MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 9 callersFunction_sse_upstream_response
(*lines: str, first_line_delay: float = 0.0)
tests/unit/proxy/agent_endpoints/test_a2a_endpoints.py:46
↓ 9 callersFunction_stamped
(span: Span, kwargs: Mapping[str, object], response_obj: object = None)
tests/unit/integrations/test_langfuse_otel.py:1116
↓ 9 callersFunction_start_lite_login
(proxy: Gateway)
tests/integration/authorization/test_cli_sso_login_ui_disabled.py:198
↓ 9 callersFunction_start_patches
(patches)
tests/unit/proxy/mcp_server/auth/test_user_api_key_auth_mcp.py:5764
↓ 9 callersFunction_statement_by_sid
(policy: WebIdentitySessionPolicy, sid: str)
tests/unit/llms/bedrock/test_web_identity_session_policy.py:150
↓ 9 callersFunction_statements
(line_number, sql) for each line, with comments removed. Prisma writes its own explanations as `-- CREATE INDEX CONCURRENTLY ...`, which a ra
tests/unit/litellm_proxy_extras/test_litellm_proxy_extras_utils.py:323
↓ 9 callersFunction_stop_patches
(patches)
tests/unit/proxy/mcp_server/auth/test_user_api_key_auth_mcp.py:5769
↓ 9 callersFunction_stream_and_close
(rig: _DisconnectRig, path: str, body: Mapping[str, JsonValue], marker: str)
tests/integration/observability/test_guardrail_effects.py:2482
↓ 9 callersFunction_stream_chat
(rig: Rig, body: Mapping[str, JsonValue])
tests/integration/streaming/test_chat_stream_guardrail_error_events.py:246
↓ 9 callersFunction_stream_content
(response: httpx.Response)
tests/integration/providers/test_vertex_anthropic_structured_output_wire.py:747
↓ 9 callersFunction_streamed_json_tool_blocks
( blocks: tuple[str, ...], schema: dict[str, object] = _STREAMED_RISK_SCHEMA )
tests/unit/llms/anthropic/chat/test_anthropic_chat_handler.py:3776
↓ 9 callersFunction_streamed_text
(chunks: Sequence[Mapping[str, JsonValue]])
tests/integration/providers/test_anthropic_refusal_stop_details_wire.py:485
↓ 9 callersFunction_streaming_model_list
(silent_model: object)
tests/unit/test_router_silent_experiment.py:180
↓ 9 callersFunction_strip_client_pricing_overrides
Drop pricing overrides from the request body and any metadata variant. Skipped only when the calling key/team carries ``allow_client_pricing_
litellm/proxy/litellm_pre_call_utils.py:825
↓ 9 callersFunction_strip_image_b64_payloads
Replace ``b64_json`` payloads in image-gen responses before save. Image-edit and image-generation responses carry the full base64 PNG/JPEG (1
tests/_vcr_conftest_common.py:288
↓ 9 callersFunction_success
(marker: str)
tests/integration/observability/test_arize_otel_v2_openinference_sad_edge.py:55
↓ 9 callersFunction_talk
( ws_base: str, query: str, key: str, frames: tuple[dict[str, JsonValue], ...], *, unt
tests/integration/providers/test_realtime_transcription_guardrail_session_update.py:688
↓ 9 callersFunction_targets
(wire: Wire)
tests/integration/routing/test_declared_provider_bare_model_routes.py:128
↓ 9 callersFunction_team
(team_id: str, members: list[Member] | None = None)
tests/unit/proxy/management_helpers/test_bulk_user_creation.py:174
↓ 9 callersFunction_team_list_member
( team_id: str, user_id: str = "caller", default_budget_id: str | None = None, )
tests/unit/proxy/management_endpoints/test_team_endpoints.py:5231
↓ 9 callersFunction_text
()
tests/integration/sdk/test_sagemaker_embedding_sdk.py:47
↓ 9 callersFunction_text
(text: str)
tests/unit/proxy/mcp_server/test_mcp_sampling_tool_conversion.py:25
↓ 9 callersFunction_text_block
(endpoint: str, text: str)
tests/integration/observability/test_bedrock_guardrail_attachments.py:289
↓ 9 callersFunction_text_chunk
(index: int | None, text: str | None, finish_reason: str | None = None)
tests/unit/llms/openai/completion/test_text_completion_guardrail_handler.py:391
↓ 9 callersMethod_text_inputs
(cls, stream: FakeBedrockStream)
tests/unit/llms/bedrock/realtime/test_bedrock_realtime_handler.py:1830
↓ 9 callersMethod_text_stream
( self, texts, *, input_tokens=12, cache_creation=0, cache_rea
tests/unit/proxy/pass_through_endpoints/llm_provider_handlers/test_anthropic_passthrough_logging_handler.py:1225
↓ 9 callersFunction_thinking_chunk
(thinking: str, signature: str = "")
tests/unit/llms/anthropic/messages/adapters/test_streaming_iterator_first_delta.py:61
↓ 9 callersFunction_tiers_by_slug
( gateway: Gateway, *, key: str | None = None, params: Mapping[str, str] | None = None )
tests/integration/compatibility/test_codex_model_catalog.py:129
↓ 9 callersFunction_to_float
(value: object)
litellm/proxy/spend_tracking/budget_reservation.py:1740
↓ 9 callersFunction_token_db_url
Build a DATABASE_URL whose password is a parseable RDS IAM token.
tests/unit/proxy/db/test_prisma_planned_engine_restart.py:148
↓ 9 callersFunction_token_exchange_params
( exchange_name: str, client_id: str, client_secret: str, )
tests/unit/llms/microsoft_365_copilot/chat/test_handler.py:118
↓ 9 callersFunction_token_response
(token="tok-abc", expires_in=3600)
tests/unit/proxy/mcp_server/test_oauth2_token_cache.py:39
↓ 9 callersFunction_token_source
A token source handing out ``tokens`` in order, raising the exceptions among them, then repeating the last.
tests/unit/proxy/db/test_pgbouncer.py:595
↓ 9 callersFunction_tool
(endpoint: Endpoint, description: str, parameters: JsonValue)
tests/integration/providers/test_gemini_anyof_null_branches_wire.py:156
↓ 9 callersFunction_tool_use
(*, name: str, tool_id: str, input_data: Dict[str, Any])
tests/unit/proxy/mcp_server/test_mcp_sampling_tool_conversion.py:29
↓ 9 callersFunction_tool_use_names
(response: dict)
tests/unit/integrations/websearch_interception/test_websearch_agentic_loop_cap.py:103
↓ 9 callersFunction_trace_spans
(sink_url: str, trace_id: str, seconds: float = 30)
tests/integration/observability/test_otel_excluded_services.py:190
↓ 9 callersFunction_transcribe_blocked
( ws_base: str, query: str, key: str, *, path: str = "/v1/realtime", update: JsonValue
tests/integration/providers/test_realtime_transcription_guardrail_session_update.py:612
↓ 9 callersFunction_transform
(payload: object)
tests/unit/llms/exa_ai/search/test_transformation.py:95
↓ 9 callersFunction_transform
(payload: object, status_code: int = 200)
tests/unit/llms/jina_ai/rerank/test_transformation.py:11
↓ 9 callersMethod_transform
( self, model: str, messages: list[dict[str, object]], *, custom_llm_p
tests/unit/llms/openai/chat/test_openai_gpt_transformation.py:1014
↓ 9 callersMethod_transform
(self, config, model, litellm_params, tools)
tests/unit/llms/openai/chat/test_openai_gpt_transformation.py:1825
↓ 9 callersMethod_transform_chat_completion_chunk_to_response_api_chunk
Transform a chat completion chunk to a response API chunk. This currently handles emitting the OutputTextDeltaEvent, which is used b
litellm/responses/litellm_completion_transformation/streaming_iterator.py:1470
↓ 9 callersMethod_transform_response
Transforms the response from the Bedrock embedding provider to the OpenAI format.
litellm/llms/bedrock/embed/embedding.py:199
↓ 9 callersMethod_transform_responses_api_function_call_to_chat_completion_message
Transform a Responses API function_call into a Chat Completion message with tool calls Handles Input items of this type: fun
litellm/responses/litellm_completion_transformation/transformation.py:2665
↓ 9 callersMethod_transform_tool_choice
Transform tool_choice from various formats to OpenAI Chat Completion format. Handles: - String values: "auto", "none", "requ
litellm/responses/litellm_completion_transformation/transformation.py:989
↓ 9 callersFunction_transformed_input_for
( model: str, input: list[dict[str, object]], litellm_params: GenericLiteLLMParams, config: Ba
tests/unit/llms/openai/responses/test_openai_responses_transformation.py:4592
↓ 9 callersFunction_translate_model_name_for_response
For team-scoped DB rows, replace `model_name` with the public name in `model_info.team_public_model_name` before returning. The DB column and
litellm/proxy/proxy_server.py:18454
↓ 9 callersMethod_try_waitpid_watch
Watch engine PID via os.waitpid() in a dedicated thread. The thread blocks on os.waitpid(pid, 0) which is a kernel-level wait and wit
litellm/proxy/utils.py:7189
↓ 9 callersFunction_turn_deployment
(kind: str)
tests/unit/test_router/test_io_token_rate_limits.py:1644
↓ 9 callersFunction_types
(items: Sequence[Mapping[str, object]])
tests/unit/completion_extras/litellm_responses_transformation/test_completion_extras_litellm_responses_transformation_history.py:245
↓ 9 callersFunction_ui_session_caller
(token: str | None = HASHED_TOKEN)
tests/unit/proxy/management_endpoints/test_session_endpoints.py:38
↓ 9 callersFunction_unaliased_ceiling
(deployments: list[dict], team_id: str, requested_model: str)
tests/unit/router_utils/test_ptu_shares.py:64
↓ 9 callersMethod_union_tool_grants
Union of one level's direct tool grants, its toolset-granted tools and its unified access-group tools on one server, ``None`` when no source r
litellm/proxy/mcp_server/auth/user_api_key_auth_mcp.py:3015
↓ 9 callersFunction_unique
(prefix: str = "l11100")
tests/unit/test_router/core/test_gaps_l11100_registry.py:26
↓ 9 callersFunction_unique_day
()
tests/integration/spend/test_daily_activity_aggregated_breakdowns.py:20
↓ 9 callersFunction_unknown_key
()
tests/integration/authorization/test_unknown_key_generic_401.py:103
↓ 9 callersFunction_unsupported_video_call
( call_name: str, custom_llm_provider: str, model: str | None = None )
litellm/videos/main.py:30
↓ 9 callersFunction_update_key_row_assigning_project
Assign a project in one writer transaction, guarded on the key's validated state.
litellm/proxy/management_endpoints/key_management_endpoints.py:2910
↓ 9 callersFunction_upstream
(probability: float)
tests/integration/providers/test_decision_model_guardrail.py:63
↓ 9 callersFunction_upstream
(respond: Callable[[Request], Reply])
tests/integration/messages_endpoint/providers/anthropic/test_passthrough_migration_wire.py:142
↓ 9 callersFunction_upstream_token_response
(status_code: int, *, json_body: object = None, text_body: str = "")
tests/unit/proxy/mcp_server/test_discoverable_endpoints.py:9484
↓ 9 callersFunction_use_quota_proxy
(monkeypatch: pytest.MonkeyPatch, prisma: MagicMock, router: Router)
tests/unit/proxy/management_endpoints/test_model_management_endpoints.py:8293
↓ 9 callersFunction_user
()
tests/unit/proxy/pass_through_endpoints/test_managed_id_rewriter.py:36
↓ 9 callersFunction_user_api_key_auth
(metadata=None, team_metadata=None)
tests/unit/proxy/test_pricing_field_strip.py:43
↓ 9 callersFunction_user_row
(user_id: str)
tests/integration/authorization/test_user_self_update_guard.py:23
↓ 9 callersFunction_v1_models
(user_api_key_dict: UserAPIKeyAuth, **kwargs)
tests/unit/proxy/test_model_list_discoverable.py:103
↓ 9 callersFunction_v1_models
(user_api_key_dict: UserAPIKeyAuth, request: Request | None = None)
tests/unit/proxy/test_model_list_aliases.py:104
↓ 9 callersMethod_validate_input_param
Ensure all input fields if pydantic are converted to dict OpenAI API Fails when we try to JSON dumps specific input pydantic fields.
litellm/llms/openai/responses/transformation.py:957
↓ 9 callersFunction_validated
(adapter: TypeAdapter[_Validated], value: object)
litellm/google_genai/adapters/transformation.py:134
↓ 9 callersFunction_video_url_from_task
A download before the video is ready is the caller polling too early, so it answers 400, which the router neither retries nor counts toward a depl
litellm/llms/minimax/videos/transformation.py:448
↓ 9 callersFunction_video_with_empty_model_id
( hidden_params: dict[str, object] | None = None, )
tests/unit/proxy/video_endpoints/test_endpoints.py:77
↓ 9 callersFunction_window
(freq: str = "daily", hour: int = 5)
tests/unit/integrations/focus/test_ternary_destination.py:21
↓ 9 callersFunction_with_jobs
(scheduler: AsyncIOScheduler)
tests/unit/proxy/common_utils/test_scheduled_job_stagger.py:40
↓ 9 callersFunction_write_wheel
( tmp_path: Path, *, filename_tag: str, metadata_tags: tuple[str, ...] | None = (_EXPECTED_TAG
tests/unit/rust_bridge/test_verify_linux_native_wheel.py:52
↓ 9 callersFunction_written_values
(update_by_name: AsyncMock)
tests/unit/proxy/credential_endpoints/test_endpoints.py:501
↓ 9 callersFunctiona
litellm/proxy/_experimental/out/_next/static/chunks/1a2lzi3ursud4.js:1
↓ 9 callersFunctiona
(t)
litellm/proxy/_experimental/out/_next/static/chunks/0cz1d0mv5g_q7.js:1
↓ 9 callersMethodabatch_completion
( self, models: list[str], # mutable-ok: the request kwargs the Python router mutates in plac
litellm/router_rust/invoke/endpoints.py:2031
↓ 9 callersMethodaccess_group_tools_for_server
Tools the unified access groups grant on ``server_id``: the union of each granting group's ``mcp_tool_permissions`` entry for it. A granting g
litellm/proxy/mcp_server/auth/user_api_key_auth_mcp.py:3031
↓ 9 callersMethodacquire
(self, owner: str, status: ROISyncStatus, scheduled_interval: float = 0)
litellm/proxy/roi_calculator/sync_store.py:44
↓ 9 callersMethodacreate_fine_tuning_job
( self, create_fine_tuning_job_data: dict, openai_client: AsyncOpenAI | AsyncAzureOpen
litellm/llms/openai/fine_tuning/handler.py:99
↓ 9 callersFunctionadapt_messages_to_generic_oci_standard_content_message
Convert a plain-text or multipart content message to OCI format.
litellm/llms/oci/chat/generic.py:60
↓ 9 callersMethodadd_litellm_async_success_callback
Add a success callback to litellm._async_success_callback
litellm/litellm_core_utils/logging_callback_manager.py:106
↓ 9 callersMethodadd_litellm_async_success_callback
(self, callback: object)
tests/unit/test_router/core/scripted_host.py:210
↓ 9 callersMethodadd_litellm_callback
(self, callback: object)
tests/unit/test_router/core/scripted_host.py:199
↓ 9 callersMethodadd_vertex_credentials
Add the vertex credentials for the given project-id, location
litellm/proxy/pass_through_endpoints/passthrough_endpoint_router.py:343
↓ 9 callersFunctionaggregate_report_outcome
Fold a worker-produced VCR outcome into the controller's session stats. No-op outside the xdist controller path: * On a worker, ``_session_s
tests/_vcr_conftest_common.py:1540
↓ 9 callersMethodaimage_edit
(self, optional_params: dict[str, object], **kwargs: object)
tests/unit/images/test_main.py:740
↓ 9 callersFunctionallm_passthrough_route
Async: Reranks a list of documents based on their relevance to the query
litellm/passthrough/main.py:298
↓ 9 callersFunctionanchor_handler_to
Keep the handler alive for as long as a streaming response can still read. A body still arriving reads through the handler's connection pool, and
litellm/llms/custom_httpx/http_handler.py:241
↓ 9 callersFunctionanswered
(sents: tuple[Sent, ...])
tests/integration/providers/_idle_upstream_support.py:607
↓ 9 callersFunctionanthropic_marks
(request: Request)
tests/integration/providers/_cache_control_marks_support.py:251
↓ 9 callersFunctionanthropic_messages_response_as_sse_events
Render a complete (non-streaming) AnthropicMessagesResponse as the SSE event sequence a real streaming request would have produced. A mi
litellm/llms/anthropic/messages/native/streaming_iterator.py:271
↓ 9 callersFunctionanthropic_stream
(identity: str, text: str)
tests/integration/observability/test_presidio_streaming_output.py:69
↓ 9 callersFunctionapidom_evaluate
(s,o,i={})
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 9 callersMethodapply_guardrail
( self, inputs: GenericGuardrailAPIInputs, request_data: dict[str, object], in
litellm/proxy/guardrails/guardrail_hooks/block_code_execution/block_code_execution.py:517
↓ 9 callersMethodapply_guardrail
Apply OpenAI moderation guardrail using the unified guardrail interface. This method is called by the UnifiedLLMGuardrails system fo
litellm/proxy/guardrails/guardrail_hooks/openai/moderations.py:212
↓ 9 callersMethodapply_guardrail
Apply Zscaler AI Guard guardrail to batch of texts. Args: inputs: Dictionary containing texts and optional images
litellm/proxy/guardrails/guardrail_hooks/zscaler_ai_guard/zscaler_ai_guard.py:159
↓ 9 callersFunctionapply_json_merge_patch
Apply an RFC 7386 JSON Merge Patch to ``target`` and return the result. - a key absent from ``patch`` keeps its value in ``target`` - a key m
litellm/proxy/common_utils/json_merge_patch.py:13
← previousnext →7,801–7,900 of 202,479, ranked by callers