MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 5 callersMethod_get_file_part
(self, contents: list)
tests/unit/llms/vertex_ai/gemini/test_vertex_ai_gemini_transformation.py:1692
↓ 5 callersFunction_get_gemini_function_response_inline_data_parts
(result)
tests/unit/litellm_core_utils/prompt_templates/test_litellm_core_utils_prompt_templates_factory.py:246
↓ 5 callersFunction_get_guardrail_field
(g: "_DbOrConfigGuardrail", field: _GuardrailStrField)
litellm/proxy/guardrails/usage_endpoints.py:411
↓ 5 callersFunction_get_guardrails_list_response
Helper function to get the guardrails list response
litellm/proxy/guardrails/guardrail_endpoints.py:138
↓ 5 callersMethod_get_headers
Get the headers for API requests, including authorization if api_key is set. Returns: Dict[str, str]: Headers to use for
litellm/proxy/client/credentials.py:27
↓ 5 callersMethod_get_headers
Get the headers for API requests, including authorization if api_key is set. Returns: Dict[str, str]: Headers to use for
litellm/proxy/client/models.py:30
↓ 5 callersMethod_get_headers
Get the headers for API requests, including authorization if api_key is set. Returns: Dict[str, str]: Headers to use for
litellm/proxy/client/keys.py:29
↓ 5 callersMethod_get_headers
(self)
litellm/proxy/client/users.py:19
↓ 5 callersMethod_get_http_exception_for_blocked_guardrail
Get the HTTP exception for a blocked guardrail, similar to Bedrock's implementation.
litellm/proxy/guardrails/guardrail_hooks/lakera_ai_v2.py:848
↓ 5 callersMethod_get_image_files_for_request
( self, image: FileTypes | None, )
litellm/llms/recraft/image_edit/transformation.py:144
↓ 5 callersMethod_get_initiator
Determine X-Initiator header value based on input analysis. Based on copilot-api's hasAgentInitiator logic: - Returns "agent
litellm/llms/github_copilot/responses/transformation.py:346
↓ 5 callersMethod_get_input_file_id_from_vertex_ai_batch_response
Gets the input file id from the Vertex AI Batch response
litellm/llms/vertex_ai/batches/transformation.py:299
↓ 5 callersMethod_get_invitation_link
Get invitation link for the user
enterprise/litellm_enterprise/enterprise_callbacks/send_emails/base_email.py:857
↓ 5 callersFunction_get_list_files
(path: str)
tests/unit/proxy/openai_files_endpoint/test_files_endpoint.py:3191
↓ 5 callersMethod_get_masked_api_base
(self, api_base: str | None)
litellm/litellm_core_utils/litellm_logging.py:1653
↓ 5 callersFunction_get_mcp_servers_in_path
Get the MCP servers from the path
litellm/proxy/mcp_server/server.py:1276
↓ 5 callersFunction_get_messages_for_spend_logs_payload
( standard_logging_payload: StandardLoggingPayload | None, metadata: dict | None = None, )
litellm/proxy/spend_tracking/spend_tracking_utils.py:1259
↓ 5 callersMethod_get_metrics
(self)
litellm/proxy/middleware/admission_control_middleware.py:129
↓ 5 callersMethod_get_openai_compatible_provider_info
Get the OpenAI compatible provider info for Baseten
litellm/llms/baseten/chat.py:92
↓ 5 callersMethod_get_or_assign_tool_output_index
(self, call_id: str)
litellm/responses/litellm_completion_transformation/streaming_iterator.py:305
↓ 5 callersMethod_get_permission_for_tool_call
( self, tool_call: ChatCompletionMessageToolCall, judged_name: str | None = None )
litellm/proxy/guardrails/guardrail_hooks/tool_permission.py:883
↓ 5 callersMethod_get_pkce_userinfo
Fetches user info from the userinfo endpoint. Falls back to decoding the id_token if the endpoint is unavailable.
litellm/proxy/management_endpoints/ui_sso.py:4557
↓ 5 callersFunction_get_priority_settings
Get the priority reservation settings, guaranteed to be non-None. The settings are lazy-loaded in litellm.__init__ and always return an inst
litellm/proxy/hooks/dynamic_rate_limiter_v3.py:49
↓ 5 callersFunction_get_realtime_http_provider_config
Return (provider_config, resolved_api_base, resolved_api_key) for the realtime HTTP endpoints (client_secrets / realtime_calls). Uses Pr
litellm/realtime_api/main.py:244
↓ 5 callersMethod_get_redis_increment_queue_lock
(self)
litellm/router_strategy/budget_limiter.py:491
↓ 5 callersFunction_get_redis_url_kwargs
Connection kwargs that redis-py forwards from ``from_url`` down to the connection. ``from_url`` is declared as ``(cls, url, **kwargs)``, so intro
litellm/_redis.py:123
↓ 5 callersMethod_get_remaining_hours_for_budget_reset
Get remaining hours for budget reset
litellm/integrations/prometheus.py:4955
↓ 5 callersMethod_get_request_headers
Get the headers for Vault API requests. Authentication priority: 1. AppRole (if role_id and secret_id are configured)
litellm/secret_managers/hashicorp_secret_manager.py:377
↓ 5 callersMethod_get_request_params
Extract request parameters like temperature and max_tokens, preferring StandardLoggingPayload.model_parameters. Returns dict
litellm/integrations/newrelic/newrelic.py:445
↓ 5 callersMethod_get_request_tool_targets
(self, tool: object)
litellm/proxy/guardrails/guardrail_hooks/tool_permission.py:1153
↓ 5 callersFunction_get_response_headers
Extract and return the response headers from an exception, if present. Used for accurate retry logic.
litellm/litellm_core_utils/exception_mapping_utils.py:214
↓ 5 callersFunction_get_response_id
(response: object)
litellm/proxy/container_endpoints/ownership.py:105
↓ 5 callersFunction_get_scim_admin_group
Get the scim_admin_group setting from litellm_settings. Returns the configured admin group identifier, or None when unset so callers lea
litellm/proxy/management_endpoints/scim/scim_v2.py:439
↓ 5 callersMethod_get_secret_manager_optional_params
( team_id: str | None, )
litellm/proxy/hooks/key_management_event_hooks.py:455
↓ 5 callersMethod_get_session_iterator
Async context manager for yielding an HTTP session. Logic: 1. If running in the main thread (where the object was initialize
litellm/proxy/guardrails/guardrail_hooks/presidio.py:390
↓ 5 callersMethod_get_spans_by_name
Get all spans with the given name
tests/unit/integrations/test_opentelemetry.py:2953
↓ 5 callersFunction_get_streaming_fallback_metadata
( response_obj: object, )
litellm/proxy/proxy_server.py:10234
↓ 5 callersMethod_get_team_config
(self, team_id: str, all_teams_config: list[dict])
litellm/proxy/proxy_server.py:6386
↓ 5 callersFunction_get_temporary_mcp_server_from_redis
Best-effort read from Redis shared cache. Returns None on miss/errors. Values must be encrypted strings (same contract as _cache_tem
litellm/proxy/management_endpoints/mcp_management_endpoints.py:566
↓ 5 callersFunction_git_over
(history: _History)
tests/unit/test_lint_base_counts.py:407
↓ 5 callersFunction_github
(transport: httpx.MockTransport)
tests/unit/proxy/roi_calculator/test_github.py:62
↓ 5 callersFunction_google
(continuation: Continuation = _continues)
tests/integration/providers/test_gemini_long_decode_chaos.py:141
↓ 5 callersFunction_grant
(*search_tools: str)
tests/integration/authorization/test_search_tool_deny_by_default.py:29
↓ 5 callersFunction_granted_raise
A team admin granted max_budget and raise_max_budget on a team budgeted at 10, standalone or in `org_table`.
tests/unit/proxy/management_endpoints/test_team_endpoints.py:18563
↓ 5 callersFunction_grounding_guardrail
(from_messages: bool = False)
tests/unit/proxy/guardrails/guardrail_hooks/test_bedrock_guardrails.py:2452
↓ 5 callersFunction_grounding_messages
()
tests/unit/proxy/guardrails/guardrail_hooks/test_bedrock_guardrails.py:2460
↓ 5 callersFunction_group_delete_mocks
Prisma and its transaction, whose users are left in no team once the delete detached them and whose group lookup answers ``team``, plus the patche
tests/unit/proxy/management_endpoints/scim/test_scim_v2_endpoints.py:3233
↓ 5 callersFunction_guardrail
(litellm_params: LitellmParams)
tests/unit/proxy/guardrails/guardrail_hooks/test_decision_model.py:642
↓ 5 callersFunction_guardrail
(*, is_detector_server: bool, detector_params: dict[str, object] | None)
tests/unit/proxy/guardrails/guardrail_hooks/ibm_guardrails/test_ibm_detector.py:37
↓ 5 callersMethod_guardrail
(self, **overrides)
tests/unit/proxy/guardrails/guardrail_hooks/test_bedrock_guardrails.py:5002
↓ 5 callersFunction_guardrail_entries
(model: str, count: int = 1)
tests/integration/observability/test_azure_content_safety_audit.py:332
↓ 5 callersMethod_guardrail_tag_budget_harness
( monkeypatch, request_body: dict, guardrail_tags: Sequence[str], route: str =
tests/unit/proxy/test_common_request_processing.py:771
↓ 5 callersMethod_handle
(self)
tests/e2e/provider_edge.py:1064
↓ 5 callersMethod_handle_message_with_file
Mistral API supports only 'file_id' in message content with type 'file'.
litellm/llms/mistral/chat/transformation.py:544
↓ 5 callersFunction_has_priorities
Return True if any priority weight is set (non-None and > 0).
litellm/proxy/mcp_server/sampling_handler.py:166
↓ 5 callersMethod_has_vision_input
Check if input contains vision content (images). Based on copilot-api's hasVisionInput and containsVisionContent logic. Recu
litellm/llms/github_copilot/responses/transformation.py:382
↓ 5 callersFunction_hash
(key: str)
tests/integration/management/test_key_default_allowed_routes.py:87
↓ 5 callersFunction_hashed
(key: str)
tests/integration/management/test_team_delete_large_membership.py:81
↓ 5 callersFunction_headers
(marker: str)
tests/integration/_support/bedrock_runtime_peer.py:64
↓ 5 callersMethod_headers
(self, headers: dict, api_key: str | None = None)
tests/unit/llms/edenai/messages/test_edenai_anthropic_messages_transformation.py:121
↓ 5 callersFunction_hits
(sweep: str, location: str, blob: bytes | str, canaries: Sequence[Canary])
tests/integration/security/_sweeps.py:209
↓ 5 callersMethod_holds_session_updates_until_first_content
(self)
litellm/litellm_core_utils/realtime_streaming.py:1140
↓ 5 callersFunction_honors_one_hour_cache_ttl
( standard_logging_object: StandardLoggingPayload, litellm_params: Mapping[str, object] )
litellm/router_utils/pre_call_checks/prompt_caching_deployment_check.py:232
↓ 5 callersMethod_hook_reporting
(upstream_failure: Exception, after_report=None)
tests/unit/proxy/test_common_request_processing.py:11723
↓ 5 callersFunction_host
(region: str)
tests/integration/providers/test_strands_decider_agentcore_wire.py:174
↓ 5 callersFunction_http_detail_message
(detail: object)
litellm/proxy/mcp_server/operations.py:680
↓ 5 callersFunction_http_scope
(headers: list[tuple[bytes, bytes]])
tests/unit/proxy/middleware/test_request_body_decompression_middleware.py:534
↓ 5 callersFunction_hydrate_member_user_details
Attach ``user_alias`` and fill in a missing ``user_email`` from ``LiteLLM_UserTable`` in one query.
litellm/proxy/management_endpoints/team_endpoints.py:5357
↓ 5 callersMethod_id_jag_server
(self, server_id: str)
tests/unit/proxy/mcp_server/test_mcp_server_manager.py:3552
↓ 5 callersFunction_id_of
(payload: dict[str, JsonValue])
tests/integration/providers/test_ollama_prompt_tools_wire.py:1671
↓ 5 callersFunction_identity_lookup
(*values: str)
tests/unit/proxy/management_endpoints/scim/test_scim_v2_endpoints.py:5328
↓ 5 callersFunction_image_reply
(usage: JsonValue, include_usage: bool = True)
tests/integration/providers/test_gemini_image_config_and_usage_wire.py:41
↓ 5 callersFunction_image_response_with_dimensions
(dimensions: tuple[tuple[int, int], ...])
tests/unit/llms/fal_ai/test_cost_calculator.py:24
↓ 5 callersFunction_image_scans
(scans: list[list[dict[str, JsonValue]]])
tests/integration/observability/test_bedrock_guardrail_attachments.py:319
↓ 5 callersFunction_image_urls_in_user_messages
(messages)
tests/unit/llms/anthropic/messages/adapters/test_anthropic_messages_adapters_transformation.py:4687
↓ 5 callersMethod_images_seen
(self, content)
tests/unit/llms/anthropic/chat/guardrail_translation/test_anthropic_guardrail_handler.py:2243
↓ 5 callersMethod_import_litellm_with_env
(env_override: dict)
tests/unit/integrations/test_anthropic_cache_control_hook.py:3510
↓ 5 callersFunction_init
(litellm_params: LitellmParams)
tests/unit/proxy/guardrails/guardrail_hooks/test_conduct.py:128
↓ 5 callersMethod_init_search_tools_in_db
Initialize search tools from database into the router on startup.
litellm/proxy/proxy_server.py:9842
↓ 5 callersMethod_initialize_budget_metrics
Generic method to initialize budget metrics for teams or API keys. Args: data_fetch_function: Function to fetch data wit
litellm/integrations/prometheus.py:4056
↓ 5 callersMethod_initialize_customer_budget_metrics
(self)
litellm/integrations/prometheus.py:4219
↓ 5 callersMethod_initialize_remaining_budget_metrics
Helper to initialize remaining budget metrics for all teams, API keys, and users.
litellm/integrations/prometheus.py:4288
↓ 5 callersMethod_inject
(self, model, api_base=None, prompt_cache_options=None, custom_llm_provider=None)
tests/unit/integrations/test_anthropic_cache_control_hook.py:4274
↓ 5 callersMethod_inject_credentials
Inject connection-level credentials and metadata into call_kwargs.
litellm/responses/streaming_iterator.py:3478
↓ 5 callersFunction_inline_part
(name: str | None, value: str, size_limit: int | None, message_index: int)
litellm/proxy/guardrails/guardrail_hooks/ovalix/ovalix_extraction.py:74
↓ 5 callersFunction_input
()
tests/integration/security/test_hide_secrets_tool_traffic.py:187
↓ 5 callersFunction_input_item_provenance
( raw_input: Sequence[object], expected_messages: Sequence[object], )
litellm/llms/openai/responses/guardrail_translation/handler.py:505
↓ 5 callersFunction_input_text
(observation: LangfuseObservation)
tests/e2e/logging/test_otel_v2_langfuse_generation_output_e2e.py:136
↓ 5 callersFunction_inspect_input
(input_items)
tests/unit/responses/litellm_completion_transformation/test_reasoning_input_item_preservation.py:38
↓ 5 callersFunction_install_router
(monkeypatch, *deployments)
tests/unit/proxy/test_model_list_discoverable.py:27
↓ 5 callersFunction_internal_user_check
(route: str, method: str, role: LitellmUserRoles = LitellmUserRoles.INTERNAL_USER)
tests/unit/proxy/auth/test_route_checks.py:4887
↓ 5 callersMethod_invalidate_spend_counter
Drop a spend counter so the next read reseeds from the committed DB row, the only value that includes increments that raced the reset.
litellm/proxy/common_utils/reset_budget_job.py:613
↓ 5 callersFunction_invoke
(scenario: Scenario, wire: Wire, **extra: JsonValue)
tests/integration/providers/test_bedrock_stream_timeout_wire.py:177
↓ 5 callersMethod_invoke
(self, op: str)
litellm/router_rust/invoke/endpoints.py:1526
↓ 5 callersMethod_invoke
( self, exc: Exception, route_type: str, monkeypatch: pytest.MonkeyPatch,
tests/unit/proxy/test_common_request_processing.py:5229
↓ 5 callersMethod_invoke_add_log
(self, request_data: dict)
tests/unit/integrations/test_custom_guardrail.py:842
↓ 5 callersFunction_invoke_body
(marker: str)
tests/integration/observability/test_bedrock_invoke_stream_post_call_guardrail.py:344
↓ 5 callersFunction_invoke_guardrail_headers
(request: httpx.Request)
tests/unit/llms/bedrock/passthrough/test_bedrock_passthrough_transformation.py:1223
↓ 5 callersMethod_invoke_with_mocked_post
Run a sync litellm.completion() with HTTPHandler.post patched to return a canned moonshot response. Returns (mock_post, response).
tests/unit/llms/bedrock/chat/invoke_transformations/test_amazon_moonshot_transformation.py:110
↓ 5 callersFunction_is_api_route_allowed
- Route b/w api token check and normal token check
litellm/proxy/auth/auth_checks.py:1607
← previousnext →14,401–14,500 of 202,479, ranked by callers