MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 7 callersFunctiontotal_deadline
Bound the block by ``seconds``: past it the block is cancelled and ``TotalTimeoutExpired`` raised, while a ``TimeoutError`` raised inside the bloc
litellm/litellm_core_utils/total_deadline.py:177
↓ 7 callersFunctiontranscribe_job_access_refusal
( job_name: object, user_api_key_dict: UserAPIKeyAuth, get_job: JobLookup )
litellm/proxy/pass_through_endpoints/llm_provider_handlers/transcribe_passthrough_logging_handler.py:325
↓ 7 callersFunctiontransform
(litellm_params: dict)
tests/unit/llms/bedrock/chat/test_converse_transformation.py:10301
↓ 7 callersFunctiontransform
(model, parsed_chunk, logging_obj)
tests/unit/responses/test_streaming_iterator_error_events.py:367
↓ 7 callersMethodtransform
()
tests/unit/llms/watsonx/rerank/test_watsonx_rerank.py:238
↓ 7 callersMethodtransform_container_file_content_request
Transform the container file content request for OpenAI API. OpenAI API expects the following request: - GET /v1/containers/{containe
litellm/llms/openai/containers/transformation.py:327
↓ 7 callersMethodtransform_container_retrieve_request
Transform the OpenAI container retrieve request.
litellm/llms/openai/containers/transformation.py:224
↓ 7 callersMethodtransform_decisions_request
( self, model: str, request: DecisionsIRRequest, custom_llm_provider: str,
litellm/llms/openai/decisions/transformation.py:367
↓ 7 callersMethodtransform_extra_body
( self, extra_body: Mapping[str, object], request: Mapping[str, object], model
litellm/llms/sail/chat/transformation.py:63
↓ 7 callersMethodtransform_image_generation_request
Transform the image generation request to Gemini format For Gemini 2.5 Flash Image Preview, use the standard Gemini format with resp
litellm/llms/gemini/image_generation/transformation.py:120
↓ 7 callersFunctiontransform_openai_messages_to_gemini_context_caching
( model: str, messages: list[AllMessageValues], custom_llm_provider: Literal["vertex_ai", "vertex_
litellm/llms/vertex_ai/context_caching/transformation.py:146
↓ 7 callersMethodtransform_request
( self, model: str, messages: list[AllMessageValues], optional_params: dict,
litellm/llms/bedrock/chat/converse_transformation.py:2397
↓ 7 callersMethodtransform_request
Transform the request for Bedrock Moonshot AI models. Uses the Moonshot transformation logic which handles: - Converting con
litellm/llms/bedrock/chat/invoke_transformations/amazon_moonshot_transformation.py:134
↓ 7 callersMethodtransform_request_to_count_tokens
Transform request to OpenAI Responses API token counting format. The Responses API uses `input` (not `messages`) and `instructions`
litellm/llms/openai/responses/count_tokens/transformation.py:176
↓ 7 callersMethodtransform_session_setup
(self, ctx: SessionContext, private_dir: str)
litellm/llms/pi/harness/transformation.py:462
↓ 7 callersMethodtransform_stream_line
Usage on message_update is ignored on purpose: the session endpoint accounts it.
litellm/llms/pi/harness/transformation.py:530
↓ 7 callersMethodtransform_video_create_request
( self, model: str, prompt: str, api_base: str, video_create_optional_
litellm/llms/hosted_vllm/videos/transformation.py:185
↓ 7 callersMethodtransform_video_list_request
( self, api_base: str, litellm_params: GenericLiteLLMParams, headers: dict, #
tests/integration/_support/custom_video_provider.py:124
↓ 7 callersMethodtransform_video_status_retrieve_response
( self, raw_response: httpx.Response, logging_obj: object, custom_llm_provider
litellm/llms/fal_ai/videos/transformation.py:486
↓ 7 callersFunctiontranslateOptions
(items: readonly OptionItem<V>[], t: TFunction)
ui/litellm-dashboard/src/app/(dashboard)/guardrails/_components/content_filter/action_options.ts:19
↓ 7 callersMethodtranslate_completion_to_generate_content
Transform litellm completion response to Google GenAI generate_content format Args: response: ModelResponse from litellm
litellm/google_genai/adapters/transformation.py:643
↓ 7 callersMethodtranslate_responses_chunk_to_openai_stream
Translate a Responses API streaming chunk to OpenAI chat completion streaming format. Args: parsed_chunk: Dict containin
litellm/completion_extras/litellm_responses_transformation/transformation.py:2187
↓ 7 callersMethodtranslate_thinking_for_model
Translate Anthropic thinking parameter based on the target model. For Claude/Anthropic models: returns {'thinking': <original_thinki
litellm/llms/anthropic/messages/adapters/transformation.py:847
↓ 7 callersFunctiontrusted_sql
(sql: str)
litellm/proxy/db/db_transaction_queue/spend_logs_partition_manager.py:143
↓ 7 callersFunctiontuning_quota_violation
Why a change to candidate tuning exceeds the baseline-relative free quota.
litellm/router_strategy/auto_router/auto_router_tuning_baseline.py:156
↓ 7 callersFunctionu
(e)
litellm/proxy/_experimental/out/_next/static/chunks/0ayyip3c-drm1.js:1
↓ 7 callersFunctionu
(e)
litellm/proxy/_experimental/out/_next/static/chunks/14v3irtjifjt2.js:1
↓ 7 callersFunctionul
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:10
↓ 7 callersFunctionunwrap_custom_tool_arguments
Extract the raw content string from JSON-wrapped arguments. The bridge converts custom tools to function tools with schema ``{"properties": {
litellm/responses/litellm_completion_transformation/custom_tools.py:102
↓ 7 callersMethodupdate_cache_key_with_event_loop
Add the event loop to the cache key, to prevent event loop closed errors. If none, use the key as is.
litellm/caching/llm_caching_handler.py:45
↓ 7 callersMethodupdate_completion_start_time
(self, completion_start_time: datetime.datetime)
litellm/litellm_core_utils/litellm_logging.py:2994
↓ 7 callersFunctionupdate_daily_tag_spend
Separate scheduler job to commit daily tag spend updates. Runs at a longer interval (2.3x default) than the main update_spend job to red
litellm/proxy/utils.py:8991
↓ 7 callersMethodupdate_in_memory_max_size
(self, max_size: int | None)
litellm/proxy/common_utils/user_api_key_cache.py:143
↓ 7 callersMethodupdate_many
(self, where: Mapping[str, object], data: Mapping[str, object])
litellm/proxy/management_endpoints/scim/scim_v2.py:138
↓ 7 callersFunctionupdate_organization_v2
Partial update of an organization (RESTful PATCH, RFC 7396 merge-patch semantics). A sent field is written and an omitted one is left untouc
litellm/proxy/management_endpoints/organization_endpoints.py:858
↓ 7 callersFunctionupdate_pass_through_endpoints
Update a pass-through endpoint by ID.
litellm/proxy/pass_through_endpoints/pass_through_endpoints.py:4594
↓ 7 callersFunctionupdate_request_with_filtered_beta
Update both headers and request body beta fields based on provider support. Modifies both dicts in place and returns them. Args:
litellm/anthropic_beta_headers_manager.py:477
↓ 7 callersMethodupload_file_to_storage_backend
Upload a file to a storage backend and create a file object. Args: file_data: File data dictionary from extract_file_dat
litellm/proxy/openai_files_endpoints/storage_backend_service.py:39
↓ 7 callersMethodupsert
( self, where: Mapping[str, object], data: Mapping[str, Mapping[str, objec
litellm/proxy/management_endpoints/customer_endpoints.py:104
↓ 7 callersFunctionupstream_auth_challenge
The first upstream 401/403 in deliberate order and its ``WWW-Authenticate`` challenge, both read from the SAME response, so the status that picks
litellm/proxy/mcp_server/faults/list_outcomes.py:113
↓ 7 callersFunctionupstream_name
(group: str)
tests/integration/routing/test_priority_scheduler_queue_cleanup.py:95
↓ 7 callersFunctionuseDisableShowPrompts
()
ui/litellm-dashboard/src/app/(dashboard)/hooks/useDisableShowPrompts.ts:33
↓ 7 callersMethoduseSyncedValue
(e,r)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 7 callersFunctionuseUIConfig
()
ui/litellm-dashboard/src/app/(dashboard)/hooks/uiConfig/useUIConfig.ts:7
↓ 7 callersFunctionuseUrlTab
(values: readonly T[], fallback: T, key = "tab")
ui/litellm-dashboard/src/hooks/useUrlTab.ts:7
↓ 7 callersMethoduse_multipart_form_data
(self)
litellm/llms/edenai/videos/transformation.py:64
↓ 7 callersMethoduserlist
(self, upstream_password: str)
litellm/proxy/db/pgbouncer.py:122
↓ 7 callersFunctionv
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 7 callersMethodv
()
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 7 callersFunctionv_
(e,t={})
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:320
↓ 7 callersFunctionvalidate_and_fix_openai_messages
Ensures all messages are valid OpenAI chat completion messages. Handles missing role for assistant messages.
litellm/utils.py:9631
↓ 7 callersFunctionvalidate_and_normalize_mcp_server_payload
(payload: McpServerPayloadLike)
litellm/proxy/management_endpoints/mcp_management_endpoints.py:329
↓ 7 callersMethodvalidate_environment
( self, headers: dict, model: str, messages: list[AllMessageValues], o
litellm/llms/oci/chat/transformation.py:515
↓ 7 callersMethodvalidate_environment
Validate environment and set up headers for GitHub Copilot API. Uses the Authenticator to obtain GitHub Copilot API key via OAuth De
litellm/llms/github_copilot/responses/transformation.py:198
↓ 7 callersMethodvalidate_environment
(self, headers: dict, model: str, litellm_params: GenericLiteLLMParams | None)
litellm/llms/bedrock_mantle/responses/transformation.py:120
↓ 7 callersFunctionvalidate_finite_spend
Reject NaN/±inf spend before it reaches the DB / spend counter. A non-finite spend would otherwise slip past `spend >= max_budget` enforcemen
litellm/proxy/management_endpoints/common_utils.py:14
↓ 7 callersFunctionvalidate_key_vector_stores_against_team
Reject vector_stores requested on a personal (no team) key by a non-admin caller. Vector store access is granted at use-time from the key's
litellm/proxy/management_helpers/object_permission_utils.py:879
↓ 7 callersFunctionvalidate_membership
(user_api_key_dict: UserAPIKeyAuth, team_table: LiteLLM_TeamTable)
litellm/proxy/management_endpoints/team_endpoints.py:5291
↓ 7 callersFunctionvalidated_object_list
(value: object)
litellm/llms/anthropic/common_utils.py:413
↓ 7 callersFunctionvcr_diag_write_line
(msg: str)
tests/_vcr_conftest_common.py:76
↓ 7 callersFunctionvcr_disabled
()
tests/_vcr_conftest_common.py:1109
↓ 7 callersMethodverify_license_without_api_request
(self, public_key, license_key)
litellm/proxy/auth/litellm_license.py:176
↓ 7 callersFunctionverify_proxy_key
Probe the proxy with the key so bad creds fail here, not inside the agent. Raises AgentRunError when the proxy is unreachable or rejects the key.
litellm/proxy/client/cli/commands/agents.py:960
↓ 7 callersMethodversion
(self)
litellm/router_api.py:365
↓ 7 callersMethodvertex_ai_live_passthrough_handler
Handle cost tracking and logging for Vertex AI Live API WebSocket passthrough. Args: websocket_messages: List of WebSock
litellm/proxy/pass_through_endpoints/llm_provider_handlers/vertex_ai_live_passthrough_logging_handler.py:363
↓ 7 callersFunctionvideo_status
( video_id: str, timeout: int = 600, custom_llm_provider: str | None = None, extra_headers: di
litellm/videos/main.py:949
↓ 7 callersMethodview
(&self, position: usize)
litellm-rust/crates/router-core/src/lookup.rs:148
↓ 7 callersFunctionw
({guardrails:e,tone:r})
litellm/proxy/_experimental/out/_next/static/chunks/39v0w3tgm6n4z.js:1
↓ 7 callersFunctionw
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 7 callersFunctionwaitForSpendLog
( request: APIRequestContext, requestId: string, timeoutMs = 60_000, )
tests/e2e/ui/helpers/traffic.ts:134
↓ 7 callersFunctionwarn_if_id_jag_assertion_uncaptured
Say, at the one moment it is knowable, that this login gave an ``oauth2_id_jag`` server nothing to spend. Without it the operator only ever sees t
litellm/proxy/management_endpoints/ui_sso.py:1823
↓ 7 callersFunctionwav_payload
(body: bytes)
tests/integration/providers/_gemini_tts_voice_support.py:388
↓ 7 callersMethodwildcard_route_deployments
(self, model: str, team_id: str | None)
litellm/router_deprecated.py:445
↓ 7 callersMethodwindow_from_table
Read the maintained per-window spend row by primary key. Returns the row's spend only when the row belongs to the window the
litellm/proxy/db/spend_counter_reseed.py:272
↓ 7 callersMethodwire
The row as the host reads it.
litellm-rust/crates/router-core/src/lookup.rs:40
↓ 7 callersMethodwithResponse
()
litellm/proxy/_experimental/out/_next/static/chunks/2hk8n3azev--d.js:1
↓ 7 callersMethodwith_caller
(self, caller: Caller)
tests/e2e/proxy_client.py:481
↓ 7 callersFunctionwith_compaction_summary
(encrypted_content: str, summary: str)
litellm/responses/litellm_completion_transformation/compaction_items.py:167
↓ 7 callersFunctionwith_headers
(request: LiteLLMOcrRequest, headers: &[(&str, &str)])
litellm-rust/crates/inference-ocr/tests/ocr/main.rs:125
↓ 7 callersMethodwith_imds_probe
(self, enabled: bool)
litellm-rust/crates/auth-azure/src/native.rs:76
↓ 7 callersFunctionwith_litellm_call_id
The same error object, answering with ``x-litellm-call-id`` when it was raised without one.
litellm/proxy/common_utils/openai_error_payload.py:253
↓ 7 callersFunctionwith_tolerated_stream_scope
(params: Mapping[str, object])
litellm/types/guardrails.py:1003
↓ 7 callersFunctionwithout_headers
(headers: Vec<(String, String)>, names: &[&str])
litellm-rust/crates/http/src/request.rs:104
↓ 7 callersFunctionwrapped
(scope: Scope, receive: Receive, send: Send)
tests/integration/_support/mcp.py:257
↓ 7 callersMethodwrite
(self, data: bytes)
tests/unit/llms/codex/harness/test_transformation.py:90
↓ 7 callersFunctionwrite_anthropic_server_tool_calls
( holder: Message | Delta, rewritten: tuple[ChatCompletionAssistantToolCall, ...] )
litellm/llms/anthropic/common_utils.py:2398
↓ 7 callersFunctionwrite_private_json
Atomically write JSON to path with owner-only permissions (0600)
litellm/litellm_core_utils/private_json.py:83
↓ 7 callersFunctionwriter_wrapper
Unlike `WriterPinnedClient`, ignores `writer_unavailable`: a raw SQL write has no replica fallback.
litellm/proxy/db/routing_prisma_wrapper.py:92
↓ 7 callersMethodwrites
(self)
litellm-rust/crates/cache-response/src/caching.rs:120
↓ 7 callersFunctionz
()
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 6 callersMethod#s
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 6 callersFunctionA
litellm/proxy/_experimental/out/_next/static/chunks/1f2vcab0yti03.js:29
↓ 6 callersFunctionB
litellm/proxy/_experimental/out/_next/static/chunks/2k-fkubkt19cc.js:8
↓ 6 callersFunctionD
({server:e,onApprove:t,onReject:r,requiredFields:l})
litellm/proxy/_experimental/out/_next/static/chunks/2k-fkubkt19cc.js:1
↓ 6 callersFunctionE
()
litellm/proxy/_experimental/out/_next/static/chunks/3yrgf44a9g52e.js:1
↓ 6 callersFunctionE
litellm/proxy/_experimental/out/_next/static/chunks/1_eer1fdrob9o.js:16
↓ 6 callersFunctionF
(e,t,n,r,a,l,u)
litellm/proxy/_experimental/out/_next/static/chunks/0dvgjd47fte1d.js:1
↓ 6 callersFunctionI
(t)
litellm/proxy/_experimental/out/_next/static/chunks/14v3irtjifjt2.js:1
↓ 6 callersFunctionInput
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 6 callersFunctionKa
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
← previousnext →11,401–11,500 of 202,479, ranked by callers