Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/BerriAI/litellm
/ functions
Functions
202,479 in github.com/BerriAI/litellm
⨍
Functions
202,479
◇
Types & classes
26,341
↳
Endpoints
5,595
↓ 5 callers
Method
get_prompt_template
( self, prompt_id: str, prompt_variables: Mapping[str, object] | None = None,
litellm/integrations/gitlab/gitlab_prompt_manager.py:332
↓ 5 callers
Function
get_provider_name
Resolve provider aliases to canonical provider names. Args: provider: Provider name (may be an alias) Returns: Canonica
litellm/anthropic_beta_headers_manager.py:233
↓ 5 callers
Method
get_provider_realtime_config
( model: str, provider: LlmProviders, drop_params: bool = False, litellm_param
litellm/utils.py:11371
↓ 5 callers
Function
get_provider_request_id
(headers: object)
litellm/litellm_core_utils/llm_response_utils/get_headers.py:13
↓ 5 callers
Function
get_provider_response_headers_from_hidden_params
(response: object)
litellm/litellm_core_utils/core_helpers.py:1196
↓ 5 callers
Method
get_redis_lock_key
(cronjob_id: str)
litellm/proxy/db/db_transaction_queue/pod_lock_manager.py:45
↓ 5 callers
Function
get_redoc_url
Get the Redoc URL from the environment variables. - If REDOC_URL is set, return it. - If NO_REDOC is True, return None. - Otherwise,
litellm/proxy/utils.py:9751
↓ 5 callers
Method
get_registered_pass_through_route
Get passthrough params for a given route and optionally filter by HTTP method
litellm/proxy/pass_through_endpoints/pass_through_endpoints.py:4163
↓ 5 callers
Method
get_remove
Returns remove list, defaulting to empty list if not specified.
litellm/types/proxy/policy_engine/policy_types.py:161
↓ 5 callers
Method
get_request_response_payload
(self, request_id, start_time_utc, end_time_utc)
tests/unit/proxy/spend_tracking/test_spend_management_endpoints.py:2771
↓ 5 callers
Method
get_routes_for_mounted_app
Get routes for a mounted sub-application.
litellm/proxy/common_utils/get_routes.py:44
↓ 5 callers
Function
get_scim_base
Base SCIM v2 endpoint for resource discovery per RFC 7644 Section 4. Returns a ListResponse of ResourceTypes supported by this SCIM service
litellm/proxy/management_endpoints/scim/scim_v2.py:1591
↓ 5 callers
Method
get_secret_str
( &self, name: &str, default_value: Option<SecretValue>, )
litellm-rust/crates/secrets/src/resolver.rs:115
↓ 5 callers
Function
get_server_root_paths
The normalized ``SERVER_ROOT_PATHS`` prefixes, empty when unset.
litellm/proxy/middleware/per_request_root_path_middleware.py:84
↓ 5 callers
Method
get_spend_logs_from_redis_buffer
Atomically take up to ``limit`` parked spend-log rows out of Redis.
litellm/proxy/db/db_transaction_queue/redis_update_buffer.py:663
↓ 5 callers
Method
get_state_snapshot
In-memory snapshot for the introspection endpoint. Cheap; no DB hit.
litellm/router_strategy/adaptive_router/adaptive_router.py:253
↓ 5 callers
Function
get_str_from_messages
Converts a list of messages to a string
litellm/litellm_core_utils/prompt_templates/common_utils.py:366
↓ 5 callers
Method
get_stream_options
Pass `stream_options` to the data dict for OpenAI requests
litellm/llms/openai/openai.py:1269
↓ 5 callers
Method
get_streaming_scan_key
(self, responses_so_far: Sequence[object])
litellm/llms/anthropic/chat/guardrail_translation/handler.py:2053
↓ 5 callers
Method
get_streaming_string_so_far
Parse streaming responses and extract accumulated text content. Handles two formats: 1. Raw bytes in SSE (Server-Sent Events
litellm/llms/anthropic/chat/guardrail_translation/handler.py:2082
↓ 5 callers
Method
get_structured_messages
Convert chat completions request data to OpenAI-spec structured messages. Messages are already in OpenAI format, so this is a simple
litellm/llms/openai/chat/guardrail_translation/handler.py:106
↓ 5 callers
Function
get_tag_daily_activity
Get daily activity for specific tags or all tags. Args: tags (Optional[str]): Comma-separated list of tags to filter by. If not prov
litellm/proxy/management_endpoints/tag_management_endpoints.py:743
↓ 5 callers
Function
get_team_object_from_cache
( key: str, user_api_key_cache: UserApiKeyCache, parent_otel_span: Span | None, )
litellm/proxy/auth/auth_checks.py:3688
↓ 5 callers
Method
get_token_and_url
( self, model: str, auth_header: str | None, gemini_api_key: str | None,
litellm/llms/vertex_ai/vertex_llm_base.py:804
↓ 5 callers
Function
get_tool_policy_registry
Return the global ToolPolicyRegistry singleton.
litellm/proxy/db/tool_registry_writer.py:496
↓ 5 callers
Method
get_unified_file_id
( self, file_id: str, litellm_parent_otel_span: Optional[Span] = None )
enterprise/litellm_enterprise/proxy/hooks/managed_files.py:1004
↓ 5 callers
Method
get_unverified_claims
Decode JWT claims without signature verification. Used for routing decisions before selecting validation path.
litellm/proxy/auth/handle_jwt.py:304
↓ 5 callers
Method
get_url
Build the URL for accessing a secret in CyberArk Conjur. Args: secret_name: Name of the secret (will be URL-encoded)
litellm/secret_managers/cyberark_secret_manager.py:170
↓ 5 callers
Method
get_usage_data
Return usage data for the requested window.
litellm/integrations/focus/database.py:24
↓ 5 callers
Method
get_user_created_file_ids
Get all file ids the caller is allowed to see for a list of model object ids. Service-account keys (no user_id) are scoped to their
enterprise/litellm_enterprise/proxy/hooks/managed_files.py:1632
↓ 5 callers
Function
get_user_credential
Return credential for a user+server pair, or None.
litellm/proxy/mcp_server/db.py:1753
↓ 5 callers
Method
get_vector_store_ids_to_run
Returns the vector store ids to run vector_store_ids can be provided in two ways:
litellm/vector_stores/vector_store_registry.py:158
↓ 5 callers
Method
get_vector_store_indexes_from_db
Get vector stores from the database
litellm/vector_stores/vector_store_registry.py:116
↓ 5 callers
Function
get_vertex_base_model_name
Strip routing prefixes from model name for PSC/endpoint URL construction. Patterns like "bge/", "gemma/", "openai/" are used for internal ro
litellm/llms/vertex_ai/common_utils.py:407
↓ 5 callers
Function
get_weave_otel_config
Retrieves the Weave OpenTelemetry configuration based on environment variables. Environment Variables: WANDB_API_KEY: Required. W&B
litellm/integrations/weave/weave_otel.py:150
↓ 5 callers
Function
github_copilot_per_user_credential_name
The credential name iff these litellm_params select per-user mode.
litellm/llms/github_copilot/per_user_auth.py:675
↓ 5 callers
Function
green
(t: str)
litellm/setup_wizard.py:156
↓ 5 callers
Method
guardrail
The guardrail configured under this name (was ``get_available_guardrail``).
litellm/router_api.py:1291
↓ 5 callers
Function
guardrail_from_db_row
Build a Guardrail from a guardrails table row with its litellm_params decrypted.
litellm/proxy/guardrails/guardrail_registry.py:182
↓ 5 callers
Function
guardrails_usage_logs
Return paginated run logs for a guardrail (or policy) from SpendLogs via index.
litellm/proxy/guardrails/usage_endpoints.py:885
↓ 5 callers
Function
h
()
litellm/proxy/_experimental/out/_next/static/chunks/1u96d84_l-6qz.js:1
↓ 5 callers
Function
h
()
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 5 callers
Function
h0
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:10
↓ 5 callers
Method
handle
(self, scope: Scope, receive: Receive, send: Send)
litellm/proxy/lens/buffering.py:93
↓ 5 callers
Function
handleAllowedToolsChange
(nextAllowedTools: string[])
ui/litellm-dashboard/src/app/(dashboard)/mcp-servers/_components/mcp_tool_configuration.tsx:333
↓ 5 callers
Function
handleCredentialAPIResponse
handleCredentialAPIResponse handles API responses specifically for credential operations
terraform/provider/litellm/utils.go:238
↓ 5 callers
Function
handleVectorStoreAPIResponse
handleVectorStoreAPIResponse handles API responses specifically for vector store operations
terraform/provider/litellm/utils.go:304
↓ 5 callers
Function
handle_bedrock_count_tokens
Handle AWS Bedrock CountTokens API requests. This function processes count_tokens endpoints like: - /v1/messages/count_tokens - /v1/
litellm/proxy/pass_through_endpoints/llm_passthrough_endpoints.py:1396
↓ 5 callers
Function
handle_budget_for_entity
Common helper to handle budget creation/updates for entities (organizations, tags, etc). This function: 1. Creates a new budget if budge
litellm/proxy/management_helpers/utils.py:189
↓ 5 callers
Method
handle_db_exception
Primary handler for `allow_requests_on_db_unavailable` flag. Decides whether to raise a DB Exception or not based on the flag. - If
litellm/proxy/db/exception_handler.py:573
↓ 5 callers
Function
handle_model_based_routing
Orchestrate model-based credential routing for file operations. The model name comes from the caller (embedded in the file id, or a header,
litellm/proxy/openai_files_endpoints/common_utils.py:831
↓ 5 callers
Method
hasRequiredAttrs
()
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 5 callers
Function
has_anthropic_credential
Whether the caller already forwarded an Anthropic credential, in either header.
litellm-rust/crates/llms/src/anthropic/common_utils.rs:135
↓ 5 callers
Function
has_header
Whether ``headers`` carries ``name`` under any casing.
litellm/types/mcp.py:347
↓ 5 callers
Method
hash_token
(self, token: str)
litellm/proxy/utils.py:5900
↓ 5 callers
Method
head
()
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 5 callers
Function
head_sha
(git: Git = REPO_GIT)
scripts/lint_base_counts.py:101
↓ 5 callers
Method
header
(self, value: str)
litellm/proxy/mcp_server/outbound_credentials/types.py:245
↓ 5 callers
Function
header_value
(headers: &'a [(String, String)], name: &str)
litellm-rust/crates/http/src/request.rs:100
↓ 5 callers
Function
heal_incomplete_nodeenv_cache
Delete a nodeenv cache directory left without a Node binary. Returns True when a half-installed toolchain was removed, so the next Prisma inv
litellm-proxy-extras/litellm_proxy_extras/prisma_toolchain.py:156
↓ 5 callers
Function
healthcheck_seconds
(healthcheck: WorkerHealthcheck)
tests/integration/_support/process.py:172
↓ 5 callers
Function
held_slot
Run the with-block while holding a machine-wide slot (or its no-op forms).
scripts/gate_slot_lock.py:133
↓ 5 callers
Function
host_client
(py: Python<'_>, variant: ClientVariant)
litellm-rust/crates/python-bridge/src/http.rs:129
↓ 5 callers
Function
http
(status: u16, body: &str)
litellm-rust/crates/core-utils/src/exception_mapping_utils/mod.rs:270
↓ 5 callers
Function
i
(e)
litellm/proxy/_experimental/out/_next/static/chunks/0ayyip3c-drm1.js:1
↓ 5 callers
Function
i
(e,t,l)
litellm/proxy/_experimental/out/_next/static/chunks/2bjw0usamfm54.js:1
↓ 5 callers
Function
i
(e)
litellm/proxy/_experimental/out/_next/static/chunks/3rvuj9y0gk-rt.js:1
↓ 5 callers
Function
i
(e)
litellm/proxy/_experimental/out/_next/static/chunks/0dvgjd47fte1d.js:1
↓ 5 callers
Function
i
(e,t,r)
litellm/proxy/_experimental/out/_next/static/chunks/33ly5p41miafe.js:1
↓ 5 callers
Function
iG
(e,t,r)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:55
↓ 5 callers
Function
iW
(e,t,r)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:55
↓ 5 callers
Method
ignoreMutation
(e)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 5 callers
Function
image_generation
( prompt: str, model: str | None = None, n: int | None = None, quality: str | ImageGenerationR
litellm/images/main.py:211
↓ 5 callers
Function
immutableToJS
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 5 callers
Method
increment
`DualCache.async_increment_cache`: memory, then `INCRBYFLOAT` keeping an existing TTL, else setting `ttl` or Redis's default. `None` when memory refus
litellm-rust/crates/redis-store/src/dual_cache/increment.rs:25
↓ 5 callers
Method
increment_deployment
One deployment's tokens and requests, `async_increment_pipeline` on its own round trip, with the totals mirrored back into memory as `int`s.
litellm-rust/crates/redis-store/src/router_usage/mod.rs:54
↓ 5 callers
Function
increment_deployment_failures_for_current_minute
In-Memory: Increments the number of failures for the current minute for a deployment_id
litellm/router_utils/router_callbacks/track_deployment_metrics.py:61
↓ 5 callers
Method
increment_local
(self, counter: str, amount: float)
tests/unit/redis/stores/spend_counters_double.py:241
↓ 5 callers
Method
increment_with_floor
(self, key: str, value: int, ttl: int)
tests/unit/router_strategy/test_least_busy.py:219
↓ 5 callers
Function
index
(raw: &Value)
litellm-rust/crates/redis-store/src/rate_limits/scripts.rs:217
↓ 5 callers
Function
inherit
(py: Python<'_>, locals: &Bound<'_, PyDict>)
litellm-rust/crates/python-bridge/src/preflight.rs:151
↓ 5 callers
Function
inherit_credentials_from_existing_server
( payload: NewMCPServerRequest, )
litellm/proxy/management_endpoints/mcp_management_endpoints.py:937
↓ 5 callers
Function
initialize_guardrail
(litellm_params: LitellmParams, guardrail: Guardrail)
litellm/proxy/guardrails/guardrail_hooks/decision_model/__init__.py:72
↓ 5 callers
Method
inject
( self, carrier: CarrierT, context: Context | None = None, setter: Setter[Carr
litellm/integrations/otel/trace_response.py:45
↓ 5 callers
Function
inline_request_body
Build an ``openapi_extra["requestBody"]`` for a route that reads its body with ``request.body()``. Swagger UI resolves ``$ref`` against the
litellm/proxy/common_utils/custom_openapi_spec.py:460
↓ 5 callers
Function
inner
()
tests/unit/caching/test_redis_cluster_cache.py:517
↓ 5 callers
Method
input_tpm_for
(self, ptus: int)
litellm/llms/azure/ptu_capacity.py:43
↓ 5 callers
Method
insertText
(e,t,n)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 5 callers
Function
insert_spend_logs
( executor: impl PgExecutor<'_>, logs: &[SpendLog], )
litellm-rust/crates/db/src/spend/spend_logs.rs:83
↓ 5 callers
Function
integer
(value: &Value)
litellm-rust/crates/redis-store/src/rate_limits/scripts.rs:188
↓ 5 callers
Function
intersect_supported_reasoning_efforts
Deployments without metadata (None) never narrow the group; an effort survives only when every deployment with metadata accepts it, so the group o
litellm/litellm_core_utils/reasoning_effort_capability.py:528
↓ 5 callers
Method
into_response
(self)
litellm-rust/crates/gateway-ui/src/error.rs:66
↓ 5 callers
Method
into_result
(self)
litellm-rust/crates/auth-azure/src/native.rs:107
↓ 5 callers
Function
invalid_request
(response: httpx.Response)
tests/integration/compatibility/_status_code_audit.py:205
↓ 5 callers
Method
invalidate
Evict one cached token so the next `get_or_compute` re-mints (e.g. after an upstream 401). Bumping the guard's generation is what makes the e
litellm/proxy/mcp_server/outbound_credentials/token_endpoint.py:188
↓ 5 callers
Method
invalidate
(self, user_id: str, server_id: str)
tests/unit/proxy/mcp_server/test_mcp_server_manager.py:17103
↓ 5 callers
Function
invalidate_cached_object_permissions
Drop permission rows an entitlement change makes stale. ``get_object_permission`` caches a row under its own id separate from the entity's cache
litellm/proxy/management_helpers/object_permission_utils.py:201
↓ 5 callers
Method
invalidate_where
(&self, predicate: impl Fn(&K) -> bool + Send + Sync + 'static)
litellm-rust/crates/secrets-types/src/cache.rs:68
↓ 5 callers
Function
invariant
(s,o)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 5 callers
Function
invoke_chunk
(inner: JsonValue)
tests/code_coverage_tests/test_provider_cache.py:923
← previous
next →
16,001–16,100 of 202,479, ranked by callers