MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 6 callersFunction_tpm_media_list
(value: object, split: Callable[[object], _TPMMediaProjection])
litellm/litellm_core_utils/prompt_templates/tpm_media_utils.py:100
↓ 6 callersFunction_trace
(*spans: dict[str, object])
tests/e2e_harness/logging/test_span_selection.py:40
↓ 6 callersFunction_transcribe
( gateway: Gateway, key: str, model: str, seconds: float = _CLIP_SECONDS, **fields: str )
tests/integration/providers/test_nvidia_riva_wire.py:29
↓ 6 callersFunction_transform
(raw_response: httpx.Response)
tests/unit/llms/replicate/chat/test_transformation.py:17
↓ 6 callersFunction_transform
(payload: object)
tests/unit/llms/serper/search/test_serper_search_transformation.py:201
↓ 6 callersFunction_transform
(payload: object)
tests/unit/llms/searchapi/search/test_searchapi_search_transformation.py:226
↓ 6 callersFunction_transform
(payload: object, model_response: ImageResponse | None = None)
tests/unit/llms/fal_ai/image_generation/test_bria_transformation.py:9
↓ 6 callersFunction_transform
(payload: object, model_response: ImageResponse | None = None)
tests/unit/llms/fal_ai/image_generation/test_imagen4_transformation.py:9
↓ 6 callersFunction_transform
(payload: object)
tests/unit/llms/watsonx/embed/test_watsonx_embedding_transformation.py:57
↓ 6 callersFunction_transform
(payload: object)
tests/unit/llms/linkup/search/test_linkup_search_transformation.py:108
↓ 6 callersFunction_transform
(payload: object)
tests/unit/llms/google_pse/search/test_google_pse_search_transformation.py:12
↓ 6 callersFunction_transform
(payload: object, status_code: int = 200)
tests/unit/llms/minimax/text_to_speech/test_transformation.py:17
↓ 6 callersFunction_transform
(payload: object)
tests/unit/llms/perplexity/search/test_perplexity_search_transformation.py:141
↓ 6 callersFunction_transform
(payload: object)
tests/unit/llms/searxng/search/test_searxng_search_transformation.py:327
↓ 6 callersFunction_transform
(payload: object)
tests/unit/llms/fireworks_ai/rerank/test_fireworks_ai_rerank_transformation.py:347
↓ 6 callersFunction_transform
(payload: object)
tests/unit/llms/voyage/rerank/test_voyage_rerank_transformation.py:348
↓ 6 callersFunction_transform
(rows: list[dict])
tests/unit/integrations/focus/test_focus_transformer.py:31
↓ 6 callersMethod_transform
(self, config, model, tools)
tests/unit/llms/azure/chat/test_azure_chat_gpt_transformation.py:312
↓ 6 callersMethod_transform_contents_to_messages
Transform Google GenAI contents to OpenAI messages format
litellm/google_genai/adapters/transformation.py:629
↓ 6 callersMethod_transform_input_image_item_to_image_item
Transform a Responses API input_image item to a Chat Completion image item
litellm/responses/litellm_completion_transformation/transformation.py:2740
↓ 6 callersMethod_transform_reasoning_effort_to_reasoning_config
Transform reasoning_effort parameter to Nova 2 reasoningConfig structure. Nova 2 models use a reasoningConfig structure in additiona
litellm/llms/bedrock/chat/converse_transformation.py:515
↓ 6 callersFunction_transform_response
(payload: object)
tests/unit/test_dashscope_image_generation.py:584
↓ 6 callersMethod_transform_response_format_to_text_format
Transform Chat Completion response_format parameter to Responses API text.format parameter. Chat Completion response_format structur
litellm/completion_extras/litellm_responses_transformation/transformation.py:2032
↓ 6 callersMethod_transform_responses_api_tool_call_output_to_chat_completion_message
ChatCompletionToolMessage is used to indicate the output from a tool call
litellm/responses/litellm_completion_transformation/transformation.py:2596
↓ 6 callersMethod_transform_thinking_blocks
Return a consistent format for thinking blocks between Anthropic and Bedrock.
litellm/llms/bedrock/chat/converse_transformation.py:2546
↓ 6 callersFunction_tree
Stand a migrations directory holding one fixture migration in for the repo's own. The root moves with it, since a rendered violation names the mig
tests/unit/test_check_migrations_no_data_rewrites.py:1862
↓ 6 callersFunction_turn
( identity: str, stop_reason: str, content: tuple[Mapping[str, JsonValue], ...] = (TEXT,), sto
tests/integration/providers/test_anthropic_context_window_stop_wire.py:66
↓ 6 callersFunction_turn_spend_log
( turn_input: str | list[dict[str, str]], answer: str, compaction_blocks: list[dict[str, str]] | None = No
tests/unit/responses/litellm_completion_transformation/test_session_handler.py:891
↓ 6 callersFunction_two_account_sora_router
()
tests/unit/test_router/test_router_provider_endpoints.py:637
↓ 6 callersFunction_two_callback_metadata
A team with two tenants' integrations registered, the LIT-5161 shape.
tests/unit/proxy/management_endpoints/test_team_callback_endpoints.py:952
↓ 6 callersFunction_unified_file_id
(provider_file_id: str = RAW_FILE_ID)
tests/unit/proxy/vector_store_files_endpoints/test_endpoints.py:78
↓ 6 callersFunction_unknown_event_frame
()
tests/unit/llms/bedrock/chat/test_invoke_handler.py:1392
↓ 6 callersFunction_unmanaged_vertex_file_object
A LiteLLMBatch JSON blob shaped like what the managed-files hook stores for an unmanaged Vertex batch (raw gs:// input_file_id).
tests/unit/proxy/common_utils/test_check_batch_cost.py:94
↓ 6 callersFunction_unreachable_redis
()
tests/unit/proxy/hooks/test_parallel_request_limiter_v3.py:7768
↓ 6 callersMethod_update_config_from_db
( self, prisma_client: PrismaClient, config: dict, store_model_in_db: bool | N
litellm/proxy/proxy_server.py:8696
↓ 6 callersMethod_update_llm_router
( self, new_models: Json | None, proxy_logging_obj: ProxyLogging, )
litellm/proxy/proxy_server.py:8055
↓ 6 callersFunction_update_request_data_with_litellm_managed_vector_store_registry
Update the request data with the litellm managed vector store registry. Args: data: Request data to update vector_store_id:
litellm/proxy/vector_store_endpoints/endpoints.py:114
↓ 6 callersFunction_update_request_data_with_litellm_managed_vector_store_registry
Update request data with model routing information from managed vector store. This function handles two types of vector stores: 1. Legac
litellm/proxy/vector_store_files_endpoints/endpoints.py:407
↓ 6 callersMethod_update_tag_db
Update spend for all tags in the request. Args: response_cost: Cost of the request request_tags: JSON string
litellm/proxy/db/db_spend_update_writer.py:1633
↓ 6 callersFunction_updated_row
()
tests/unit/proxy/mcp_server/test_mcp_sigv4_auth.py:24
↓ 6 callersFunction_upstream
( marker: str, headers: Mapping[str, str], *, status: int = 200, stream: bool = False )
tests/integration/spend/test_passthrough_upstream_model.py:26
↓ 6 callersFunction_upstream_400
(target: str)
tests/unit/proxy/pass_through_endpoints/test_pass_through_endpoints.py:10640
↓ 6 callersMethod_upstream_headers
(self, request: Request)
tests/unit/proxy/pass_through_endpoints/test_llm_pass_through_endpoints.py:6746
↓ 6 callersFunction_upstream_targets
(wire: Wire)
tests/integration/providers/test_hosted_vllm_stream_stall_wire.py:148
↓ 6 callersFunction_user
(marker: str, *words: str)
tests/integration/sdk/test_responses_bridge_tool_search_sdk.py:31
↓ 6 callersFunction_user
(**overrides)
tests/unit/proxy/mcp_server/test_proxy_api_credentials.py:31
↓ 6 callersFunction_user_info
(gateway: Gateway, user_id: str)
tests/integration/authorization/test_user_self_update_guard.py:31
↓ 6 callersFunction_user_info
(alert_emails=None)
tests/unit/proxy/utils/proxy_logging/test_alerting.py:72
↓ 6 callersFunction_user_is_full_admin
True only for ``PROXY_ADMIN``; ``PROXY_ADMIN_VIEW_ONLY`` returns False. Global env var secrets pre-fill the admin edit form, so a full admin
litellm/proxy/management_endpoints/mcp_management_endpoints.py:750
↓ 6 callersFunction_user_message
()
tests/integration/compatibility/test_openai_sdk_client_paths.py:490
↓ 6 callersFunction_user_row
(user_id: str, user_email: str | None, user_alias: str | None = None)
tests/unit/proxy/management_endpoints/test_team_endpoints.py:14772
↓ 6 callersFunction_user_texts
(case: _Case, body: Mapping[str, JsonValue])
tests/unit/llms/base_llm/chat/test_provider_chat_translation.py:644
↓ 6 callersFunction_utils_token_counter
( monkeypatch: pytest.MonkeyPatch, body: Mapping[str, JsonValue], headers: Mapping[str, str] )
tests/unit/proxy/test_proxy_token_counter.py:5246
↓ 6 callersFunction_v1_calls
(rig: Rig, marker: str, key: str)
tests/integration/observability/test_straiker_v3_platform.py:489
↓ 6 callersFunction_v3_response_calls
(rig: Rig, marker: str, agent: str | None = POST_AGENT)
tests/integration/observability/test_straiker_v3_platform.py:479
↓ 6 callersFunction_validate
(messages, headers=None, optional_params=None)
tests/unit/llms/anthropic/messages/native/test_anthropic_messages_per_turn_control.py:36
↓ 6 callersFunction_validate_end_user_budget_id_change
A key's default end-user budget overrides the proxy-wide one, so only proxy admins may change it, and a non-empty value must name an existing budg
litellm/proxy/management_endpoints/key_management_endpoints.py:3591
↓ 6 callersFunction_validate_mcp_required_fields
Validate submission payload against admin-configured mcp_required_fields.
litellm/proxy/management_endpoints/mcp_management_endpoints.py:393
↓ 6 callersFunction_validate_vertex_headers
( client_headers: dict[str, str], messages: list[object], optional_params: dict[str, object] | Non
tests/unit/llms/vertex_ai/vertex_ai_partner_models/anthropic/test_vertex_ai_partner_models_anthropic_messages_config.py:298
↓ 6 callersFunction_vertex_search_file_ids
( peer: TlsPeer, search_url: str | None = None, ssl_verify: ssl.SSLContext | None = None )
tests/integration/sdk/test_http2_wire.py:285
↓ 6 callersFunction_victim
(scenario: Scenario)
tests/integration/authorization/test_sso_blank_identity.py:469
↓ 6 callersFunction_virtual_key_multi_budget_check
Raises BudgetExceededError if any budget window in valid_token.budget_limits is exceeded. Each window has its own Redis counter keyed by spe
litellm/proxy/auth/auth_checks.py:6806
↓ 6 callersFunction_wait_for_received
(peer: _Peer, expected: int)
tests/integration/providers/test_bedrock_stream_timeout_chaos.py:199
↓ 6 callersFunction_wait_out_a_rate_limit_minute_rollover
()
tests/unit/proxy/test_route_llm_request.py:2530
↓ 6 callersFunction_warnings_naming
(caplog: pytest.LogCaptureFixture, param: str)
tests/unit/llms/mistral/test_mistral_chat_transformation.py:1710
↓ 6 callersFunction_wheel
(tmp_path, *entry_names)
tests/unit/test_check_windows_wheel_install.py:17
↓ 6 callersFunction_wildcard_deployment
(model_name: str)
tests/unit/router_utils/test_pattern_match_deployments.py:22
↓ 6 callersFunction_window
()
tests/unit/integrations/ternary/test_ternary_logger.py:37
↓ 6 callersFunction_window_spend_upserts
(db)
tests/unit/proxy/db/test_db_spend_update_writer.py:3301
↓ 6 callersFunction_wire_body
(request: Request, *, stream: bool = False)
tests/integration/providers/test_openai_responses_prompt_cache_breakpoint_wire.py:91
↓ 6 callersMethod_wire_span_processor
Context manager: while active, the next OpenTelemetry instance wires its TracerProvider to `exporter`.
tests/unit/integrations/test_opentelemetry.py:845
↓ 6 callersFunction_with_complete_response
(request_data, text="Hello, how are you?")
tests/unit/proxy/guardrails/guardrail_hooks/akto/test_akto.py:342
↓ 6 callersFunction_with_content
The copy of ``sent`` at ``url`` once its model span arrived and some span carries the marker.
tests/integration/observability/test_otel_team_capture_message_content.py:297
↓ 6 callersMethod_with_db_write_retry
Same, for writes: only replay when the statements provably never reached the database. A reset zeroes spend unconditionally, so replaying
litellm/proxy/common_utils/reset_budget_job.py:599
↓ 6 callersFunction_with_get
(value: object)
litellm/proxy/proxy_server.py:16941
↓ 6 callersFunction_with_pdf
(text="summarise this")
tests/unit/proxy/guardrails/guardrail_hooks/akto/test_akto.py:1160
↓ 6 callersFunction_worker_that_never_listed
A worker whose tool rows for ``server`` are empty, in front of an upstream that answers tools/list with ``upstream_tools`` and a managed dispatch
tests/unit/proxy/mcp_server/test_mcp_server_tool_calls_and_headers.py:7945
↓ 6 callersFunction_wrap_cache_with_tracker
Wrap a DualCache to track all reads and writes.
tests/unit/proxy/auth/test_auth_hot_path_network_requests.py:71
↓ 6 callersFunction_wrapper_with_partial_chunks
( chunk_model: str, usage: Optional[Usage] = None, model: str = "gpt-4o-mini", custom_llm_prov
tests/unit/litellm_core_utils/test_streaming_handler.py:5467
↓ 6 callersFunction_wrapping_codec
()
tests/unit/proxy/mcp_server/outbound_credentials/test_token_cache_codec.py:11
↓ 6 callersMethod_write
(self, change: Callable[[dict[object, object]], object])
litellm/router_rust/surface/indexes.py:157
↓ 6 callersMethod_write_auth_file
(self, data: JsonObject)
litellm/llms/chatgpt/authenticator.py:167
↓ 6 callersFunction_write_config
(path: Path, general_settings: dict[str, object], litellm_settings: dict[str, object])
tests/unit/proxy/proxy_server/test_proxy_config.py:2705
↓ 6 callersFunction_write_login_token
(home: Path, base_url: str, key: str | None)
tests/unit/proxy/client/cli/test_global_options.py:154
↓ 6 callersFunction_write_prepared_key_update_object_permission
( data_json: Mapping[str, object], upsert: ObjectPermissionUpsert | None, prisma_client: PrismaCli
litellm/proxy/management_endpoints/key_management_endpoints.py:3139
↓ 6 callersFunction_write_stat
(proc_root, pid, comm, ppid)
tests/unit/proxy/db/test_query_engine_reaper.py:25
↓ 6 callersFunction_ws_base
(http_url: str)
tests/integration/providers/test_openai_realtime_transcription_url.py:102
↓ 6 callersFunctiona
()
litellm/proxy/_experimental/out/_next/static/chunks/0tx19jeq-wskb.js:1
↓ 6 callersFunctiona
(e)
litellm/proxy/_experimental/out/_next/static/chunks/14v3irtjifjt2.js:1
↓ 6 callersFunctionaL
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/1f2vcab0yti03.js:29
↓ 6 callersMethodaadapter_completion
( self, adapter_id: str, model: str, is_retry: bool | None = False, is
litellm/router_rust/invoke/endpoints.py:2150
↓ 6 callersFunctionaccepted
An Azure Document Intelligence 202 whose operation lives on `server`.
litellm-rust/crates/inference-ocr/tests/ocr/main.rs:145
↓ 6 callersFunctionaccessible_agents
Every registry agent for proxy admins, else only the agents the caller was granted.
litellm/proxy/agent_endpoints/auth/agent_permission_handler.py:842
↓ 6 callersMethodaclose
(self)
litellm/router_rust/invoke/streaming.py:1645
↓ 6 callersMethodaclose
(self)
tests/unit/proxy/management_endpoints/test_key_management_endpoints.py:5817
↓ 6 callersMethodacquire
(&self, py: Python<'_>)
litellm-rust/crates/python-bridge/src/credentials.rs:47
↓ 6 callersFunctionacquire_langfuse_tracing
One export channel per credential set, shared by every logger built for it. A provider owns a batch export thread, so a channel lives while any l
litellm/integrations/langfuse/langfuse_sdk.py:891
↓ 6 callersFunctionacting_user_auth
The principal acting-as-user MCP routes resolve permissions with. A non-admin dashboard session acts as the admitted subject, the same identity a
litellm/proxy/mcp_server/ui_session_utils.py:114
↓ 6 callersFunctionactor_admission_failure
( agent: AgentResponse, context: ManagedAgentContext | None, )
litellm/proxy/agent_endpoints/auth/managed_authorization.py:209
↓ 6 callersFunctionad
litellm/proxy/_experimental/out/_next/static/chunks/03q-w6h_lqdi1.js:1
← previousnext →12,501–12,600 of 202,479, ranked by callers