malformed_tools_wire.py:105
↓ 12 callersFunction_anthropic_stream
(text: str)
tests/unit/llms/base_llm/responses/test_transformation.py:778
↓ 12 callersFunction_anthropic_tool_use_turn
(*tool_use_ids)
tests/unit/llms/anthropic/messages/adapters/test_anthropic_messages_adapters_transformation.py:4632
↓ 12 callersFunction_assert_classifier_call
( call: Request, *, prompt: str, system: str | None = None, key: str = _API_KEY, endpoint: str | None = No
tests/integration/routing/test_complexity_router_databricks_classifier.py:215
↓ 12 callersFunction_assert_client_turns
( session: Session, observed: tuple[dict[str, JsonValue], ...], scenario_id: str, update: dict
tests/integration/providers/test_realtime_unguarded_voice_turns.py:445
↓ 12 callersFunction_assert_otel_destination_configured
Recorded state: the proxy reports the OTEL v2 logger among its active callbacks, so a missing/failed destination config fails here, before any
tests/e2e/logging/test_otel_trace_e2e.py:50
↓ 12 callersFunction_assert_search_call_output
(payload: Mapping[str, JsonValue], marker: str)
tests/integration/providers/test_responses_bridge_tool_search_wire.py:414
↓ 12 callersFunction_assert_served_only_by
(rows: list[SpendLogRow], allowed: frozenset[str], context: str)
tests/e2e/router/test_auto_router_regressions_e2e.py:198
↓ 12 callersFunction_assertion
(id_token: str, expires_in: timedelta | None = timedelta(minutes=30))
tests/unit/proxy/mcp_server/outbound_credentials/test_resolver.py:127
↓ 12 callersFunction_assistant_tool_call_msg
(*tool_call_ids)
tests/unit/litellm_core_utils/prompt_templates/test_litellm_core_utils_prompt_templates_common_utils.py:369
↓ 12 callersMethod_async_commands
(self)
litellm/caching/redis_cache.py:758
↓ 12 callersFunction_attrify
Wrap a dict so that attribute access (`.token`, `.user_id`, `.team_id`, etc.) works alongside the existing item-access the fake_reset_* helpe
tests/unit/proxy/common_utils/test_reset_budget_job.py:3717
↓ 12 callersFunction_authorization_values
(headers)
tests/unit/proxy/test_litellm_pre_call_utils.py:8751
↓ 12 callersFunction_await_span
(received: list[Request], destination: Wire, call_id: str)
tests/integration/observability/test_langfuse_delivery.py:471
↓ 12 callersFunction_b64
(raw: bytes)
tests/unit/proxy/guardrails/guardrail_hooks/test_ovalix_extraction.py:14
↓ 12 callersMethod_base_kwargs
Return minimal kwargs for set_attributes with Responses API defaults.
tests/unit/integrations/test_opentelemetry.py:4350
↓ 12 callersFunction_batch_output_row
(provider: str, *, size_bytes: int, fallback: bool)
tests/unit/enterprise/proxy/hooks/test_managed_files.py:2481
↓ 12 callersFunction_before_record_request
Fingerprint API keys, scrub them, and normalize multipart boundaries. Order matters in two ways: 1. vcrpy's ``filter_headers`` config option
tests/_vcr_conftest_common.py:908
↓ 12 callersMethod_billing_patches
Patch the cost path a batch runs through, journalling the results fetch and the spend-log write. during_fetch runs while the output file is be
tests/unit/proxy/common_utils/test_check_batch_cost.py:3262
↓ 12 callersFunction_block
(summary: str)
tests/integration/providers/test_responses_compaction_items_wire.py:87
↓ 12 callersFunction_block_reason
(guardrail: CustomCodeGuardrail)
tests/unit/proxy/guardrails/test_custom_code_security.py:469
↓ 12 callersFunction_body
(request: Request)
tests/integration/providers/test_databricks_agent_wire.py:100
↓ 12 callersFunction_body
( model: str, messages: Sequence[JsonValue], *, stream: bool = False, **extra: JsonValue )
tests/integration/providers/test_responses_bridge_tool_search_replay.py:105
↓ 12 callersFunction_body
(request: Request)
tests/integration/routing/test_model_capability_flags.py:79
↓ 12 callersFunction_browser
()
tests/integration/authorization/test_cli_sso_login_ui_disabled.py:194
↓ 12 callersFunction_bucket
(metrics: SpendMetrics, keys: dict[str, SpendMetrics] | None = None)
tests/unit/proxy/management_endpoints/test_ptu_consumption.py:42
↓ 12 callersFunction_budget_model_candidates
Names a budget may be configured under for a request on `model`, most specific first. Beyond the model as sent, a budget may be keyed on the mode
litellm/proxy/hooks/model_max_budget_limiter.py:590
↓ 12 callersFunction_build_call
A captured success-call (kwargs, response_obj, start, end) that exercises every one of the six metrics: usage for token.usage, response_cost for c
tests/unit/integrations/otel/test_otel_v2_metrics.py:94
↓ 12 callersMethod_build_config
( providers: list[dict], env_vars: dict[str, str], master_key: str, )
litellm/setup_wizard.py:495
← previousnext →5,101–5,200 of 202,479, ranked by callers