MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 12 callersFunctionchat_body
(model: str, text: str, **extra: JsonValue)
tests/integration/caching/response_cache_case.py:362
↓ 12 callersFunctionchat_file
(file_data: JsonValue, filename: JsonValue = "document.pdf")
tests/integration/_support/pdf_document.py:117
↓ 12 callersMethodcheck_and_fix_namespace
(self, key: str)
tests/unit/proxy/anthropic_endpoints/test_gateway_endpoints.py:85
↓ 12 callersFunctioncheck_team_member_model_access
Check if a team member's per-member model scope allows access to the requested model. Only enforced when the member's budget table has a non
litellm/proxy/auth/auth_checks.py:7164
↓ 12 callersMethodclaim
(self, interaction_id)
tests/unit/interactions/test_background_cost_polling.py:1174
↓ 12 callersFunctionclassify_upstream_token_rejection
Classify a token-endpoint rejection into exactly one fault: a body with an RFC 6749 §5.2 ``error`` field goes through blame assignment (:func:`_cl
litellm/proxy/mcp_server/faults/classify.py:102
↓ 12 callersMethodclearTimeout
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 12 callersMethodclose
Close the aiohttp client session and transport if we own them.
litellm/llms/custom_httpx/aiohttp_handler.py:116
↓ 12 callersMethodclose
(self)
tests/unit/harness/sandbox/test_docker.py:29
↓ 12 callersMethodclose
(self)
tests/unit/llms/custom_httpx/test_llm_http_handler.py:5160
↓ 12 callersFunctioncodex_configure_state_path
(settings_path: Path)
litellm/proxy/client/cli/commands/codex_settings.py:59
↓ 12 callersFunctioncollect
Records the string at `key`, along with the write that replaces it.
litellm/proxy/guardrails/guardrail_hooks/llm_shield_proxy/payload.py:54
↓ 12 callersFunctioncollect
Apply an extractor table to ``source``, dropping ``None`` results.
litellm/integrations/otel/mappers/utils.py:92
↓ 12 callersFunctioncollect_texts_sync
(stream: object)
tests/unit/test_router/core/streaming_helpers.py:226
↓ 12 callersMethodcombine_usage_objects
Combine multiple Usage objects into a single Usage object, checking model keys for nested values.
litellm/cost_calculator.py:3474
↓ 12 callersFunctioncomplete
(endpoint: Endpoint)
tests/integration/providers/_gemini_long_decode_support.py:510
↓ 12 callersFunctioncomplete_connect_flow
Mint the code only after a deliberate POST by the sealed user. A scoped flow additionally requires its sealed server to have a live vendor creden
litellm/proxy/mcp_server/gateway_dcr_flow.py:1195
↓ 12 callersMethodcontains
(&self, character: char)
litellm-rust/crates/token-counter-fast/src/unicode_classes.rs:45
↓ 12 callersMethodcontentMatchAt
(e)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 12 callersMethodcontent_length
(&self)
litellm-rust/crates/gateway-forward/tests/support/mod.rs:166
↓ 12 callersFunctionconvert_to_anthropic_tool_invoke
OpenAI tool invokes: { "role": "assistant", "content": null, "tool_calls": [ { "id": "call_abc123",
litellm/litellm_core_utils/prompt_templates/factory.py:2160
↓ 12 callersFunctioncost_at
(column_suffix: str)
tests/unit/llms/sail/helpers.py:19
↓ 12 callersMethodcount
Count ordinary text; `fast` accelerates supported encodings and otherwise counts normally.
litellm/litellm_core_utils/tokenizer.py:147
↓ 12 callersMethodcount
(self, where: Mapping[str, object] | None = None)
litellm/proxy/management_endpoints/scim/scim_v2.py:140
↓ 12 callersMethodcounter
(&self, py: Python<'_>, fast: bool)
litellm-rust/crates/python-bridge/src/tokenizer.rs:502
↓ 12 callersMethodcreate
(self, *, data: Mapping[str, object], include: Mapping[str, object] | None = None)
litellm/proxy/auth/auth_checks.py:272
↓ 12 callersFunctioncreate_fallback
Create or update fallbacks for a specific model. This endpoint allows you to configure fallback models separately from the general config.
litellm/proxy/management_endpoints/fallback_management_endpoints.py:195
↓ 12 callersFunctioncreate_group
Create a group according to SCIM v2 protocol
litellm/proxy/management_endpoints/scim/scim_v2.py:2978
↓ 12 callersMethodcreate_many
(self, data: Sequence[Mapping[str, object]])
litellm/proxy/management_endpoints/auto_router_endpoints.py:177
↓ 12 callersFunctioncreate_standard_logging_payload
()
tests/unit/enterprise/enterprise_callbacks/test_prometheus_logging_callbacks.py:55
↓ 12 callersMethodcreate_user
(self, *, max_budget: float, budget_duration: str | None = None)
tests/e2e/quota_management/budgets/budget_client.py:328
↓ 12 callersFunctioncustom
(request)
tests/unit/proxy/middleware/test_security_headers_middleware.py:65
↓ 12 callersFunctioncut_off
(endpoint: Endpoint)
tests/integration/providers/_gemini_long_decode_support.py:520
↓ 12 callersFunctiondebitable_model_access_groups
Groups to debit: the set attributed at auth time, narrowed to those the served model belongs to. The router may fall back to a model outside the
litellm/proxy/db/db_spend_update_writer.py:641
↓ 12 callersMethoddebugLog
(...e)
litellm/proxy/_experimental/out/_next/static/chunks/3lb5gjzjxjxem.js:1
↓ 12 callersMethoddebugLog
(...e)
litellm/proxy/_experimental/out/_next/static/chunks/1gr6rzkj48efi.js:1
↓ 12 callersMethoddebugLog
(...e)
litellm/proxy/_experimental/out/_next/static/chunks/3pt4j6dlwjpqo.js:1
↓ 12 callersMethoddebugLog
(...e)
litellm/proxy/_experimental/out/_next/static/chunks/3tb8tug0et-f3.js:1
↓ 12 callersFunctiondelete_cache_key_object
Evict one key object, best-effort, matching `delete_cache_team_object` and `delete_cache_key_objects`. Every caller runs this after its
litellm/proxy/auth/auth_checks.py:3463
↓ 12 callersMethoddelete_many
(self, where: Mapping[str, object])
litellm/proxy/management_endpoints/customer_endpoints.py:110
↓ 12 callersFunctiondelete_team_callback
Remove a single callback from a team The team's other callbacks stay registered and keep firing. Use this instead of POST /team/{team_id
litellm/proxy/management_endpoints/team_callback_endpoints.py:479
↓ 12 callersMethoddelete_user
(self, user_id: str)
tests/e2e/quota_management/budgets/budget_client.py:339
↓ 12 callersFunctiondeployment
(scenario: Scenario, row: Row, api_base: str | None)
tests/integration/providers/_api_base_trailing_slash_support.py:304
↓ 12 callersMethoddisconnect
(self)
litellm/proxy/utils.py:7056
↓ 12 callersMethoddrive
( self, plan: "Plan", request: Mapping[str, object], overrides: Mapping[str, o
litellm/router_rust/invoke/endpoints.py:102
↓ 12 callersMethoddropped
(self, kwargs: Mapping[str, object])
litellm/rust_bridge/public_call.py:93
↓ 12 callersFunctioneE
litellm/proxy/_experimental/out/_next/static/chunks/37cr8te-omsl0.js:1
↓ 12 callersFunctioned
({value:e})
litellm/proxy/_experimental/out/_next/static/chunks/2vp9d70y5g3fw.js:1
↓ 12 callersFunctioneffective_scan_only_tool_results_for_guardrail
(guardrail_to_apply: object)
litellm/llms/base_llm/guardrail_translation/utils.py:280
↓ 12 callersFunctionel
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 12 callersFunctionemit
(provider: TracerProvider, name: str = "chat gpt-4")
tests/unit/integrations/otel/test_otel_v2_destinations.py:124
↓ 12 callersFunctionenc_project
(p)
tests/unit/integrations/gitlab/test_gitlab_client.py:85
↓ 12 callersMethodenforce_member_can_assign_access_groups
Field-level opt-in gate: a non-admin team member may only set `access_group_ids` on a (team) key if their team has opted in by adding
litellm/proxy/management_helpers/team_member_permission_checks.py:142
↓ 12 callersMethodenqueue
(self, pipe: _RedisPipeline)
litellm/caching/redis_batch.py:92
↓ 12 callersFunctiones
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 12 callersFunctionet
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/0_6jqgnorqxl2.js:1
↓ 12 callersMethodexecute_raw
(self, query: LiteralString, *args: object)
litellm/proxy/telemetry/store.py:25
↓ 12 callersFunctionexercise
(first_replica, second_replica)
tests/integration/mcp/test_pagination.py:53
↓ 12 callersFunctionexit_code
(sources: Mapping[str, str])
tests/code_coverage_tests/check_workflow_job_name_collisions.py:501
↓ 12 callersMethodexported_generation
(self)
tests/unit/integrations/test_langfuse.py:148
↓ 12 callersFunctionexported_llm_span
(collector: Wire, response_id: str)
tests/integration/observability/_langfuse_otel_metadata_support.py:317
↓ 12 callersFunctionextract_tool_results
( structured_messages: Sequence[object] | None, )
litellm/proxy/guardrails/guardrail_hooks/ovalix/ovalix_extraction.py:353
↓ 12 callersFunctioney
(e,a,s,t)
litellm/proxy/_experimental/out/_next/static/chunks/2r8xiri7nad3g.js:1
↓ 12 callersFunctionf
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 12 callersFunctionf
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 12 callersFunctionfailed_with
(core: RouterCore, **request: object)
tests/unit/test_router/core/test_parity_regress5_errors.py:77
↓ 12 callersMethodfetch
(self, user_id: str, server_id: str)
litellm/proxy/mcp_server/outbound_credentials/oauth_token_store.py:179
↓ 12 callersMethodfield
(&self)
litellm-rust/crates/model-catalog/src/error.rs:221
↓ 12 callersFunctionfields
(body: str)
scripts/check_schema_compatibility.py:20
↓ 12 callersFunctionfields
(expected: &[(&str, &str)])
litellm-rust/crates/gateway-forward/tests/exchange.rs:371
↓ 12 callersMethodfillBefore
(e,t=!1,n=0)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 12 callersMethodfilter_analyze_results_by_score
Drop detections that fall below configured per-entity score thresholds or match an entity type in the deny list.
litellm/proxy/guardrails/guardrail_hooks/presidio.py:954
↓ 12 callersMethodfind_by_id
(self, team_id: str, id_field: str = "team_id")
litellm/repositories/team_repository.py:157
↓ 12 callersMethodfind_many
( self, *, where: Mapping[str, object] | None = None, include: Mapping[str, ob
litellm/proxy/auth/auth_checks.py:262
↓ 12 callersFunctionfirst_messages
(marker: str)
tests/integration/providers/_tool_search_support.py:240
↓ 12 callersFunctionfixture_proc
(name: str, exit_code: int = 0)
tests/unit/llms/pi/harness/test_transformation.py:242
↓ 12 callersMethodflush_post
Sends every post-call op declared so far and waits for the follow-ups spawned on them; the shutdown drain calls it too.
litellm-rust/crates/redis-store/src/request.rs:120
↓ 12 callersFunctionformatDate
(date: Date)
ui/litellm-dashboard/src/components/networking.tsx:2
↓ 12 callersMethodfrom_logging_entry
Build from one ``standard_logging_guardrail_information`` entry. Reads the canonical, provider-agnostic ``StandardLoggingGuardrailInformation
litellm/integrations/otel/model/payloads.py:296
↓ 12 callersFunctionget
()
ui/litellm-dashboard/tests/setupTests.ts:76
↓ 12 callersMethodget
( self, url: str, params: dict | None = None, headers: dict | None = None,
litellm/llms/custom_httpx/http_handler.py:839
↓ 12 callersMethodgetConfigs
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 12 callersFunctiongetUiPageUrl
(url: string, relativePath = false)
ui/litellm-dashboard/src/components/networking.tsx:237
↓ 12 callersMethodget_affinity_cache_key
(cls, model_group: str, user_key: str)
litellm/router_utils/pre_call_checks/deployment_affinity_check.py:264
↓ 12 callersMethodget_aggregated_daily_spend_update_transactions
Aggregate updates by daily_transaction_key.
litellm/proxy/db/db_transaction_queue/daily_spend_update_queue.py:112
↓ 12 callersMethodget_all_policies
Get all loaded policies. Returns: Dictionary mapping policy names to Policy objects
litellm/proxy/policy_engine/policy_registry.py:290
↓ 12 callersMethodget_app_roles_from_id_token
Extract app roles from the Microsoft Entra ID (Azure AD) id_token JWT. App roles are assigned in the Azure AD Enterprise Application
litellm/proxy/management_endpoints/ui_sso.py:4837
↓ 12 callersMethodget_aws_region_name_for_non_llm_api_calls
Get the AWS region name for non-llm api calls. LLM API calls check the model arn and end up using that as the region name.
litellm/llms/bedrock/base_aws_llm.py:821
↓ 12 callersFunctionget_azure_ai_agent_entra_token
Mints the Entra bearer from the agent's own litellm_params, never from process-wide AZURE_* env vars.
litellm/llms/azure_ai/common_utils.py:108
↓ 12 callersMethodget_base_model
Wrapper for standalone function. See get_bedrock_base_model().
litellm/llms/bedrock/common_utils.py:2043
↓ 12 callersFunctionget_cli_token_file_path
Get the path to the CLI token file
litellm/litellm_core_utils/cli_token_utils.py:150
↓ 12 callersMethodget_closest_marker
(self, name: str)
tests/unit/test_vcr_classification.py:58
↓ 12 callersMethodget_complete_batch_url
( self, api_base, api_key, model, optional_params, litellm_params, data )
tests/unit/llms/base_llm/batches/test_transformation.py:59
↓ 12 callersFunctionget_configured_request_timeout
Return the explicitly-configured ``litellm.request_timeout``, else ``None``.
litellm/litellm_core_utils/request_timeout_resolver.py:25
↓ 12 callersFunctionget_datadog_tags
Build Datadog tags as a list of individual tag strings. Returns a list of "key:value" strings suitable for Datadog LLM Observability (which e
litellm/integrations/datadog/datadog_handler.py:47
↓ 12 callersMethodget_extra_info
(self, info: str)
tests/integration/management/test_credential_federation_values.py:57
↓ 12 callersFunctionget_last_user_message
Get the last consecutive block of messages from the user. Example: messages = [ {"role": "user", "content": "Hello, how are you?
litellm/litellm_core_utils/prompt_templates/common_utils.py:1206
↓ 12 callersFunctionget_marketplace
Serve marketplace.json for Claude Code plugin discovery. This endpoint is accessed by Claude Code CLI when users run: - claude plugin ma
litellm/proxy/anthropic_endpoints/claude_code_endpoints/claude_code_marketplace.py:346
↓ 12 callersMethodget_mcp_servers_from_access_groups
Resolve MCP access groups against the operation snapshot, or database and config outside an operation. ``requires_fresh_policy`` read
litellm/proxy/mcp_server/auth/user_api_key_auth_mcp.py:4743
↓ 12 callersFunctionget_model_cost_map_source_info
Return metadata about where the current model cost map was loaded from. Returns a dict with: - source: "local" or "remote" - url: th
litellm/litellm_core_utils/get_model_cost_map.py:531
← previousnext →5,501–5,600 of 202,479, ranked by callers