MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 10 callersMethodget_complete_url
( self, api_base: str | None, api_key: str | None, model: str, optiona
litellm/llms/deepgram/audio_transcription/transformation.py:201
↓ 10 callersMethodget_credentials
(self)
litellm/_redis_credential_provider.py:199
↓ 10 callersFunctionget_datadog_service
()
litellm/integrations/datadog/datadog_handler.py:16
↓ 10 callersFunctionget_external
GET an absolute URL outside the proxy (e.g. a public /.well-known document). Unlike the transport wrappers there is no proxy base url and no proxy
tests/e2e/e2e_http.py:478
↓ 10 callersFunctionget_fal_ai_image_generation_config
Get the appropriate Fal AI image generation configuration based on the model. Args: model: The Fal AI model name (e.g., "fal-ai/imag
litellm/llms/fal_ai/image_generation/__init__.py:43
↓ 10 callersFunctionget_form_data
Read form data from request Handles when OpenAI SDKs pass form keys as `timestamp_granularities[]="word"` instead of `timestamp_granularitie
litellm/proxy/common_utils/http_parsing_utils.py:598
↓ 10 callersFunctionget_fuse_presets
()
litellm/router_strategy/complexity_router/fuse_presets.py:40
↓ 10 callersFunctionget_guardrail_info
Get detailed information about a specific guardrail by ID 👉 [Guardrail docs](https://docs.litellm.ai/docs/proxy/guardrails/quick_start)
litellm/proxy/guardrails/guardrail_endpoints.py:1399
↓ 10 callersMethodget_jobs
(self)
litellm/proxy/common_utils/scheduled_job_stagger.py:94
↓ 10 callersFunctionget_mcp_server
Returns the matching mcp server from the db iff exists
litellm/proxy/mcp_server/db.py:893
↓ 10 callersMethodget_model_access_groups
( self, model_name: str | None = None, team_id: str | None = None )
tests/unit/llms/anthropic/messages/test_safeguards.py:344
↓ 10 callersMethodget_package_license_from_pypi
Fetch license information for a package from PyPI. Prefers the PEP 639 SPDX expression (``info.license_expression``), falls back to t
tests/code_coverage_tests/check_licenses.py:134
↓ 10 callersMethodget_prompt_callback_for_prompt
(self, prompt: PromptSpec)
litellm/proxy/prompts/prompt_registry.py:300
↓ 10 callersMethodget_provider_embedding_config
( model: str, provider: LlmProviders, )
litellm/utils.py:10220
↓ 10 callersMethodget_public_mcp_servers
Return the MCP servers published to the AI Hub via /v1/mcp/make_public. Default (litellm.public_mcp_hub_strict_whitelist=True): mirr
litellm/proxy/mcp_server/mcp_server_manager.py:7406
↓ 10 callersMethodget_response_headers
( headers: httpx.Headers, litellm_call_id: str | None = None, custom_headers: Mapping[
litellm/proxy/pass_through_endpoints/pass_through_endpoints.py:428
↓ 10 callersMethodget_router_model_info
( self, deployment: "dict | Deployment", # mutable-ok: the old parameter type, unchanged
litellm/router_deprecated.py:381
↓ 10 callersFunctionget_salt_key
()
litellm/proxy/common_utils/encrypt_decrypt_utils.py:35
↓ 10 callersMethodget_secret_from_google_secret_manager
( &self, name: &str, )
litellm-rust/crates/secrets-google/src/secret_manager.rs:121
↓ 10 callersMethodget_streaming_scan_key
(self, responses_so_far: Sequence[object])
litellm/llms/openai/chat/guardrail_translation/handler.py:893
↓ 10 callersMethodget_supported_openai_params
(self, model: str)
tests/unit/llms/test_custom_llm.py:523
↓ 10 callersMethodget_team_ids_from_jwt
(self, token: dict)
litellm/proxy/auth/handle_jwt.py:409
↓ 10 callersFunctionget_team_provider_credentials
Resolve upstream credentials for a provider-scoped file operation (e.g. GET /v1/files), which doesn't pin a model. Priority: 1. The
litellm/proxy/openai_files_endpoints/common_utils.py:574
↓ 10 callersMethodget_tracer_to_use_for_request
Get the tracer to use for this request If dynamic headers are present, a temporary tracer is created with the dynamic headers.
litellm/integrations/opentelemetry.py:1121
↓ 10 callersMethodget_ttl
(self, **kwargs)
litellm/caching/base_cache.py:19
↓ 10 callersFunctionget_vendor_from_model
Return the OCI vendor enum for a model name. OCI GenAI uses two ``apiFormat`` values: - ``"COHERE"`` for Cohere models (``cohere.*``) -
litellm/llms/oci/chat/transformation.py:318
↓ 10 callersMethodget_vertex_credentials_from_router_deployments
Resolve vertex pass-through credentials from the live router deployments flagged ``use_in_pass_through``. ``deployment_key_to_vertex
litellm/proxy/pass_through_endpoints/passthrough_endpoint_router.py:225
↓ 10 callersFunctionget_web_search_requests
Tolerantly read ``web_search_requests`` from a ``server_tool_use`` value that may be ``None``, a ``dict``, a ``ServerToolUse`` pydantic insta
litellm/litellm_core_utils/llm_cost_calc/utils.py:153
↓ 10 callersFunctiongithub_api_headers
( access_token: str | None = None, )
litellm/llms/github_copilot/authenticator.py:109
↓ 10 callersFunctiongrey
(t: str)
litellm/setup_wizard.py:164
↓ 10 callersFunctionguardrail_request_data_with_streaming
( data: Mapping[str, object], *, is_streaming: bool, )
litellm/integrations/custom_guardrail.py:207
↓ 10 callersFunctionhandle_cohere_stream_chunk
Parse a single Cohere SSE chunk into a LiteLLM ModelResponseStream. OCI Cohere streams the answer as single-token ``text`` deltas, then restates
litellm/llms/oci/chat/cohere.py:288
↓ 10 callersFunctionhealthy_stream
(identity: str, text: str)
tests/integration/_support/responses_stream.py:109
↓ 10 callersMethodhost_indexes
The indexes the host hands out (`HostIndexes`): id map, name and team indexes, group and deployment names, team public names, provider default ids and
litellm-rust/crates/python-bridge/src/router/mod.rs:888
↓ 10 callersFunctionhumanize_lakera_block_reasons
Turn a Lakera v2 ``breakdown`` list into a plain-language reason string suitable for an advisory message shown to the LLM (e.g. "a potential
litellm/proxy/guardrails/guardrail_hooks/lakera_ai_v2.py:57
↓ 10 callersFunctionidentity_source_ref
``oidc/<kind>/<hash>``: a short, secret-free pointer, stable for identical config and rolling whenever any field does, including a ``*_ref`` point
litellm/llms/base_llm/auth/identity_source.py:54
↓ 10 callersFunctionin_post_response_phase
()
litellm/_internal_context.py:86
↓ 10 callersMethodincrement
`InMemoryCache.increment_cache`: `(current or 0) + amount`, refusing an entry that is not a number and leaving it in place.
litellm-rust/crates/redis-store/src/memory.rs:103
↓ 10 callersFunctioninitialize_guardrail
(litellm_params: "LitellmParams", guardrail: "Guardrail")
litellm/proxy/guardrails/guardrail_hooks/straiker/__init__.py:60
↓ 10 callersFunctioninitialize_python
()
litellm-rust/crates/host-python/src/lib.rs:47
↓ 10 callersMethodinsert_rows
(self, table: str, rows: Sequence[Mapping[str, object]])
litellm/tracing/remote.py:125
↓ 10 callersMethodinto_pyobject
(self, py: Python<'py>)
litellm-rust/crates/host-python/src/marshal.rs:58
↓ 10 callersFunctioninvalid_response
(error: impl std::error::Error + Send + Sync + 'static)
litellm-rust/crates/storage-clickhouse/src/read.rs:204
↓ 10 callersMethodinvalidate_credentials
Drop any cached credential the resolver owns for this `(subject, server)`. Used after an upstream rejects the injected credential, so the nex
litellm/proxy/mcp_server/outbound_credentials/resolver.py:386
↓ 10 callersFunctioninvoke
(router: litellm.Router, surface: Surface, payload: Mapping[str, object], retries: int = 0)
tests/unit/router_strategy/complexity_router/test_context_compaction.py:152
↓ 10 callersFunctionir_to_openai_response
( response: DecisionsIRResponse, request: DecisionsIRRequest, requested_model: str, evidence_f
litellm/llms/openai/decisions/transformation.py:309
↓ 10 callersFunctionisBlank
(value: unknown)
ui/litellm-dashboard/src/components/model_add/federation_field.ts:16
↓ 10 callersFunctionisDecisionMode
(mode: string | null | undefined)
ui/litellm-dashboard/src/lib/decisionModels.ts:32
↓ 10 callersFunctionisRecord
(value: unknown)
ui/litellm-dashboard/src/components/logs/detail/prettyMessagesUtils.ts:17
↓ 10 callersFunctionisUserTeamAdminForSingleTeam
( teamMemberWithRoles: readonly Member[] | null, userID: string, )
ui/litellm-dashboard/src/utils/roles.ts:49
↓ 10 callersMethodis_a
`isinstance(error, <class named name>)`.
litellm-rust/crates/router-core/src/error.rs:423
↓ 10 callersFunctionis_anthropic_oauth_key
Check if a value contains an Anthropic OAuth token (sk-ant-oat*).
litellm/llms/anthropic/common_utils.py:524
↓ 10 callersFunctionis_base64_encoded
(s: str)
litellm/utils.py:9475
↓ 10 callersMethodis_database_service_unavailable_error_in_chain
Like ``is_database_service_unavailable_error`` but also walks the ``__cause__`` / ``__context__`` chain. ``is_database_service_unavai
litellm/proxy/db/exception_handler.py:557
↓ 10 callersMethodis_jwt
(token: str | None)
litellm/proxy/auth/handle_jwt.py:300
↓ 10 callersFunctionis_managed_id
(id_str: str)
tests/e2e/batches/capabilities.py:251
↓ 10 callersFunctionis_unbilled_non_inference_call_from_params
:func:`is_unbilled_non_inference_call` for callers holding raw ``litellm_params``. The call-type and background tests run first so that inference
litellm/litellm_core_utils/internal_call_metadata.py:152
↓ 10 callersFunctionis_valid_api_key
Validates API key format: - sk- keys: must match ^sk-[A-Za-z0-9_-]+$ - hashed keys: must match ^[a-fA-F0-9]{64}$ - Length between 20
litellm/proxy/utils.py:9988
↓ 10 callersMethodjson
(&self)
litellm-rust/crates/inference-ocr/tests/support/mod.rs:104
↓ 10 callersFunctionjson_contains
(value: object, key: object)
litellm/litellm_core_utils/core_helpers.py:199
↓ 10 callersFunctionjudge_target
Resolve `model` the way a call from `team_id` would be. Three outcomes and no others: the router serves it (a deployment, a team-public name,
litellm/litellm_core_utils/llm_judge.py:99
↓ 10 callersFunctionk
litellm/proxy/_experimental/out/_next/static/chunks/3yrgf44a9g52e.js:1
↓ 10 callersFunctionkept_results
(assistant: Event)
tests/integration/providers/_tool_search_support.py:307
↓ 10 callersFunctionkey
(prefix: &str, name: &str)
litellm-rust/crates/cache-testing/src/lib.rs:11
↓ 10 callersFunctionkey_access_group_grants_model
Returns True if the key's `access_group_ids` expand to models that grant access to `model`. Used to let a key's access group override a team'
litellm/proxy/auth/auth_checks.py:5848
↓ 10 callersMethodkeys
(self)
litellm/router_strategy/budget_limiter.py:115
↓ 10 callersFunctionl
(n)
litellm/proxy/_experimental/out/_next/static/chunks/14v3irtjifjt2.js:1
↓ 10 callersMethodlegacy_auth
( self, )
litellm/proxy/mcp_server/contracts.py:100
↓ 10 callersFunctionlh
litellm/proxy/_experimental/out/_next/static/chunks/3yrgf44a9g52e.js:1
↓ 10 callersFunctionlist_guardrails_v2
List the guardrails that are available in the database using GuardrailRegistry 👉 [Guardrail docs](https://docs.litellm.ai/docs/proxy/guardra
litellm/proxy/guardrails/guardrail_endpoints.py:226
↓ 10 callersFunctionlist_key_helper
Helper function to list keys Args: page: int size: int user_id: Optional[str] team_id: Optional[str]
litellm/proxy/management_endpoints/key_management_endpoints.py:7778
↓ 10 callersMethodlist_tools
List all tools available across all MCP Servers. Args: user_api_key_auth: User authentication mcp_auth_heade
litellm/proxy/mcp_server/mcp_server_manager.py:4001
↓ 10 callersMethodlisting_entries
`(response_id, metadata_lookup_id)` for each listed model, de-duplicated by response_id while preserving order. For team-scoped rows
litellm/proxy/common_utils/model_listing_utils.py:466
↓ 10 callersMethodlock
( &self, )
litellm-rust/crates/inference-chat/tests/support/mod.rs:143
↓ 10 callersFunctionlogged
(py: Python<'_>, locals: &Bound<'_, PyDict>, asynchronous: bool)
litellm-rust/crates/callbacks-legacy-python/src/adapter.rs:1829
↓ 10 callersMethodlogger
(&self)
litellm-rust/crates/callbacks-legacy-python/src/adapter.rs:202
↓ 10 callersFunctionlookup
(host: &dyn Host, lookup: ModelInfoLookup)
litellm-rust/crates/router-core/src/model_info.rs:87
↓ 10 callersFunctionm
(e,t,s)
litellm/proxy/_experimental/out/_next/static/chunks/3yrgf44a9g52e.js:1
↓ 10 callersFunctionmakeSequence
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 10 callersFunctionmake_handler
()
tests/unit/llms/codex/harness/test_transformation.py:190
↓ 10 callersFunctionmake_issuer
( issuer_url: str = ISSUER_URL, subject: str = SUBJECT, signing_key_ref: str = SIGNING_KEY_REF,
tests/unit/llms/base_llm/auth/test_identity_source.py:24
↓ 10 callersFunctionmanaged_agent
()
tests/unit/proxy/agent_endpoints/test_managed_identity.py:97
↓ 10 callersMethodmap_openai_params
( self, video_create_optional_params: VideoCreateOptionalRequestParams, model: str, drop_params: b
tests/unit/videos/test_main.py:444
↓ 10 callersMethodmask_value
(self, value: str)
litellm/litellm_core_utils/sensitive_data_masker.py:61
↓ 10 callersMethodmatchFragment
(e,t=0,n=e.childCount)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 10 callersMethodmatches
(self, scope: Scope)
litellm/proxy/pass_through_endpoints/pass_through_endpoints.py:4205
↓ 10 callersMethodmaybeChild
(e)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 10 callersFunctionmaybe_run_chat_completion_agentic_loop
( *, response: ModelResponse, model: str, messages: list[dict[str, object]], optional_para
litellm/litellm_core_utils/chat_completion_agentic_loop.py:362
↓ 10 callersFunctionmcp_server_tool_call
( ctx: ServerRequestContext, params: CallToolRequestParams )
litellm/proxy/mcp_server/server.py:1009
↓ 10 callersFunctionmerge_agent_headers
Merge outbound HTTP headers for A2A agent calls. Merge rules: - Start with ``dynamic_headers`` (values extracted from the incoming client req
litellm/interactions/agents/utils.py:11
↓ 10 callersFunctionmerge_anthropic_beta_headers
Merge anthropic-beta header values, deduplicated and sorted. Either side may arrive as a list rather than a comma-separated string: the Skills su
litellm/llms/anthropic/common_utils.py:550
↓ 10 callersFunctionmessages_body
(model: str, marker: str, *, stream: bool = False)
tests/integration/providers/_anthropic_safeguards_beta_support.py:222
↓ 10 callersFunctionmessages_body
( model: str, request_nonce: str, *, tools: JsonValue, guardrails: Sequence[str] = (TOOL_R
tests/integration/messages_endpoint/test_anthropic_messages_caller_tools_wire.py:268
↓ 10 callersFunctionmicrosoft_interactive_subject
( tenant: str | None, response: Mapping[str, object], endpoints: Mapping[str, str | None], )
litellm/proxy/management_endpoints/sso/agent_subject_enrollment.py:9
↓ 10 callersFunctionmock_open
Helper to create a mock file object
tests/unit/proxy/guardrails/guardrail_hooks/test_model_armor.py:1965
↓ 10 callersFunctionmock_responses_api_response
( mock_response: str = "In a peaceful grove beneath a silver moon, a unicorn named Lumina discovered a hid
litellm/responses/main.py:156
↓ 10 callersMethodmodel_dump
(self)
tests/unit/llms/github_copilot/test_github_copilot_transformation.py:862
↓ 10 callersFunctionmutable_tuned_identities
Heuristic-v1 routers whose current tuning differs from their baseline or shipped default.
litellm/router_strategy/auto_router/auto_router_tuning_baseline.py:133
↓ 10 callersMethodname
(&self)
litellm-rust/crates/token-counter-tiktoken/src/lib.rs:104
↓ 10 callersFunctionnative
(py: Python<'_>, error: Error)
litellm-rust/crates/python-bridge/src/routes/ocr/errors.rs:31
← previousnext →7,101–7,200 of 202,479, ranked by callers