MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 16 callersFunction_body
( model: str, prompt: str, source: BudgetSource, *, stream: bool = True, budget: int = 1 )
tests/integration/messages_endpoint/providers/anthropic/test_anthropic_messages_pre_content_retry_wire.py:118
↓ 16 callersFunction_build_part_for_input
Build a single PartType for an input element, handling text, data URIs, file references, GCS URLs, and file content blocks carrying a mime ty
litellm/llms/vertex_ai/gemini_embeddings/batch_embed_content_transformation.py:353
↓ 16 callersFunction_build_router
()
tests/unit/test_router_retry_policy_update.py:99
↓ 16 callersFunction_call
( middleware: ASGIApp, path: str = "/", root_path: str = "", parent_scope: Scope | None = None
tests/unit/proxy/middleware/test_admission_control_middleware.py:28
↓ 16 callersFunction_calls_to
(requests: Sequence[Request], target: str)
tests/integration/providers/test_databricks_agent_wire.py:96
↓ 16 callersFunction_chat
( rig: Rig, content: str, metadata: Mapping[str, object] | None = None, headers: Mapping[str,
tests/integration/observability/test_langfuse_otel_trace_fields.py:314
↓ 16 callersFunction_chat
(rig: _Rig, model: str, marker: str, *, key: str | None = None, **extra: JsonValue)
tests/integration/routing/test_non_chat_model_endpoint_gate.py:582
↓ 16 callersMethod_check_and_increment_batch_counters
Atomically check + increment rate-limit counters by the batch amounts. Raises HTTPException if any descriptor would exceed its limit
litellm/proxy/hooks/batch_rate_limiter.py:765
↓ 16 callersFunction_client
(gateway: Gateway, key: str, prefix: str)
tests/integration/providers/test_responses_lifecycle_wire.py:164
↓ 16 callersFunction_coerce_user_id_to_str
Return a usable end-user identifier string, or None if the value isn't one. Always drops non-string structured values (dict/list/tuple/set) becau
litellm/proxy/auth/auth_utils.py:1961
↓ 16 callersMethod_common_add_spend_log_transaction_to_daily_transaction
( self, payload: dict | SpendLogsPayload, prisma_client: PrismaClient, type: L
litellm/proxy/db/db_spend_update_writer.py:3067
↓ 16 callersFunction_connection_row
( user_id: str = "user-a", credential_name: str = "copilot-cred", login: str = "octo", github_
tests/unit/proxy/credential_endpoints/test_endpoints.py:2111
↓ 16 callersFunction_conversation_payload
A ``turns``-message chat with ``choices`` response choices, content-bearing.
tests/unit/integrations/otel/test_otel_v2_emitter.py:486
↓ 16 callersFunction_count
(gateway: Gateway, body: Mapping[str, JsonValue])
tests/integration/providers/test_vertex_partner_count_tokens_wire.py:228
↓ 16 callersFunction_counter
(bedrock: _Bedrock)
tests/unit/llms/bedrock/count_tokens/test_bedrock_token_counter.py:43
↓ 16 callersFunction_decide
(gateway: Gateway, route: Route, model: str, marker: str, **extra: JsonValue)
tests/integration/providers/test_cloudflare_clef_omni_media_wire.py:168
↓ 16 callersMethod_decrypt_response_id
Returns: - original_response_id: the original response id - user_id: the user id - team_id: the team id
litellm/proxy/hooks/responses_id_security.py:329
↓ 16 callersFunction_delete_database_guardrail
(gateway: Gateway, identity: str)
tests/integration/observability/_logging_only_scope_support.py:816
↓ 16 callersFunction_deployment
(scenario: Scenario, handle: ScenarioHandle, provider: _Provider, *, drop_params: bool = False)
tests/integration/providers/test_decisions_openai_format_wire.py:314
↓ 16 callersFunction_deployment
( scenario: Scenario, wire: Wire, api_key: str = _API_KEY, provider: str = "openai", **parameters: JsonVal
tests/integration/providers/test_responses_lifecycle_wire.py:112
↓ 16 callersFunction_deployment
(gateway: Gateway, scenario: Scenario, wire: Wire, provider: Provider, backend: str = _BACKEND)
tests/integration/providers/test_gemini_anyof_null_branches_wire.py:135
↓ 16 callersFunction_deployment
(scenario: Scenario, wire: Wire, location: _Location, *, images: bool = False)
tests/integration/spend/test_vertex_regional_uplift_spend.py:113
↓ 16 callersFunction_deployment_bucket_params
(**deployment_litellm_params: object)
tests/unit/llms/bedrock/files/test_bedrock_files_transformation.py:3286
↓ 16 callersFunction_drain
(response)
tests/unit/proxy/test_common_request_processing.py:10932
↓ 16 callersFunction_empty_proxy_configuration
(tmp_path: Path, identity: str, reload_seconds: int = 30)
tests/integration/observability/_logging_only_scope_support.py:716
↓ 16 callersMethod_ended_by_upstream_error
(self, chunks: list[bytes])
tests/unit/proxy/guardrails/guardrail_hooks/test_tool_permission.py:3719
↓ 16 callersFunction_entry
(price: float = 1e-06, **extra: object)
tests/unit/test_cost_map_guard.py:32
↓ 16 callersFunction_env
(tmp_path: Path, config_dir: Path, **extra: str)
tests/unit/proxy/client/cli/test_statusline_script.py:85
↓ 16 callersFunction_expect_messages
( observed: _Observed, *, target: str, auth: tuple[str, str] | None, beta: str | None,
tests/integration/messages_endpoint/providers/anthropic/test_anthropic_safeguards_beta_wire.py:243
↓ 16 callersFunction_expected_upstream_body
(clef_name: str, state: str, images: Sequence[JsonValue] = ())
tests/integration/providers/test_cloudflare_clef_images_wire.py:153
↓ 16 callersFunction_family
(name: str, wire: Wire)
tests/integration/routing/test_model_capability_flags.py:263
↓ 16 callersFunction_fireworks_response
(model: str)
tests/unit/llms/fireworks_ai/responses/test_fireworks_ai_responses_transformation.py:40
↓ 16 callersFunction_full_upstream_card
()
tests/unit/proxy/a2a/test_agent_card.py:45
↓ 16 callersFunction_generate_calls
(wire: Wire)
tests/integration/providers/test_ollama_prompt_tools_wire.py:129
↓ 16 callersMethod_getOrReturnCtx
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2j7hjtph8n74b.js:1
↓ 16 callersMethod_get_prompt_from_kwargs
Extract a semantic-cache prompt from chat or Responses API request kwargs.
litellm/caching/redis_semantic_cache.py:269
↓ 16 callersMethod_get_token_and_url
Internal function. Returns the token and url for the call. Handles logic if it's google ai studio vs. vertex ai. Returns
litellm/llms/vertex_ai/vertex_llm_base.py:737
↓ 16 callersFunction_headers_forwarded_to
(client_headers: dict, custom_llm_provider: str)
tests/unit/proxy/test_litellm_pre_call_utils.py:8742
↓ 16 callersFunction_identity
()
tests/integration/streaming/test_responses_top_level_error_events.py:84
↓ 16 callersFunction_identity
( redemption: AssertionRedemption, verifier: _Verifier | None = None, resolver: _Resolver | None =
tests/unit/proxy/mcp_server/test_id_jag_grant.py:179
↓ 16 callersFunction_index_validity
index name -> indisvalid for every index ending in `suffix` on the SpendLogs parent or one of its partitions.
tests/integration/database/migrations/test_request_log_indexes.py:200
↓ 16 callersFunction_json_object
(body: bytes)
tests/integration/spend/test_spend_log_tool_payload_content.py:62
↓ 16 callersFunction_labeled_credential
(name: str = "openai-prod", display_name: str | None = "Prod OpenAI")
tests/unit/proxy/credential_endpoints/test_endpoints.py:2997
↓ 16 callersFunction_listening
(port: int)
tests/unit/proxy/db/test_pgbouncer.py:342
↓ 16 callersFunction_live_session_results
(*events: dict[str, object])
tests/unit/test_cost_calculator.py:10201
↓ 16 callersMethod_log_langfuse_v2
( self, user_id: str | None, metadata: dict[str, object], litellm_params: dict
litellm/integrations/langfuse/langfuse.py:662
↓ 16 callersFunction_logged_call
(messages: list | str)
tests/unit/integrations/test_custom_guardrail.py:2679
↓ 16 callersFunction_logged_response
(rig: Rig, key: str)
tests/integration/providers/test_anthropic_refusal_stop_details_wire.py:523
↓ 16 callersMethod_logging_obj
( self, pricing: Mapping[str, object], stream: bool = False, model: str = "ope
tests/unit/litellm_core_utils/test_litellm_logging.py:714
↓ 16 callersFunction_make_app
(recorder: Optional[FakeRecorder], status_code: int = 200, model_id: Optional[str] = None)
tests/unit/proxy/middleware/test_billable_request_metrics_middleware.py:43
↓ 16 callersFunction_make_background_streaming_kwargs
Build kwargs for background_streaming_task with all required mocks.
tests/unit/proxy/response_polling/test_response_polling_handler.py:1414
↓ 16 callersFunction_make_guardrail
( handler: MagicMock | None = None, *, max_result_chars_in_state: int | None = None, unreachab
tests/unit/proxy/guardrails/guardrail_hooks/test_typesafe.py:68
↓ 16 callersFunction_make_invite
( *, is_accepted: bool, expired: bool = False, claimed: bool = False )
tests/unit/proxy/auth/test_onboarding.py:42
↓ 16 callersFunction_make_reset_budget_windows_job
Build a ResetBudgetJob with a fully-mocked prisma client and a fake `litellm.proxy.proxy_server` module exposing a stub `spend_counter_store`.
tests/unit/proxy/common_utils/test_reset_budget_job.py:1043
↓ 16 callersFunction_manager
( *, servers_by_id: Mapping[str, MCPServer] | None = None, servers_by_name: Mapping[str, MCPServer
tests/unit/proxy/mcp_server/test_server_resolution.py:84
↓ 16 callersFunction_marker
()
tests/integration/observability/test_akto_logging_only.py:283
↓ 16 callersFunction_matching_requests
(wire: Wire, marker: str)
tests/integration/observability/test_guardrail_stream_scope_matrix.py:588
↓ 16 callersFunction_merge_over_saved
Keep the stored secret behind any credential the caller echoed back redacted or omitted. GET returns credentials as the marker and the form never
litellm/proxy/management_endpoints/cache_settings_endpoints.py:226
↓ 16 callersFunction_message_start_frame
(model: str, line_end: str = "\n")
tests/unit/proxy/anthropic_endpoints/test_streaming_model_restamp.py:21
↓ 16 callersFunction_messages
(*, tail: list[dict[str, object]] | None = None)
tests/unit/proxy/guardrails/guardrail_hooks/test_typesafe.py:60
↓ 16 callersFunction_mistral_request_messages
( messages: list[dict[str, object]], config: MistralConfig | None = None, model: str = "mistral-medium-3-5
tests/unit/llms/mistral/test_mistral_chat_transformation.py:959
↓ 16 callersFunction_mock_env_vars_prisma
Build a MagicMock prisma_client whose env-vars table returns ``row``.
tests/unit/proxy/mcp_server/test_mcp_env_vars.py:866
↓ 16 callersFunction_named
(count: int, **overrides: object)
tests/unit/proxy/public_endpoints/public_v1/test_model_hub.py:56
↓ 16 callersFunction_native
(scenario: Scenario, peer: Peer, **limits: JsonValue)
tests/integration/routing/test_responses_websocket_turn_admission.py:170
↓ 16 callersFunction_objects
(value: JsonValue)
tests/integration/providers/test_responses_compaction_items_wire.py:270
↓ 16 callersFunction_one_second_wav
()
tests/unit/llms/openai/transcriptions/test_gpt_transcribe.py:441
↓ 16 callersFunction_only
(wire: Wire)
tests/integration/messages_endpoint/providers/anthropic/test_anthropic_safeguards_beta_wire.py:189
↓ 16 callersFunction_patch_translation_mappings
Point the unified guardrail at ``mappings`` for one test, restored by pytest. Every override goes through this one seam: competing writers to the
tests/unit/proxy/guardrails/guardrail_hooks/unified_guardrails/test_unified_guardrail.py:114
↓ 16 callersFunction_patched
Patch credentials, request prep, and the HTTP post for a checks call.
tests/unit/proxy/guardrails/guardrail_hooks/test_bedrock_invoke_guardrail_checks.py:39
↓ 16 callersFunction_pdf_cost
(model: str, pdf_base64: str, wrap: Callable[[str], Mapping[str, object]] = _as_pdf_document)
tests/unit/litellm_core_utils/test_token_counter.py:2819
↓ 16 callersFunction_plugin_router
(mock_router_instance, plugin, **config_overrides)
tests/unit/router_strategy/test_complexity_router.py:8399
↓ 16 callersMethod_points
(self, model="claude-sonnet-4-5", provider="anthropic", messages=None, system=None, tools=None)
tests/unit/integrations/test_anthropic_cache_control_hook.py:2315
↓ 16 callersFunction_posts
(wire: Wire)
tests/integration/routing/test_complexity_router_databricks_classifier.py:205
↓ 16 callersFunction_price
(*rounds: tuple[int, int])
tests/integration/mcp/test_mcp_llm_endpoints.py:939
↓ 16 callersFunction_prompt
()
tests/integration/spend/test_vertex_regional_uplift_spend.py:109
↓ 16 callersFunction_real_map_bytes
()
tests/unit/litellm_core_utils/test_get_model_cost_map.py:293
↓ 16 callersFunction_redemption
( assertion: str, client_id: str = PUBLIC_APP.client_id, client_secret: str | None = None, aut
tests/unit/proxy/mcp_server/test_id_jag_grant.py:145
↓ 16 callersMethod_reloaded_key
A live key record as ``get_key_object`` would return it: carries real authorization context (key identity, team, org, and an object-permission
tests/unit/proxy/mcp_server/auth/test_user_api_key_auth_mcp.py:6625
↓ 16 callersFunction_resp
(payload, status_code: int = 200)
tests/unit/llms/azure/search/test_bing_grounding_search_transformation.py:31
↓ 16 callersFunction_response_id
(text: str)
tests/integration/providers/test_bedrock_mantle_output_limit_wire.py:341
↓ 16 callersFunction_router
(content: str, config: ComplexityRouterConfig | None = None)
tests/unit/router_strategy/test_llm_v2.py:89
↓ 16 callersMethod_router
( surface: str = "chat", *, peer: bool = False, session: bool = False,
tests/unit/router_strategy/test_complexity_router.py:15563
↓ 16 callersFunction_rows
(router: str, *, want: int)
tests/integration/routing/test_complexity_router_databricks_classifier.py:247
↓ 16 callersFunction_rows_by_exact_id
``find_many`` stand-in for a table where members match only exact user ids.
tests/unit/proxy/management_endpoints/scim/test_scim_v2_endpoints.py:2054
↓ 16 callersFunction_run
Run the script against a stubbed `gh`; returns (decision, stdout).
tests/unit/test_detect_changes.py:79
↓ 16 callersFunction_run
Drives run_configure_wizard's orchestration logic (discovery, validation, config writing, classifier/semantic/adaptive branching) by mocking the f
tests/unit/proxy/client/cli/autoroute/test_wizard.py:47
↓ 16 callersMethod_run
( self, monkeypatch, headers: list[tuple[bytes, bytes]], authenticated: UserAP
tests/unit/proxy/pass_through_endpoints/test_llm_pass_through_endpoints.py:5161
↓ 16 callersMethod_run
(self, provider, destinations, *, failed=False, trees=1)
tests/unit/integrations/otel/test_otel_v2_destinations.py:1230
↓ 16 callersMethod_run_deferred_stream_guardrails
Run non-streaming post-call guardrail hooks on an assembled streaming response, then fire success logging via ``dispatch_success_hand
litellm/proxy/common_request_processing.py:4502
↓ 16 callersFunction_second_turn
(result: JsonValue = _RESULT)
tests/integration/providers/test_ollama_prompt_tools_wire.py:220
↓ 16 callersFunction_seed_shared_a2a_client
Put the one A2A client the cache will hand out behind a mock transport. Seeding has to happen on the test's own event loop, because the client ca
tests/unit/a2a_protocol/test_main.py:358
↓ 16 callersFunction_seed_token
( db, scratch_prefix: str, *, suffix: str = "tok", user_id: str, spend: float = 0.0,
tests/integration/management/test_f7_key_coverage_push.py:16
↓ 16 callersFunction_send
( rig: _Rig, key: str, path: str, *, method: str = "SendMessage", version: str | None
tests/integration/authorization/test_agent_denial_logging.py:317
↓ 16 callersFunction_sent_declarations
(body: Mapping[str, JsonValue])
tests/integration/providers/test_gemini_anyof_null_branches_wire.py:205
↓ 16 callersFunction_sent_request
(client: MagicMock)
tests/unit/llms/fireworks_ai/responses/test_fireworks_ai_responses_transformation.py:93
↓ 16 callersFunction_spend
(row: dict[str, JsonValue])
tests/integration/spend/test_vertex_regional_uplift_spend.py:177
↓ 16 callersFunction_stored_row
(response_id: str, *, responses_api: bool = False)
tests/integration/spend/test_spend_log_tool_payload_content.py:101
↓ 16 callersFunction_stored_upload
(hub: HubClient, enabled: bool = True)
tests/unit/proxy/discovery_endpoints/test_skill_hub_endpoints.py:176
↓ 16 callersFunction_stub_roster_sync
Stand in for the bulk roster write: apply the plan to ``team`` (else to the row the prisma mock answers for the group, else to an empty roster) an
tests/unit/proxy/management_endpoints/scim/test_scim_v2_endpoints.py:97
↓ 16 callersFunction_stub_sync_dns
(monkeypatch: pytest.MonkeyPatch, *ips: str)
tests/unit/router_utils/test_kubernetes_pod_discovery.py:287
← previousnext →3,601–3,700 of 202,479, ranked by callers