MCPcopy Create free account

hub / github.com/crewAIInc/crewAI / functions

Functions19,482 in github.com/crewAIInc/crewAI

↓ 10 callersFunctionactivate_skill
Promote a skill to INSTRUCTIONS disclosure level. Idempotent: returns the skill unchanged if already at or above INSTRUCTIONS. Args:
lib/crewai/src/crewai/skills/loader.py:120
↓ 10 callersFunctionadd_job
Register one validated queued record through the serialized state path.
lib/crewai/src/crewai/experimental/flow_jobs.py:97
↓ 10 callersFunctionbuild
(model: str, **kwargs)
lib/crewai/tests/llms/openai/test_responses_only_models.py:34
↓ 10 callersFunctionbuild_rich_field_description
Build a comprehensive field description including constraints. Embeds format, enum, pattern, min/max, and example constraints into the descri
lib/crewai/src/crewai/utilities/pydantic_schema_utils.py:724
↓ 10 callersFunctionbuild_tool
Build a tool whose every scrape entrypoint answers with ``raw_response``. ``sdk_logs`` reproduces the oxylabs SDK's habit of logging the real cau
lib/crewai-tools/tests/tools/test_oxylabs_tools.py:177
↓ 10 callersFunctionclear_all
Clear all global hooks across every interception point.
lib/crewai/src/crewai/hooks/dispatch.py:153
↓ 10 callersMethodcopy
Creates a deep copy of the Crew instance. Returns: Crew: A new instance with copied components
lib/crewai/src/crewai/crew.py:2233
↓ 10 callersMethodcreate_table
(self)
lib/crewai-tools/src/crewai_tools/tools/oracle_vector_search_tool/vector_search.py:693
↓ 10 callersFunctiondb_storage_path
Return the path for SQLite database / app-data storage. Creates the directory if it does not exist.
lib/crewai-core/src/crewai_core/paths.py:16
↓ 10 callersMethodfork
Fork a Crew from a checkpoint, creating a new execution branch. Args: config: Checkpoint configuration with ``restore_from`` set.
lib/crewai/src/crewai/crew.py:459
↓ 10 callersFunctionformat_message_for_llm
Create an LLM message with trailing whitespace removed.
lib/crewai/src/crewai/utilities/message_utils.py:29
↓ 10 callersFunctionfreeze
Freeze the current Edge into ``docs/v<version>/`` and update docs.json. Args: version: Release version as ``"X.Y.Z"`` (no leading ``v``).
lib/devtools/src/crewai_devtools/docs_versioning.py:100
↓ 10 callersMethodfrom_content
(content: str | Path | None = None)
lib/crewai-tools/src/crewai_tools/rag/data_types.py:103
↓ 10 callersMethodfrom_flow
Build an expression with the standard Flow runtime context.
lib/crewai/src/crewai/flow/expressions.py:235
↓ 10 callersMethodfrom_provider_dict
Normalize a provider's raw usage dict into a ``UsageMetrics``. Accepts the full set of key aliases CrewAI providers emit: ``prompt_to
lib/crewai/src/crewai/types/usage_metrics.py:143
↓ 10 callersFunctionget_after_llm_call_hooks
Get all registered global after_llm_call hooks. Returns: List of registered after hooks
lib/crewai/src/crewai/hooks/llm_hooks.py:304
↓ 10 callersMethodget_mcp_tools
Convert MCP server references/configs to CrewAI tools. Delegates to :class:`~crewai.mcp.tool_resolver.MCPToolResolver`.
lib/crewai/src/crewai/agent/core.py:1492
↓ 10 callersFunctionguardrail
(decision, expected="accept", **extra)
lib/crewai/tests/test_jev_evaluation_runner.py:123
↓ 10 callersMethodhandle_llm_stream_completed
Handle completion of LLM streaming - stop the streaming live display.
lib/crewai/src/crewai/events/utils/console_formatter.py:666
↓ 10 callersFunctionhandle_max_iterations_exceeded
Handles the case when the maximum number of iterations is exceeded. Performs one more LLM call to get the final answer. Args: printer: Pr
lib/crewai/src/crewai/utilities/agent_utils.py:387
↓ 10 callersFunctionis_tracing_enabled_in_context
Check if tracing is enabled in current execution context. Returns: True if tracing is enabled in context, False otherwise. Return
lib/crewai/src/crewai/events/listeners/tracing/utils.py:205
↓ 10 callersFunctionjson_crew_project
(folder: Path, llm: str = "openai/gpt-5.6-luna")
lib/cli/tests/test_api_keys.py:54
↓ 10 callersMethodkickoff
(self, inputs)
lib/cli/tests/test_run_crew.py:855
↓ 10 callersMethodkickoff
Execute the agent with the given messages. Args: messages: Either a string query or a list of message dictionaries.
lib/crewai/src/crewai/lite_agent.py:501
↓ 10 callersMethodkickoff_async
Execute the agent asynchronously with the given messages. This is the async version of the kickoff method that uses native async exec
lib/crewai/src/crewai/agent/core.py:2350
↓ 10 callersMethodkickoff_for_each
Executes the Crew's workflow for each input and aggregates results. Args: inputs: List of input dictionaries, one per execution.
lib/crewai/src/crewai/crew.py:1110
↓ 10 callersMethodload
(self, source_content: SourceContent, **kwargs: Any)
lib/crewai-tools/src/crewai_tools/rag/loaders/webpage_loader.py:16
↓ 10 callersMethodload
(self, source_content: SourceContent, **kwargs: Any)
lib/crewai-tools/src/crewai_tools/rag/loaders/docx_loader.py:11
↓ 10 callersFunctionload_notebook
Provide a loader for serialized notebook fixtures.
lib/crewai-tools/tests/rag/test_notebook_loader.py:31
↓ 10 callersFunctionmark_cache_breakpoint
Return ``message`` with the cache-breakpoint flag set. Returns a new dict so callers can safely pass literal dicts.
lib/crewai/src/crewai/llms/cache.py:27
↓ 10 callersMethodoff
Unregister an event handler for a specific event type. Args: event_type: The event class to stop listening for handle
lib/crewai/src/crewai/events/event_bus.py:368
↓ 10 callersMethodpath_exists
(self)
lib/crewai-tools/src/crewai_tools/rag/source_content.py:29
↓ 10 callersFunctionread_toml
Read a TOML file from disk and return its parsed contents.
lib/crewai-core/src/crewai_core/project.py:38
↓ 10 callersFunctionrecord_stop
Count an evaluation that was asked for and did not reach a verdict, and why. `cli_usage:eval` counts the evaluations that started; this is the ot
lib/cli/src/crewai_cli/experimental/eval_crew.py:196
↓ 10 callersFunctionrender_text_description_and_args
Render the tool name, description, and args in plain text. search: This tool is used for search, args: {"query": {"type": "string"}} calculat
lib/crewai/src/crewai/utilities/agent_utils.py:222
↓ 10 callersMethodrequest
( self, method: str | bytes, url: str | bytes, *args: Any, **kwargs: Any )
lib/crewai-tools/src/crewai_tools/security/safe_requests.py:76
↓ 10 callersFunctionrequire
Import a module, optionally returning a specific attribute. Args: name: The module name to import. purpose: Description of what r
lib/crewai/src/crewai/utilities/import_utils.py:21
↓ 10 callersMethodreset_memories
Reset specific or all memories for the crew. Args: command_type: Type of memory to reset. Valid options: 'memory'
lib/crewai/src/crewai/crew.py:2410
↓ 10 callersMethodsave_state
Save the current flow state to SQLite. Args: flow_uuid: Unique identifier for the flow instance method_name: Name of
lib/crewai/src/crewai/flow/persistence/sqlite.py:193
↓ 10 callersMethodset_files
Set available input files. Args: files: Dictionary mapping file names to file inputs.
lib/crewai/src/crewai/tools/agent_tools/read_file_tool.py:39
↓ 10 callersMethodset_tracer
Mark telemetry live (idempotent). Deliberately does not install a global TracerProvider. Doing so made every OTel-instrumented librar
lib/crewai/src/crewai/telemetry/telemetry.py:141
↓ 10 callersMethodshutdown
Drain execution events, export, and remove only this session's handlers.
lib/crewai/src/crewai/telemetry/tracing/session.py:255
↓ 10 callersMethodstatus
Get the git status in porcelain format.
lib/cli/src/crewai_cli/git.py:84
↓ 10 callersMethodto_pydantic
Generate structured output using the specified Pydantic model. Returns: Instance of the specified Pydantic model with structured
lib/crewai/src/crewai/utilities/internal_instructor.py:139
↓ 10 callersFunctionupdate_pyproject_dependencies
Update workspace dependency versions in pyproject.toml. Args: file_path: Path to pyproject.toml file. new_version: New version st
lib/devtools/src/crewai_devtools/cli.py:344
↓ 9 callersFunction_a_tracing_project
(directory: Path)
lib/cli/tests/experimental/test_eval_crew.py:4145
↓ 9 callersMethod_acall_completions
Async call to OpenAI Chat Completions API. Falls back to the Responses API for models not served by chat completions, mirroring :meth
lib/crewai/src/crewai/llms/providers/openai/completion.py:872
↓ 9 callersMethod_api_response
(status_code: int, body: object)
lib/cli/tests/deploy/test_deploy_main.py:1155
↓ 9 callersMethod_asave_documents
Save the documents to the storage asynchronously. This method should be called after the chunks and embeddings are generated. Raises
lib/crewai/src/crewai/knowledge/source/base_knowledge_source.py:67
↓ 9 callersFunction_at_a_terminal
Run `crewai create flow` as a person at a terminal: stdin and stdout are terminals and CREWAI_DMN is unset. Call it in the test body: pytest gives
lib/cli/tests/test_create_flow.py:127
↓ 9 callersFunction_build_docs_root
Build a minimal docs/ tree with one previous snapshot + Edge + docs.json. The shape mirrors the real repo: an Edge directory with per-locale fold
lib/devtools/tests/test_docs_versioning.py:16
↓ 9 callersFunction_close_storage
Flush and release a backend; a no-op for backends without ``close``.
lib/crewai/tests/memory/test_storage_backend_async_parity.py:61
↓ 9 callersFunction_completion_body
(content: str)
lib/crewai/tests/llms/openai/test_gateway_error_envelope.py:44
↓ 9 callersFunction_create_skill_dir
Helper to create a skill directory with SKILL.md.
lib/crewai/tests/skills/test_loader.py:20
↓ 9 callersFunction_dict_tool_use_response
()
lib/crewai/tests/llms/anthropic/test_anthropic.py:1607
↓ 9 callersFunction_emit
Run one telemetry span method against a mocked tracer. The singleton is reset first: it caches the provider built on the very first construct
lib/crewai/tests/telemetry/test_telemetry.py:331
↓ 9 callersFunction_ensure_litellm
Lazy-load litellm on first use. Returns True if available.
lib/crewai/src/crewai/llm.py:138
↓ 9 callersMethod_extract_anthropic_token_usage
Extract token usage and response metadata from Anthropic response.
lib/crewai/src/crewai/llms/providers/anthropic/completion.py:2125
↓ 9 callersMethod_format_messages
Format messages for OpenAI API.
lib/crewai/src/crewai/llms/providers/openai/completion.py:3226
↓ 9 callersMethod_format_messages_for_converse
Format messages for Converse API following AWS documentation. Note: Returns dict[str, Any] instead of LLMMessage because Bedrock uses
lib/crewai/src/crewai/llms/providers/bedrock/completion.py:1919
↓ 9 callersMethod_format_messages_for_gemini
Format messages for Gemini API. Gemini has specific requirements: - System messages are separate system_instruction - Content
lib/crewai/src/crewai/llms/providers/gemini/completion.py:638
↓ 9 callersMethod_get_or_create_interpreter
Get or create a code interpreter for the specified thread. Args: thread_id: Thread ID for the code interpreter session R
lib/crewai-tools/src/crewai_tools/aws/bedrock/code_interpreter/code_interpreter_toolkit.py:520
↓ 9 callersFunction_instant_span
Emit a zero-duration span for an event that has no start/end pair. Studio's trace tree is built from spans alone -- ``Wharf::SpansFetchService``
lib/crewai/src/crewai/telemetry/tracing/handlers.py:1332
↓ 9 callersFunction_load_user_data
Read the user-data JSON file, returning ``{}`` on missing/corrupt.
lib/crewai-core/src/crewai_core/user_data.py:34
↓ 9 callersFunction_open_storage
Open a backend of kind ``backend`` rooted at ``path``.
lib/crewai/tests/memory/test_storage_backend_async_parity.py:49
↓ 9 callersFunction_pause
Persist a pending review for ``flow_cls.draft`` and restore it, as AMP does.
lib/crewai/tests/test_async_human_feedback.py:1472
↓ 9 callersFunction_prepare_documents_for_chromadb
Prepare documents for ChromaDB by extracting IDs, texts, and metadata. Args: documents: List of BaseRecord documents to prepare. Ret
lib/crewai/src/crewai/rag/chromadb/utils.py:56
↓ 9 callersFunction_python_ref_errors
(value: Any, source: str | Path)
lib/crewai/src/crewai/project/json_loader.py:665
↓ 9 callersFunction_quote_identifier
(name: str)
lib/crewai-tools/src/crewai_tools/tools/oracle_vector_search_tool/vector_search.py:109
↓ 9 callersMethod_rejects_reasoning_effort_as_unsupported
Whether a 400 is the server refusing `reasoning_effort` for this model. Non-reasoning models reject the parameter itself, in one of two shape
lib/crewai/src/crewai/llms/providers/openai/completion.py:2176
↓ 9 callersMethod_run_sync
Run an async coroutine from sync context without blocking event loop.
lib/crewai-files/src/crewai_files/cache/upload_cache.py:403
↓ 9 callersMethod_scope_path
(self, scope: str | None)
lib/crewai/src/crewai/memory/memory_scope.py:93
↓ 9 callersMethod_set_plan_step_status
Set status for an explicit plan step reported by the planner.
lib/cli/src/crewai_cli/crew_run_tui.py:2482
↓ 9 callersFunction_tar_from_members
Build an in-memory tar archive via `build(tf)` and return it for reading.
lib/cli/tests/skills/test_safe_extract.py:19
↓ 9 callersMethod_zip_create
A repository mock, and AMP accepting a ZIP create.
lib/cli/tests/deploy/test_deploy_main.py:1552
↓ 9 callersMethodaction_evaluate_crew
Grade the run that just finished, here. Unlike Deploy, this does not leave: the evaluation takes a few minutes, it has a link worth s
lib/cli/src/crewai_cli/crew_run_tui.py:1482
↓ 9 callersMethodaemit
Asynchronously emit an event to registered async handlers. Only processes async handlers. Use in async contexts. Args: s
lib/crewai/src/crewai/events/event_bus.py:771
↓ 9 callersMethodasearch
(self, query, limit=5, metadata_filter=None, score_threshold=0.6)
lib/crewai/tests/agents/test_agent.py:1887
↓ 9 callersFunctionbuild_xlsx
Return the bytes of a single-sheet XLSX holding *rows*.
lib/crewai-tools/tests/url_read_tool_test.py:79
↓ 9 callersMethodcheckpoint
Write a checkpoint. Args: location: Storage destination. For JsonProvider this is a directory path; for SqlitePro
lib/crewai/src/crewai/state/runtime.py:292
↓ 9 callersMethodcheckpoint
(self)
lib/crewai/tests/test_flow_definition.py:992
↓ 9 callersMethodclient
(self, service_name: str, **kwargs: Any)
lib/crewai-files/tests/test_bedrock_async_client.py:49
↓ 9 callersMethodclose
Clean up Stagehand resources.
lib/crewai-tools/src/crewai_tools/tools/stagehand_tool/stagehand_tool.py:681
↓ 9 callersMethodclose
(self)
lib/crewai/tests/test_jev_evaluation_runner.py:476
↓ 9 callersFunctionconfigured_project_declarative_flow
Return the configured declarative flow source for flow projects.
lib/cli/src/crewai_cli/run_declarative_flow.py:556
↓ 9 callersMethoddelete_collection
Delete a collection and all its data. Keyword Args: collection_name: Name of the collection to delete. Raises:
lib/crewai/src/crewai/rag/qdrant/client.py:507
↓ 9 callersFunctionevaluate
Classify every record and compute routing and guardrail metrics. Both thresholds are inclusive: a Choice confidence equal to ``min_confidence
scripts/jev_evaluation_runner.py:269
↓ 9 callersFunctionextract_output_from_stream
Extract output from code interpreter response stream. Args: response: Response from code interpreter execution Returns: Extr
lib/crewai-tools/src/crewai_tools/aws/bedrock/code_interpreter/code_interpreter_toolkit.py:19
↓ 9 callersMethodfinalize_batch
Finalize batch and return it for sending
lib/crewai/src/crewai/events/listeners/tracing/trace_batch_manager.py:327
↓ 9 callersFunctionget_after_tool_call_hooks
Get all registered global after_tool_call hooks. Returns: List of registered after hooks
lib/crewai/src/crewai/hooks/tool_hooks.py:287
↓ 9 callersFunctionget_auth_token
Return the saved authentication token; raise ``AuthError`` if missing.
lib/crewai-core/src/crewai_core/auth/token.py:12
↓ 9 callersMethodget_tracer
(self, name: str | None = None)
lib/crewai/src/crewai/telemetry/tracing/session.py:177
↓ 9 callersMethodincrement_tools_errors
Increment the tools errors counter.
lib/crewai/src/crewai/task.py:1226
↓ 9 callersMethodinitialize_batch
Initialize a new trace batch (thread-safe)
lib/crewai/src/crewai/events/listeners/tracing/trace_batch_manager.py:91
↓ 9 callersMethodinstall
(self, handle: str)
lib/cli/src/crewai_cli/tools/main.py:208
↓ 9 callersFunctionis_current_version_yanked
Return ``(yanked, reason)`` for the currently installed version.
lib/crewai-core/src/crewai_core/version.py:149
↓ 9 callersFunctionis_dmn_mode_enabled
Return True when the enterprise non-interactive mode is enabled.
lib/cli/src/crewai_cli/utils.py:100
↓ 9 callersFunctionis_replaying
Return True if the current context is dispatching a replayed event. Listeners with side effects (checkpoint writes, external API calls that s
lib/crewai/src/crewai/events/event_bus.py:73
↓ 9 callersFunctionis_tool_call_list
Check if a response from the LLM is a list of tool calls. Supports OpenAI, Anthropic, Bedrock, and Gemini formats. Args: response: T
lib/crewai/src/crewai/utilities/agent_utils.py:1339
↓ 9 callersMethodis_url
(self)
lib/crewai-tools/src/crewai_tools/rag/source_content.py:20
← previousnext →501–600 of 19,482, ranked by callers