MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 11 callersFunctioncache
(server: &MockServer, gcs_path: Option<&str>)
litellm-rust/crates/cache-gcs/tests/support/mod.rs:38
↓ 11 callersFunctioncall_mcp_tool
Call a specific tool with the provided arguments (handles prefixed tool names). A modern ``InputRequiredResult`` is an interim answer, so it
litellm/proxy/mcp_server/operations.py:2935
↓ 11 callersFunctioncallback
()
tests/unit/proxy/test_proxy_server.py:287
↓ 11 callersFunctioncallback
()
tests/unit/proxy/common_utils/test_config_sync_pubsub.py:220
↓ 11 callersFunctioncaller_boundary
( status: int = 200, bodies: SimpleQueue[bytes] | None = None, *, delete_status: int | None = None )
tests/e2e_harness/test_proxy_client.py:87
↓ 11 callersFunctionchat_bodies
(wire: Wire, marker: str)
tests/integration/streaming/test_mid_stream_fallback_continuation.py:433
↓ 11 callersFunctionchat_completion
Follows the exact same API spec as `OpenAI's Chat API https://platform.openai.com/docs/api-reference/chat` ```bash curl -X POST http://
litellm/proxy/proxy_server.py:13194
↓ 11 callersFunctionchat_request
(model: str, marker: str, **fields: JsonValue)
tests/integration/routing/_reasoning_effort_levels_support.py:265
↓ 11 callersMethodchat_status
( self, key: str, model: str, content: str, max_completion_tokens: int | None = None )
tests/e2e/access_control/access_control_client.py:81
↓ 11 callersFunctioncheck
(name: str)
litellm/proxy/auth/auth_checks.py:5916
↓ 11 callersMethodcheck_gdpr
Check GDPR compliance. Returns: List of compliance check results for: - Art. 32: Data protection applied (pr
litellm/proxy/compliance_checks.py:229
↓ 11 callersMethodchunk
Split text into chunks using RecursiveCharacterTextSplitter. Args: text: Text from OCR (if used) file_conten
litellm/rag/ingestion/base_ingestion.py:187
↓ 11 callersMethodchunk_parser
( self, chunk_data: dict[str, object], # mutable-ok: mirrors override contract )
litellm/llms/bedrock/chat/invoke_handler.py:839
↓ 11 callersMethodchunk_parser
(self, chunk: dict)
litellm/llms/ollama/chat/transformation.py:455
↓ 11 callersMethodchunk_parser
(self, chunk: dict)
litellm/llms/openai/chat/gpt_transformation.py:1057
↓ 11 callersFunctioncli_poll_key
CLI polling endpoint - retrieves session from cache and generates JWT. Flow: 1. First poll (no team_id): Returns teams list without gene
litellm/proxy/management_endpoints/ui_sso.py:2736
↓ 11 callersMethodclient
(self)
litellm/llms/custom_httpx/http_handler.py:1612
↓ 11 callersMethodclient_to_backend
Forward response.create events from client to backend.
litellm/responses/streaming_iterator.py:3091
↓ 11 callersMethodclose
()
tests/integration/mcp/test_interactions.py:650
↓ 11 callersMethodclose
(self)
tests/unit/proxy/mcp_server/test_mcp_server_manager.py:19752
↓ 11 callersMethodcomplete_path
(mut self, target: &[&str])
litellm-rust/crates/core-utils/src/url_utils.rs:29
↓ 11 callersFunctioncompute_coverage
( cells: tuple[Cell, ...], covered: frozenset[str], collection_errors: tuple[str, ...] = (), s
tests/e2e/coverage_registry/collector.py:169
↓ 11 callersFunctioncompute_per_user_token_ttl
Compute Redis TTL for a per-user token. Uses server.token_storage_ttl_seconds when configured, capped at the token's remaining lifetime (expi
litellm/proxy/mcp_server/oauth2_token_cache.py:212
↓ 11 callersFunctionconfig
(user_agent: &str)
litellm-rust/crates/http/src/pool.rs:149
↓ 11 callersFunctionconnect
( resolved: Resolution, host: HostServices, breaker: Option<Breaker>, )
litellm-rust/crates/redis-connect/src/connect.rs:40
↓ 11 callersMethodconstruct_url
( self, api_base: str, model: str, api_version: str | None, realtime_p
litellm/llms/azure/realtime/handler.py:190
↓ 11 callersFunctionconsume_sync_stream
(create: Callable[[], Iterable[object]])
tests/rust-python-harness/shared/parity/stream.py:111
↓ 11 callersMethodconverse_chunk_parser
(self, chunk_data: dict)
litellm/llms/bedrock/chat/invoke_handler.py:705
↓ 11 callersMethodcooled
(self, deployment_id: str)
tests/integration/routing/test_payment_required_cooldown.py:79
↓ 11 callersMethodcount_input_file_usage
Count number of requests and tokens in a batch input file. Args: file_id: The file ID to read custom_llm_pro
litellm/proxy/hooks/batch_rate_limiter.py:882
↓ 11 callersFunctioncreate_anthropic_image_param
Create an Anthropic content block from an image URL input. Supports both URL references (for HTTP/HTTPS URLs) and base64 encoding.
litellm/litellm_core_utils/prompt_templates/factory.py:923
↓ 11 callersFunctioncreate_bodies
(requests: tuple[Request, ...])
tests/integration/providers/_dashscope_video_support.py:92
↓ 11 callersFunctioncreate_client
Helper function to create a client from context.
litellm/proxy/client/cli/commands/models.py:104
↓ 11 callersMethodcreate_file
( self, _is_async: bool, create_file_data: CreateFileRequest, api_base: str,
litellm/llms/openai/openai.py:1831
↓ 11 callersFunctioncreate_mock_router
Helper function to create a mock router with fallback configurations.
tests/unit/proxy/auth/test_model_checks_fallbacks.py:13
↓ 11 callersFunctioncreate_user
(user_id: str, created_via: str = "scim_group")
tests/unit/proxy/management_endpoints/scim/test_scim_v2_endpoints.py:4510
↓ 11 callersFunctioncreate_zero_weight_backup_deployment
The other half of a retry pair: healthy, but weight 0, so the weighted shuffle never opens on it. It is reachable only once its sibling is out of
tests/e2e/router/reliability_support.py:284
↓ 11 callersMethodcut
(e,t=this.size)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 11 callersFunctiond
({actionQueue:e,action:t,setState:n})
litellm/proxy/_experimental/out/_next/static/chunks/0dvgjd47fte1d.js:1
↓ 11 callersFunctiond
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 11 callersMethoddecode_container_id
Decode a managed container ID to extract provider, model, and original container ID. Returns: DecodedResponseId with custom_llm_p
litellm/responses/utils.py:855
↓ 11 callersMethoddecrypt_db_variables
Decrypts a dictionary of variables and returns them.
litellm/proxy/proxy_server.py:8237
↓ 11 callersFunctiondecrypt_global_env_var_values
Decrypt ``scope="global"`` env var values in place after reading the DB. Accepts ``MCPEnvVar`` models (``LiteLLM_MCPServerTable``) or plain dicts
litellm/proxy/mcp_server/db.py:287
↓ 11 callersFunctiondefault_image_cost_calculator
Default image cost calculator for image generation Args: model (str): Model name image_response (ImageResponse): Response fr
litellm/cost_calculator.py:3037
↓ 11 callersFunctiondelete_config_general_settings
Delete the db value of this field in litellm general settings. Resets it to it's initial default value on litellm.
litellm/proxy/proxy_server.py:21436
↓ 11 callersFunctiondelete_mcp_server
Delete the mcp server from the db by server_id The server-row delete is the commit point. Per-user credential and env var rows have no F
litellm/proxy/mcp_server/db.py:1011
↓ 11 callersFunctiondeliverable_destinations
The destinations a request can anchor, given what is published to carry them. Anchoring a destination is what tells the operator's own exporter t
litellm/integrations/otel/plumbing/providers.py:1685
↓ 11 callersFunctiondeployment_id
The stable id of a deployment that has no ``model_info.id``: a sha256 over the model group and every litellm_params key and value, in order.
litellm/router_api.py:195
↓ 11 callersFunctiondisplayMode
(mode: string | null | undefined)
ui/litellm-dashboard/src/lib/decisionModels.ts:35
↓ 11 callersFunctione
litellm/proxy/_experimental/out/_next/static/chunks/2j7hjtph8n74b.js:36
↓ 11 callersFunctione$
({control:e})
litellm/proxy/_experimental/out/_next/static/chunks/37cr8te-omsl0.js:1
↓ 11 callersFunctioneA
(e)
litellm/proxy/_experimental/out/_next/static/chunks/14v3irtjifjt2.js:1
↓ 11 callersFunctioneT
()
litellm/proxy/_experimental/out/_next/static/chunks/37cr8te-omsl0.js:1
↓ 11 callersFunctioned
(e,t,r,o,a=!1)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 11 callersFunctioneg
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/0ayyip3c-drm1.js:1
↓ 11 callersFunctionen
(e,t,r)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 11 callersFunctionencrypt_credentials
(credentials: MCPCredentials, encryption_key: str | None)
litellm/proxy/mcp_server/db.py:516
↓ 11 callersFunctionep
({error:e})
litellm/proxy/_experimental/out/_next/static/chunks/2vp9d70y5g3fw.js:1
↓ 11 callersMethodequals
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 11 callersFunctionerror
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 11 callersMethoderror
(&self)
litellm-rust/crates/python-compat/src/literal.rs:74
↓ 11 callersFunctionestimate_request_max_cost
( request_body: dict, route: str, llm_router: Router | None, input_token_counts: Mapping[str,
litellm/proxy/spend_tracking/budget_reservation.py:1317
↓ 11 callersFunctionevict_config_param
(param_name: str, cache: DualCache | None = None)
litellm/proxy/utils.py:5532
↓ 11 callersFunctionextractProxyErrorMessage
(error: unknown)
ui/litellm-dashboard/src/lib/http/client.ts:107
↓ 11 callersFunctionfake_model
(monkeypatch: pytest.MonkeyPatch)
tests/unit/harness/handlers/test_deepagents_handler.py:58
↓ 11 callersFunctionfal_ai_passthrough_cost
(model: str, request_body: Mapping[str, object])
litellm/llms/fal_ai/cost_calculator.py:166
↓ 11 callersMethodfetch
(e,r)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 11 callersMethodfiles
(&self)
litellm-rust/crates/redis-testing/src/tls.rs:93
↓ 11 callersMethodfilter_new_texts_for_session
Return only the text segments not already scanned earlier in this session. Returns ``None`` when incremental scanning is inactive (feature of
litellm/integrations/custom_guardrail.py:705
↓ 11 callersFunctionfilter_out_litellm_params
( kwargs: Mapping[str, object], excluding: Collection[str] = frozenset() )
litellm/utils.py:5242
↓ 11 callersMethodfinal_text
(self, body: Mapping[str, object])
tests/integration/mcp/test_mcp_llm_endpoints.py:552
↓ 11 callersMethodfind_first
( self, where: Mapping[str, object] | None = None, include: Mapping[str, b
litellm/proxy/management_endpoints/customer_endpoints.py:76
↓ 11 callersMethodfind_many
( self, where: Mapping[str, object], take: int = ..., order: Union[Mapping[str
enterprise/litellm_enterprise/proxy/hooks/managed_files.py:332
↓ 11 callersMethodfind_unique
(self, *, where: Mapping[str, object])
litellm/proxy/management_helpers/utils.py:80
↓ 11 callersFunctionflush_autorouter_turn_transactions
Drain a queue batch into the rollup, one upsert per turn. Statements run sequentially in per-session event order: a turn's classification dep
litellm/proxy/db/autorouter_session_rollup.py:586
↓ 11 callersMethodflush_pre
(&self)
litellm-rust/crates/redis-store/src/request.rs:114
↓ 11 callersFunctionforward
( request: Request, identity: Identity, path: str, connection: Connection | None, client:
litellm/proxy/lens/adapter.py:141
↓ 11 callersFunctionforwarded_internal_call_metadata
Parent metadata, minus its budget reservation, stamped with the sub-call's origin. For sub-calls made inside the parent request (classifier, embe
litellm/litellm_core_utils/internal_call_metadata.py:215
↓ 11 callersMethodfrom_config_yaml
Initialize WebSearchInterceptionLogger from proxy config.yaml parameters. Args: config: Configuration dictionary from li
litellm/integrations/websearch_interception/handler.py:547
↓ 11 callersFunctionfrom_py_argument
Converts a `#[pyo3(from_py_with = ...)]` argument, reporting failures as `ValueError` so a bad argument reads as a bad argument rather than as whateve
litellm-rust/crates/host-python/src/marshal.rs:13
↓ 11 callersFunctiongateway_injected
(response_id: str)
tests/integration/providers/_cache_control_marks_support.py:430
↓ 11 callersMethodgetById
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 11 callersFunctionget_access_token_async
Async version of get_access_token.
litellm/llms/gigachat/authenticator.py:131
↓ 11 callersMethodget_agent_by_id
The agent registered under ``agent_id``, if any.
litellm/proxy/auth/handle_jwt.py:191
↓ 11 callersMethodget_api_base
(api_base: str | None = None)
litellm/llms/anthropic/common_utils.py:1676
↓ 11 callersMethodget_azure_ad_token
( &self, inputs: &AzureAuthInputs, env_lookup: &(dyn Fn(&str) -> Option<String> + Sync
litellm-rust/crates/auth-azure/src/resolve.rs:107
↓ 11 callersFunctionget_base_prompt_id
Extract the base prompt ID by stripping the version suffix if present. Examples: >>> get_base_prompt_id("jack_success.v1") "
litellm/proxy/prompts/prompt_registry.py:21
↓ 11 callersFunctionget_batch_cost_rates
(model_info: ModelInfo, usage: Usage, custom_llm_provider: str | None)
litellm/litellm_core_utils/llm_cost_calc/utils.py:377
↓ 11 callersMethodget_cache
(self, key, parent_otel_span=None, **kwargs)
tests/unit/router_utils/test_health_state_cache.py:151
↓ 11 callersFunctionget_completion_messages
Ensures messages alternate between user and assistant roles by adding placeholders only when there are consecutive messages of the same role.
litellm/litellm_core_utils/prompt_templates/common_utils.py:760
↓ 11 callersFunctionget_custom_llm_provider_from_request_body
Get the `custom_llm_provider` from the request body Safely reads the request body
litellm/proxy/common_utils/openai_endpoint_utils.py:55
↓ 11 callersFunctionget_custom_provider_from_data
(data: dict[str, Any])
litellm/proxy/video_endpoints/utils.py:44
↓ 11 callersFunctionget_fallback_model_group
Returns: - fallback_model_group: List[str] of fallback model groups. example: ["gpt-4", "gpt-3.5-turbo"] - generic_fallback_idx: int of t
litellm/router_utils/fallback_event_handlers.py:612
↓ 11 callersMethodget_file_content
Fetch the content of a file from the GitLab repository at the given ref (tag, branch, or commit SHA). If `ref` is None, uses self.ref
litellm/integrations/gitlab/gitlab_client.py:179
↓ 11 callersMethodget_job
(job_name: str)
tests/unit/proxy/pass_through_endpoints/llm_provider_handlers/test_transcribe_passthrough_logging_handler.py:324
↓ 11 callersFunctionget_key_models
Returns: - List of model name strings - Empty list if no models set - If model_access_groups is provided, only return models that are
litellm/proxy/auth/model_checks.py:145
↓ 11 callersFunctionget_model_cost_map_provenance
()
litellm/litellm_core_utils/get_model_cost_map.py:524
↓ 11 callersMethodget_model_for_tier
Get the model name for a given complexity tier. Args: tier: The complexity tier. Returns: The model
litellm/router_strategy/complexity_router/complexity_router.py:3079
↓ 11 callersFunctionget_optional_params_transcription
( model: str, custom_llm_provider: str, language: str | None = None, languages: Sequence[str]
litellm/utils.py:4508
↓ 11 callersMethodget_param
(self, param_name: str)
litellm/proxy/roi_calculator/sync.py:50
← previousnext →6,201–6,300 of 202,479, ranked by callers