MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions86,368 in github.com/BerriAI/litellm

↓ 10,771 callersMethodget
(path: string, options?: RequestOptions)
ui/litellm-dashboard/src/lib/http/client.ts:111
↓ 4,584 callersFunctionpatch
( url: URL, *, headers: BaseModel, json: BaseModel, response_type: type[R], timeout: f
tests/e2e/e2e_http.py:380
↓ 2,740 callersMethodappend
(s,o)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 2,339 callersMethodmap
(s,o)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 1,872 callersMethoddebug
(s,...o)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 1,377 callersMethodpost
(path: string, options?: RequestOptions)
ui/litellm-dashboard/src/lib/http/client.ts:112
↓ 1,286 callersMethodnow
(self)
tests/test_litellm/proxy/hooks/test_dynamic_rate_limiter_v3.py:30
↓ 1,194 callersMethodpop
(self, session_id: str, default: None, /)
litellm/proxy/_experimental/mcp_server/server.py:558
↓ 1,186 callersMethoditems
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 1,084 callersMethodsplit
(self, _sep)
tests/test_litellm/llms/bedrock/batches/test_handler.py:76
↓ 1,008 callersMethodjson
(self, **kwargs)
litellm/types/utils.py:1339
↓ 952 callersMethodreplace
(self, *args, **kwargs)
tests/test_litellm/litellm_core_utils/test_safe_json_dumps.py:188
↓ 908 callersMethodsleep
(self, seconds: float)
tests/test_litellm/proxy/utils/prisma_and_spend/conftest.py:267
↓ 905 callersMethodfail
(e,t,n)
litellm/proxy/_experimental/out/_next/static/chunks/3ytz29phknzsy.js:1
↓ 890 callersMethodisArray
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 880 callersMethodpush
({key:e,query:r,options:s},i=n.timeMs)
litellm/proxy/_experimental/out/_next/static/chunks/20mvgyvrlrdla.js:2
↓ 879 callersMethodincludes
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 876 callersMethodfilter
(s,o)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 863 callersFunctionset
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 757 callersMethodslice
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/3ytz29phknzsy.js:1
↓ 733 callersMethodassign
(carried: tuple[int, int], length: int)
litellm/proxy/guardrails/guardrail_hooks/bedrock_guardrails.py:1274
↓ 692 callersMethodencode
(self, token: OAuthToken)
litellm/proxy/_experimental/mcp_server/outbound_credentials/token_cache_codec.py:28
↓ 658 callersMethodstringify
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/3ytz29phknzsy.js:1
↓ 650 callersMethodtime
(self)
tests/test_litellm/proxy/utils/prisma_and_spend/conftest.py:264
↓ 645 callersMethoddecode
(e)
litellm/proxy/_experimental/out/_next/static/chunks/42gio3rky08u5.js:4
↓ 599 callersMethodjson
(self)
tests/test_litellm/proxy/fine_tuning_endpoints/test_endpoints.py:78
↓ 588 callersFunctionit
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/3t4iumhktznmc.js:24
↓ 588 callersFunctionlist
List vector stores. Args: after: A cursor for use in pagination. before: A cursor for use in pagination. limit: A li
litellm/vector_stores/main.py:657
↓ 538 callersMethodforEach
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/1jfookxfajkeo.js:1
↓ 536 callersMethodentries
()
litellm/proxy/_experimental/out/_next/static/chunks/2fckmmo55b3as.js:1
↓ 511 callersMethoddelete
(path: string, options?: RequestOptions)
ui/litellm-dashboard/src/lib/http/client.ts:114
↓ 498 callersMethodkeys
()
litellm/proxy/_experimental/out/_next/static/chunks/1jfookxfajkeo.js:1
↓ 481 callersMethodapply_guardrail
(self, inputs, request_data, input_type, **kwargs)
tests/test_litellm/proxy/guardrails/guardrail_hooks/unified_guardrails/test_unified_guardrail.py:57
↓ 481 callersMethodupdate
Update an existing API key's parameters. Args: models: Optional[List[str]] = None, aliases: Optional[Dict[st
litellm/proxy/client/keys.py:229
↓ 476 callersMethodfrom
(e)
litellm/proxy/_experimental/out/_next/static/chunks/1jfookxfajkeo.js:1
↓ 438 callersFunctionfetch
(team_id: str)
tests/test_litellm/proxy/auth/test_route_checks.py:2719
↓ 418 callersMethodfilter
(self, record: logging.LogRecord)
litellm/_logging.py:51
↓ 417 callersMethodset
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 411 callersMethodpush
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 403 callersFunctionnext
(u)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 392 callersMethodkeys
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 389 callersMethodconcat
(...e)
litellm/proxy/_experimental/out/_next/static/chunks/28hnu_qv5e_c_.js:1
↓ 387 callersMethoditems
(self)
tests/test_litellm/passthrough/test_passthrough_main.py:219
↓ 380 callersMethoddict
(self)
tests/test_litellm/repositories/test_repositories.py:39
↓ 376 callersFunctionget_secret_str
Guarantees response from 'get_secret' is either string or none. Used for fixing linting errors.
litellm/secret_managers/main.py:139
↓ 373 callersFunctionopen
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 372 callersMethodcopy
(self)
litellm/types/proxy/litellm_pre_call_utils.py:13
↓ 355 callersMethodset
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2fckmmo55b3as.js:1
↓ 354 callersFunctione
(e)
litellm/proxy/_experimental/out/_next/static/chunks/0kzod24rqslaj.js:1
↓ 353 callersMethodhas
(e)
litellm/proxy/_experimental/out/_next/static/chunks/1jfookxfajkeo.js:1
↓ 347 callersMethodcompletion
( self, model: str, messages: list, api_base: str, custom_prompt_dict:
tests/local_testing/test_custom_llm.py:115
↓ 340 callersMethodrun
(self, context)
tests/test_litellm/proxy/proxy_server/test_proxy_config.py:217
↓ 340 callersMethodtoString
()
litellm/proxy/_experimental/out/_next/static/chunks/1jfookxfajkeo.js:1
↓ 336 callersMethodapply
Apply metadata to the response object
litellm/litellm_core_utils/llm_response_utils/response_metadata.py:160
↓ 328 callersFunctioncompletion
Perform a completion() using any of litellm supported llms (example gpt-4, gpt-3.5-turbo, claude-2, command-nightly) Parameters: mode
litellm/main.py:4839
↓ 324 callersMethodpatch
(path: string, options?: RequestOptions)
ui/litellm-dashboard/src/lib/http/client.ts:115
↓ 320 callersMethodsort
()
litellm/proxy/_experimental/out/_next/static/chunks/3nc6x0_y5iwnk.js:1
↓ 319 callersFunctionrender
(ready = true)
ui/litellm-dashboard/src/app/(dashboard)/hooks/useTabRouting.test.tsx:21
↓ 317 callersMethodfind
(e)
litellm/proxy/_experimental/out/_next/static/chunks/19frz_r2jewoi.js:1
↓ 293 callersFunctionget_async_httpx_client
Retrieves the async HTTP client from the cache If not present, creates a new client Caches the new client and returns it.
litellm/llms/custom_httpx/http_handler.py:1428
↓ 292 callersMethoduseState
(e,n,i,o)
litellm/proxy/_experimental/out/_next/static/chunks/2fckmmo55b3as.js:1
↓ 287 callersMethodadd
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2fckmmo55b3as.js:1
↓ 283 callersMethodforEach
(s,o)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 282 callersMethodjson
(self)
tests/image_gen_tests/test_image_edits.py:258
↓ 278 callersFunctionlist
List all API keys
litellm/proxy/client/cli/commands/keys.py:42
↓ 277 callersMethodfind
(s,o)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 272 callersMethodacompletion
( self, model: str, messages: list, api_base: str, custom_prompt_dict:
tests/local_testing/test_custom_llm.py:140
↓ 268 callersMethodreduce
(s,o)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 260 callersMethodadd
Append one model's outcome to the per-test results list. Use this when a single test exercises multiple Claude tiers concurrently and
tests/e2e/claude_code/conftest.py:96
↓ 260 callersMethodparse
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 259 callersFunctiont
()
litellm/proxy/_experimental/out/_next/static/chunks/0kzod24rqslaj.js:23
↓ 258 callersFunctionsetTimeout
(...e)
litellm/proxy/_experimental/out/_next/static/chunks/2649p504vhh-y.js:1
↓ 257 callersMethodresolve
( self, hashed_token: str, *, auth_method: AuthMethod = AuthMethod.API_KEY,
litellm/proxy/auth/resolvers/store.py:74
↓ 250 callersMethodkeys
(self)
tests/pass_through_unit_tests/test_pass_through_unit_tests.py:56
↓ 249 callersMethodi
litellm/proxy/_experimental/out/_next/static/chunks/2m0_88ia6ych8.js:1
↓ 248 callersMethodraise_for_status
Raise exception for error status codes.
litellm/integrations/mock_client_factory.py:79
↓ 246 callersMethodclear
(self)
tests/logging_callback_tests/test_amazing_s3_logs.py:37
↓ 246 callersMethoddict
(self)
tests/test_litellm/proxy/proxy_server/test_streaming_helpers.py:116
↓ 246 callersMethodthen
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/42gio3rky08u5.js:4
↓ 245 callersMethodmap_openai_params
(self, non_default_params, optional_params, model, drop_params)
tests/test_litellm/llms/custom_httpx/test_llm_http_handler.py:1742
↓ 244 callersFunctions
litellm/proxy/_experimental/out/_next/static/chunks/3t4iumhktznmc.js:1
↓ 243 callersMethoddirname
()
litellm/proxy/_experimental/out/_next/static/chunks/3ytz29phknzsy.js:1
↓ 243 callersMethods
litellm/proxy/_experimental/out/_next/static/chunks/2q3uods7pdkez.js:2
↓ 242 callersMethodbind
(e)
litellm/proxy/_experimental/out/_next/static/chunks/3z-oetkpttgun.js:1
↓ 239 callersMethodparse
(e,t,r)
litellm/proxy/_experimental/out/_next/static/chunks/2ghof0nt7xbjx.js:1
↓ 234 callersMethodinfo
Get information about API keys. Args: key (str): The key hash to get information about return_request (bool)
litellm/proxy/client/keys.py:289
↓ 227 callersFunctionunique_marker
A short unique token per call/run, so concurrent runs and the shared response cache never collide on prompts, tags, or customer ids.
tests/e2e/e2e_config.py:149
↓ 223 callersMethodmodel_validate
(self, obj: Mapping[str, object])
litellm/llms/volcengine/responses/transformation.py:45
↓ 221 callersMethodsetup
(self, mock_provider_mapping, mock_http_handler, mock_http_async_handler)
tests/llm_translation/test_huggingface_chat_completion.py:233
↓ 219 callersMethodextend
(self, key: str, token: str, ttl_seconds: float)
litellm/proxy/_experimental/mcp_server/outbound_credentials/redis_refresh_coordinator.py:55
↓ 217 callersMethodpre_call
(self, input, api_key, model=None, additional_args={})
litellm/litellm_core_utils/litellm_logging.py:918
↓ 216 callersMethodasync_pre_call_hook
(self, **kwargs)
tests/test_litellm/proxy/utils/proxy_logging/test_pre_call_hook.py:110
↓ 210 callersMethodselect
(e,t,n,r)
litellm/proxy/_experimental/out/_next/static/chunks/2fckmmo55b3as.js:1
↓ 209 callersFunctionhash_token
(token: str)
litellm/proxy/utils.py:5374
↓ 200 callersMethodtext
(self)
tests/e2e/a2a/a2a_client.py:254
↓ 197 callersMethodcatch
(e)
litellm/proxy/_experimental/out/_next/static/chunks/42gio3rky08u5.js:4
↓ 192 callersMethodcompile
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 186 callersMethodformat
(self, record)
litellm/_logging.py:159
↓ 185 callersMethodinfo
(self)
litellm/caching/redis_cache.py:1345
↓ 182 callersMethoddefer
Register a teardown action for any resource the test just created.
tests/e2e/lifecycle.py:63
next →1–100 of 86,368, ranked by callers