MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 5 callersFunctioneq
litellm/proxy/_experimental/out/_next/static/chunks/0-i21ejarohtj.js:1
↓ 5 callersFunctioner
litellm/proxy/_experimental/out/_next/static/chunks/2n5r7czpxrc08.js:1
↓ 5 callersFunctionerrorRate
(failed: number, total: number)
ui/litellm-dashboard/src/app/(dashboard)/usage/_components/components/errors/errorsData.ts:69
↓ 5 callersFunctionerror_frame
(status: int, message: str)
tests/integration/_support/anthropic_sse.py:108
↓ 5 callersFunctiones
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/11et800l-khs-.js:1
↓ 5 callersMethodestimate
(self, pull: ROIPullEvidence)
litellm/proxy/roi_calculator/estimator.py:106
↓ 5 callersFunctionet
(e)
litellm/proxy/_experimental/out/_next/static/chunks/0dvgjd47fte1d.js:2
↓ 5 callersFunctioneu
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2hk8n3azev--d.js:1
↓ 5 callersFunctioneval
(py: Python<'py>, source: &std::ffi::CStr)
litellm-rust/crates/python-bridge/src/preflight.rs:145
↓ 5 callersFunctioneval
(py: Python<'py>, source: &std::ffi::CStr)
litellm-rust/crates/host-python/src/file_reader.rs:87
↓ 5 callersMethodeval
(self, script: str, numkeys: int, *args: str | bytes | int)
tests/e2e/provider_cache_redis.py:67
↓ 5 callersFunctionevaluate
(head: Counts, base: Counts, caps: Counts = NO_CAPS)
scripts/lint_base_counts.py:322
↓ 5 callersFunctionevent_stream
(bytes: ByteStream)
litellm-rust/crates/llms/src/base_llm/messages/streaming.rs:14
↓ 5 callersFunctionevict_shared
Drop cached objects from the cache's memory and, when it has one, its Redis layer, in one chunked round trip. Runs right after ``evict_l
litellm/proxy/common_utils/auth_cache_invalidation_pubsub.py:197
↓ 5 callersMethodexact_true
(&self)
litellm-rust/crates/python-bridge/src/coercion.rs:159
↓ 5 callersFunctionexchange_token
( client: HTTPHandler, config: OAuthTokenExchangeConfig, subject_token: str, timeout: float |
litellm/litellm_core_utils/oauth_token_exchange.py:254
↓ 5 callersFunctionexec_config
(sandbox, index=0)
tests/unit/llms/opencode/harness/test_transformation.py:208
↓ 5 callersMethodexecute
(self)
litellm/proxy/common_utils/config_sync_pubsub.py:33
↓ 5 callersFunctionexpectUiRoute
(page: PlaywrightPage, segment: string)
tests/e2e/ui/helpers/navigation.ts:20
↓ 5 callersMethodexpire
(self, name: str, time: int)
litellm/caching/redis_cache.py:85
↓ 5 callersMethodexport
(self, report: Report)
tests/unit/telemetry/test_aggregate.py:31
↓ 5 callersMethodexported_generation_metadata
The generation's metadata as langfuse receives it, one attribute per key. v4 serializes each value onto the span, so they are decoded back he
tests/unit/integrations/test_langfuse.py:621
↓ 5 callersMethodextension
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 5 callersFunctionextract
(s,o)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 5 callersFunctionextractErrorMessage
(err: unknown)
ui/litellm-dashboard/src/utils/errorUtils.ts:12
↓ 5 callersFunctionextract_cache_creation_tokens
Cache-write tokens from a logged usage object, whatever shape recorded them. Anthropic writes a top-level ``cache_creation_input_tokens``; OpenAI
litellm/litellm_core_utils/llm_cost_calc/cache_tokens.py:26
↓ 5 callersFunctionextract_cache_read_tokens
Cache-read tokens from a logged usage object, whatever shape recorded them. Anthropic writes a top-level ``cache_read_input_tokens``; OpenAI-comp
litellm/litellm_core_utils/llm_cost_calc/cache_tokens.py:5
↓ 5 callersFunctionextract_chatgpt_account_id
(token: str | None)
litellm/llms/chatgpt/common_utils.py:283
↓ 5 callersFunctionextract_file_access_credentials
Extract credentials from litellm_params for file access operations. This method extracts relevant authentication and configuration parameter
litellm/batches/batch_utils.py:615
↓ 5 callersMethodextract_model_from_url
(url: str)
litellm/proxy/pass_through_endpoints/llm_provider_handlers/gemini_passthrough_logging_handler.py:321
↓ 5 callersMethodextract_request_path
(request_data: Mapping[str, object])
litellm/proxy/guardrails/guardrail_hooks/akto/akto.py:346
↓ 5 callersFunctionextract_search_results_text
Extract model-visible text from OpenAI tool-message ``search_results``. Used by token estimators and TPM limiters so large search result pay
litellm/litellm_core_utils/prompt_templates/common_utils.py:309
↓ 5 callersMethodextract_tool_call_details
Extract tool name, arguments, and call_id from a tool call.
litellm/responses/mcp/litellm_proxy_mcp_handler.py:643
↓ 5 callersFunctionf
(o,i,a)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 5 callersFunctionf
litellm/proxy/_experimental/out/_next/static/chunks/1a2lzi3ursud4.js:1
↓ 5 callersFunctionf
()
litellm/proxy/_experimental/out/_next/static/chunks/2j96ftcthirif.js:141
↓ 5 callersFunctionf
litellm/proxy/_experimental/out/_next/static/chunks/0_6jqgnorqxl2.js:1
↓ 5 callersFunctionf5
()
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:10
↓ 5 callersFunctionfailure
(kind: FailureKind, status: u16)
litellm-rust/crates/router-core/tests/call_loop.rs:186
↓ 5 callersFunctionfake_llm_call
()
tests/unit/proxy/test_proxy_server_endpoints_and_startup.py:10908
↓ 5 callersFunctionfallback_target_model_name
(target: object)
litellm/proxy/auth/auth_utils.py:716
↓ 5 callersFunctionfan_out_provider
The provider :func:`publish_global_otel_v2_provider` gave the tenant fan-out. Read off the publish itself, not the OTel global and not the regist
litellm/integrations/otel/logger.py:1045
↓ 5 callersMethodfeed
(self, chunk: bytes)
tests/integration/_support/database_relay.py:195
↓ 5 callersFunctionfetch_cli_sso_team_details
``None`` means the lookup itself failed, which is not the same as the user having no teams.
litellm/proxy/management_endpoints/ui_sso.py:2507
↓ 5 callersFunctionfetch_global_spend_with_event_coordination
Fetch global spend with event-driven coordination to prevent cache stampede. Uses EventDrivenCacheCoordinator: first request queries DB and s
litellm/proxy/auth/user_api_key_auth.py:1436
↓ 5 callersFunctionfetch_model_listing
( base_url: str, api_key: str, *, get: Callable[..., requests.Response] = requests.get, he
litellm/proxy/client/cli/commands/pi.py:94
↓ 5 callersFunctionfetch_openai_daily_costs
USD billed by OpenAI per UTC day (ISO date) over the closed range, following pagination to the end.
litellm/llms/openai/organization_costs.py:81
↓ 5 callersFunctionfetcher
( pinned_address: SocketAddr, blocked_hosts: HashSet<&'static str>, url_policy: UrlPol
litellm-rust/crates/http/src/media.rs:436
↓ 5 callersMethodfields
(&self, key: &str)
litellm-rust/crates/model-catalog/src/catalog.rs:78
↓ 5 callersMethodfields
(&self)
litellm-rust/crates/config/src/redis.rs:17
↓ 5 callersFunctionfile_retrieve
Returns the contents of the specified file. LiteLLM Equivalent of POST: POST https://api.openai.com/v1/files
litellm/files/main.py:345
↓ 5 callersFunctionfilter
`_pre_call_checks` over `candidates`; `pool` is the group's deployments before health filters (`request_deployments`), which decide whether nothing le
litellm-rust/crates/router-core/src/precall.rs:86
↓ 5 callersFunctionfilter_partitioned_spend_logs_diff
Drop statements from a `prisma migrate diff` script that fight the SpendLogs partitioning runbook (db_scripts/partition_spend_logs.sql): the p
litellm-proxy-extras/litellm_proxy_extras/utils.py:180
↓ 5 callersMethodfind_all_except
Find every model except the row currently being updated.
litellm/repositories/model_repository.py:106
↓ 5 callersMethodfind_by_id
(self, id_value: str)
tests/unit/proxy/management_endpoints/test_subscription_accounts.py:60
↓ 5 callersFunctionfind_category_file
First ``<name>.yaml`` or ``<name>.json`` across the category folders, or None. A name that would escape its folder (``../x``) never matches. A sy
litellm/proxy/guardrails/content_filter_data/__init__.py:28
↓ 5 callersMethodfind_first
( self, skip: int | None = None, where: Mapping[str, object] | None = None, cu
litellm/repositories/prisma_protocols.py:32
↓ 5 callersMethodfind_many
(self, where: Mapping[str, object])
litellm/proxy/management_endpoints/access_group_endpoints.py:121
↓ 5 callersMethodfind_spec
( self, fullname: str, path: Sequence[str] | None = None, target: ModuleType |
litellm/litellm_core_utils/deprecated_package.py:34
↓ 5 callersMethodfind_unique
(self, **kwargs: object)
tests/unit/proxy/agent_endpoints/test_endpoints.py:176
↓ 5 callersFunctionfinish
(py: Python<'_>, hooks: &mut H, step: HookStep<H, T>)
litellm-rust/crates/host-python/tests/hook_chain.rs:231
↓ 5 callersMethodfire
(&self, event: M::Event)
litellm-rust/crates/circuit-breaker/src/fsm.rs:39
↓ 5 callersFunctionfire_kill_switch
( *, agent_id: str, config: AgentKillSwitchConfig, http_client: KillSwitchHttpClient, time
litellm/proxy/agent_endpoints/kill_switch.py:186
↓ 5 callersFunctionfirst_match
The first rule that applies decides the class, as the `if`/`elif` chain does in Python.
litellm-rust/crates/core-utils/src/exception_mapping_utils/rules.rs:28
↓ 5 callersFunctionfixture_proc
(name: str, **kwargs)
tests/unit/llms/codex/harness/test_transformation.py:182
↓ 5 callersFunctionflip_entry_to_empty
Rewrite the stored response so ``field`` is ``[]`` and its id carries ``-stale``, keeping the encoding. Returns the stale id. The proxy worker th
tests/integration/caching/response_cache_case.py:317
↓ 5 callersMethodflush_in_memory_records
(self)
litellm/integrations/galileo.py:778
↓ 5 callersMethodflush_queue
Flush as usual, or report liveness when there is nothing to send. ``CustomBatchLogger`` skips an empty queue entirely, so without th
litellm/integrations/pointfive/logger.py:234
↓ 5 callersFunctionforecastModels
(tiers: ComplexityTiers, tier: string)
ui/litellm-dashboard/src/components/add_model/forecast_classifier_config.ts:104
↓ 5 callersFunctionforged_id
(provider: str, model: str, task_id: str, served: str | None)
tests/integration/providers/_dashscope_video_support.py:115
↓ 5 callersFunctionformatProdErrorMessage
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 5 callersFunctionformat_deprecation_alert_message
Render the alert for the deprecated and imminent buckets, None when both are empty Upcoming models are left out of the alert to keep it actionabl
litellm/proxy/common_utils/model_deprecation.py:370
↓ 5 callersFunctionfragment
(arguments: str, name: str | None = None, call_id: str | None = None)
tests/unit/litellm_core_utils/test_streaming_chunk_builder_utils.py:1421
↓ 5 callersFunctionframe
(identity: str, delta: dict, *, finish: str | None = None)
tests/integration/streaming/test_stream_contracts.py:28
↓ 5 callersFunctionfreeName
(taken: readonly string[], prefix: "option" | "question")
ui/litellm-dashboard/src/app/(dashboard)/playground/components/systemOneUI/lib/formPayload.ts:47
↓ 5 callersMethodfrom_pretrained
(identifier: str, revision: str = "main", token: str | None = None)
litellm/litellm_core_utils/tokenizer.py:255
↓ 5 callersMethodfully_blocked_model_names
Groups whose every deployment is paused (was ``get_fully_blocked_model_names``).
litellm/router_api.py:1344
↓ 5 callersFunctionfunction_tool
(name: str, description: str = "")
tests/integration/providers/test_responses_codex_repeated_additional_tools_wire.py:18
↓ 5 callersFunctionfunction_tools
()
tests/integration/_support/responses_stream.py:121
↓ 5 callersFunctiong
(e,i={})
litellm/proxy/_experimental/out/_next/static/chunks/218jq7ygtsrfo.js:1
↓ 5 callersFunctiong
({id:e,label:t,value:i,selectedLabel:a,feature:r,onValueChange:l,children:o})
litellm/proxy/_experimental/out/_next/static/chunks/2jxpy6eth1zvy.js:1
↓ 5 callersFunctiongate
(websocket: WebSocket, model: str, /)
litellm/proxy/pass_through_endpoints/llm_passthrough_endpoints.py:3581
↓ 5 callersFunctiongatewayUrl
()
ui/litellm-dashboard/src/components/publicModelHub/hubFormat.ts:122
↓ 5 callersFunctiongemini_texts
(raw: bytes)
tests/integration/observability/test_presidio_streaming_output.py:61
↓ 5 callersFunctiongenerateCodeSnippet
(params: GenerateCodeParams)
ui/litellm-dashboard/src/components/chat_ui/CodeSnippets.tsx:37
↓ 5 callersFunctiongenerate_container_endpoints
Generate all container endpoint functions from the JSON config. Returns a dict mapping function names to their implementations.
litellm/containers/endpoint_factory.py:194
↓ 5 callersFunctiongenerate_content
Generate content using Google GenAI
litellm/google_genai/main.py:308
↓ 5 callersFunctiongenerate_id
()
litellm/types/utils.py:142
↓ 5 callersFunctiongenerate_service_account_key_fn
Generate a Service Account API key based on the provided data. This key does not belong to any user. It belongs to the team. Why use a servi
litellm/proxy/management_endpoints/key_management_endpoints.py:2567
↓ 5 callersFunctionget
Get a credential by name
litellm/proxy/client/cli/commands/credentials.py:176
↓ 5 callersFunctionget
(s,o)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 5 callersFunctiongetAgentModelId
(agent: AgentModel)
ui/litellm-dashboard/src/app/(dashboard)/playground/components/chat_ui/AgentBuilderView.tsx:151
↓ 5 callersFunctiongetCustomTierRowsError
( customTierSet: CustomTierSet, t: TFunction = i18n.t.bind(i18n), )
ui/litellm-dashboard/src/components/add_model/tier_rows.ts:177
↓ 5 callersFunctiongetEntryOutcome
(entry: GuardrailInformation)
ui/litellm-dashboard/src/components/logs/detail/sections/GuardrailViewer/GuardrailViewer.tsx:141
↓ 5 callersFunctiongetFrameworks
(term: Term = keepTerminology)
ui/litellm-dashboard/src/data/compliancePrompts.ts:701
↓ 5 callersFunctiongetLanguage
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 5 callersFunctiongetLoggingOnlyScopeOptions
( directionalScopeSupported: boolean, t: TFunction = i18n.t.bind(i18n), )
ui/litellm-dashboard/src/app/(dashboard)/guardrails/_components/guardrail_info_helpers.tsx:208
↓ 5 callersMethodgetQueryState
(e)
litellm/proxy/_experimental/out/_next/static/chunks/0tx19jeq-wskb.js:2
↓ 5 callersFunctiongetToken
(serverId: string, userId?: string | null)
ui/litellm-dashboard/src/utils/mcpTokenStore.ts:44
↓ 5 callersFunctiongetUiConfig
()
ui/litellm-dashboard/src/components/networking.tsx:566
← previousnext →15,801–15,900 of 202,479, ranked by callers