MCPcopy Create free account

hub / github.com/crewAIInc/crewAI / functions

Functions19,663 in github.com/crewAIInc/crewAI

↓ 2 callersFunctionbuild_schema_hint
Build a human-readable hint from a Pydantic model's JSON schema. Args: args_schema: The Pydantic model class to extract schema from.
lib/crewai/src/crewai/tools/structured_tool.py:100
↓ 2 callersFunctionbuild_step_executor
(llm: StubProviderLLM)
lib/crewai/tests/hooks/test_deny_reaches_the_caller.py:247
↓ 2 callersFunctionbuild_task_prompt_with_schema
Build task prompt with JSON/Pydantic schema instructions if applicable. Args: task: The task being executed. task_prompt: The ini
lib/crewai/src/crewai/agent/utils.py:62
↓ 2 callersFunctionbuild_text_tool_calling_fallback_message
Build instructions for downgrading native tools to text tool calls.
lib/crewai/src/crewai/utilities/agent_utils.py:1406
↓ 2 callersFunctionbuildable_json_crew
A JSON crew crewAI builds for real, its one agent on LLM.
lib/cli/tests/test_run_usage.py:1287
↓ 2 callersFunctionbuilding_mapped_model
Build the model the overlay mapped to, without mapping it again.
lib/crewai/src/crewai/llm_overlay.py:273
↓ 2 callersFunctioncache_func
(args, result)
lib/crewai/tests/test_crew.py:2209
↓ 2 callersMethodcalculateNetworkPosition
(isDrawerOpen, centerScreen = false)
lib/crewai/src/crewai/flow/visualization/assets/interactive.js:2338
↓ 2 callersMethodcall
(self, messages, tools=None, callbacks=None, available_functions=None, **kw)
lib/crewai/tests/tools/test_tool_failure.py:61
↓ 2 callersMethodcall_tool
Call a tool on the MCP server. Args: tool_name: Name of the tool to call. arguments: Tool arguments. Returns
lib/crewai/src/crewai/mcp/client.py:453
↓ 2 callersFunctioncallback
Marks a method as a crew callback. Args: meth: The method to mark. Returns: A wrapped method marked as a callback with memoi
lib/crewai/src/crewai/project/annotations.py:138
↓ 2 callersFunctioncatalog_context_window
Return the full catalog window for a model id, or ``None`` if unlisted. Exact IDs are resolved in ``sizes``. A miss falls back to ``BARE_CONT
lib/crewai/src/crewai/llms/context_window.py:241
↓ 2 callersFunctioncheck_conditional_skip
Check if a conditional task should be skipped. Args: crew: The crew instance. task: The conditional task to check. task_o
lib/crewai/src/crewai/crews/utils.py:180
↓ 2 callersFunctioncheck_gh_installed
Check if GitHub CLI is installed and offer to install it. Raises: SystemExit: If gh is not installed and user declines installation.
lib/devtools/src/crewai_devtools/cli.py:92
↓ 2 callersFunctioncheck_git_clean
Check if git working directory is clean. Raises: SystemExit: If there are uncommitted changes.
lib/devtools/src/crewai_devtools/cli.py:149
↓ 2 callersFunctioncheck_native_tool_support
Check if the LLM supports native function calling and tools are available. Args: llm: The LLM instance. original_tools: Original
lib/crewai/src/crewai/utilities/agent_utils.py:1382
↓ 2 callersMethodcheck_open
Call at stage boundaries; this cannot abort an arbitrary provider call.
lib/crewai/src/crewai/experimental/flow_jobs.py:201
↓ 2 callersFunctionclassic_create
Run `crewai create crew my_crew --classic` in ``tmp_path`` with ``tmp_path`` as home, so the LiteLLM cache starts cold.
lib/cli/tests/test_create_crew.py:2517
↓ 2 callersMethodclassify
(error: BaseException, tmp_path: Path)
lib/crewai/tests/llms/test_missing_api_key.py:522
↓ 2 callersMethodclear
Clear the training data by removing the file or resetting its contents.
lib/crewai/src/crewai/utilities/training_handler.py:33
↓ 2 callersFunctionclear_all_tool_call_hooks
Clear all registered global tool call hooks (both before and after). Returns: Tuple of (before_hooks_cleared, after_hooks_cleared) E
lib/crewai/src/crewai/hooks/tool_hooks.py:384
↓ 2 callersMethodclear_expired
Sync wrapper for aclear_expired.
lib/crewai-files/src/crewai_files/cache/upload_cache.py:471
↓ 2 callersMethodclear_pending_feedback
Clear the pending feedback marker after successful resume. Args: flow_uuid: Unique identifier for the flow instance
lib/crewai/src/crewai/flow/persistence/sqlite.py:368
↓ 2 callersFunctionclient_for_selector
Select the integrations client for an application selector.
lib/crewai-tools/src/crewai_tools/tools/crewai_platform_tools/integrations_client.py:363
↓ 2 callersMethodclose
(self)
lib/crewai-tools/tests/utilities/test_safe_requests.py:491
↓ 2 callersMethodclose
Fence pending/active delivery; retained job results are untouched.
lib/crewai/src/crewai/experimental/flow_replies.py:428
↓ 2 callersMethodcompare_with_baseline
( self, baseline_filepath: str, save_current: bool = True, print_summary: bool
lib/crewai/src/crewai/experimental/evaluation/experiment/result.py:48
↓ 2 callersMethodconfigure_tools
(self, tools: List[BaseTool])
lib/crewai/tests/agents/agent_adapters/test_base_tool_adapter.py:11
↓ 2 callersMethodconnect
Establish SSE connection to MCP server. Returns: Self for method chaining. Raises: ConnectionError: If conne
lib/crewai/src/crewai/mcp/transports/sse.py:50
↓ 2 callersFunctioncopy_assistant_imports
Copy assistant instruction files that import ``AGENTS.md``.
lib/cli/src/crewai_cli/utils.py:124
↓ 2 callersMethodcount
Count records in scope (and subscopes).
lib/crewai/src/crewai/memory/storage/qdrant_edge_storage.py:696
↓ 2 callersMethodcount_tokens
( *, betas: list[str] | None = None, output_format: dict[str,
lib/crewai/src/crewai/llms/providers/anthropic/completion.py:386
↓ 2 callersMethodcreate_agent_executor
(self, tools=None)
lib/crewai/tests/agents/agent_builder/test_base_agent.py:19
↓ 2 callersFunctioncreate_client
Create a ChromaDBClient from configuration. Args: config: ChromaDB configuration object. Returns: Configured ChromaDBClient
lib/crewai/src/crewai/rag/chromadb/factory.py:12
↓ 2 callersMethodcreate_crew
(self, payload: CreateCrewPayload)
lib/crewai-core/src/crewai_core/plus_api.py:525
↓ 2 callersMethodcreate_crew_from_zip
Create a crew deployment from a local project ZIP archive. PROJECT_ID is `[tool.crewai].project_id`, so AMP knows which project the d
lib/crewai-core/src/crewai_core/plus_api.py:528
↓ 2 callersFunctioncreate_default_evaluator
( agents: list[Agent] | list[BaseAgent], llm: None = None )
lib/crewai/src/crewai/experimental/evaluation/agent_evaluator.py:344
↓ 2 callersMethodcreate_evaluation
(self, execution_id, *, eval_config=None, project_id=None)
lib/cli/tests/test_crew_run_tui.py:3073
↓ 2 callersFunctioncreate_extension_registry_from_config
Create an extension registry from A2A client configuration. Extracts client_extensions from each A2AClientConfig and registers them with the
lib/crewai/src/crewai/a2a/extensions/registry.py:123
↓ 2 callersFunctioncreate_file
(path, content)
lib/cli/tests/test_utils.py:27
↓ 2 callersMethodcreate_initial_commit_if_needed
Create a local initial commit when the repository has no commits.
lib/cli/src/crewai_cli/git.py:163
↓ 2 callersFunctioncreate_llm_from_kwargs_like
Build ``model`` configured like ``LLM(declared_model, **kwargs)`` would be. What ``llm_overlay``'s model keys build when ``LLM(model=...)`` is ca
lib/crewai/src/crewai/utilities/llm_utils.py:265
↓ 2 callersMethodcreate_models_evaluation
(self, models, *, project_id, eval_config=None, deployment_id=None)
lib/cli/tests/experimental/test_eval_crew.py:1701
↓ 2 callersFunctioncreate_nested
(depth)
lib/crewai/tests/utilities/test_serialization.py:152
↓ 2 callersFunctioncreate_static_tool_filter
Create a static tool filter function. This is a convenience function for creating static tool filters with allow/block lists. Args:
lib/crewai/src/crewai/mcp/filters.py:91
↓ 2 callersMethodcrew
(self)
lib/crewai/tests/test_crew.py:4826
↓ 2 callersFunctioncut_connections_at
Shut down every connection opened inside the block once *deadline* (a :func:`time.monotonic` value) passes; the event yielded is set if it did.
lib/crewai-tools/src/crewai_tools/security/ssrf_adapter.py:150
↓ 2 callersFunctiondeclarative_flow_project
(folder: Path)
lib/cli/tests/test_run_usage.py:184
↓ 2 callersFunctiondefault_embedding_function
Return the default embedder: OpenAI's text-embedding-3-small. This is the model Knowledge and the RAG tools used with Chroma. It is set expli
lib/crewai/src/crewai/rag/config/utils.py:61
↓ 2 callersMethoddelete_all
Delete all task output records from the database. This method removes all records from the latest_kickoff_task_outputs table. Use wit
lib/crewai/src/crewai/memory/storage/kickoff_task_outputs_storage.py:217
↓ 2 callersMethoddelete_object
(self, Bucket: str, Key: str)
lib/crewai-files/tests/test_bedrock_async_client.py:27
↓ 2 callersFunctiondetect_provider
Detect the storage provider from a checkpoint path. Reads the file's magic bytes to determine if it's a SQLite database. For paths containing
lib/crewai/src/crewai/state/provider/utils.py:11
↓ 2 callersFunctiondrawRoundedRect
(ctx, x, y, width, height, radius)
lib/crewai/src/crewai/flow/visualization/assets/interactive.js:49
↓ 2 callersFunctionecho_missing_keys
Print the ``.env`` lines to add before ``crewai run``, one per missing key.
lib/cli/src/crewai_cli/utils.py:305
↓ 2 callersMethodembed
(self, texts: list[str])
lib/crewai/tests/knowledge/test_knowledge_storage_providers.py:169
↓ 2 callersFunctionembed_text
Embed a single text string and return a list of floats. Args: embedder: Callable that accepts a list of strings and returns embeddings.
lib/crewai/src/crewai/memory/types.py:289
↓ 2 callersMethodemit_evaluation_started_event
( self, agent_role: str, agent_id: str, task_id: str | None = None )
lib/crewai/src/crewai/experimental/evaluation/agent_evaluator.py:296
↓ 2 callersMethodend_event_processing
Mark that an event handler finished processing (for synchronization).
lib/crewai/src/crewai/events/listeners/tracing/trace_batch_manager.py:254
↓ 2 callersMethodensure_force_final_answer
Force agent to provide final answer when max iterations exceeded.
lib/crewai/src/crewai/agents/agent_executor.py:1619
↓ 2 callersMethodensure_task_name
Ensure task result has a name set. Args: result: The task result to check. Returns: The task result with nam
lib/crewai/src/crewai/project/wrappers.py:284
↓ 2 callersMethodevaluate
( self, agent: Agent | BaseAgent, execution_trace: dict[str, Any], final_outpu
lib/crewai/src/crewai/experimental/evaluation/agent_evaluator.py:248
↓ 2 callersMethodevaluate
( self, agent: Agent | BaseAgent, execution_trace: dict[str, Any], final_outpu
lib/crewai/src/crewai/experimental/evaluation/metrics/tools_metrics.py:154
↓ 2 callersMethodevaluate
( self, agent: Agent | BaseAgent, execution_trace: dict[str, Any], final_outpu
lib/crewai/src/crewai/experimental/evaluation/metrics/goal_metrics.py:25
↓ 2 callersFunctionevaluation_marker
The app's word about the run this command just watched, if it left one. AFTER is when the run was started, and the marker must be newer: a projec
lib/cli/src/crewai_cli/experimental/eval_crew.py:613
↓ 2 callersMethodexecute
Execute a single todo item using a multi-turn action loop. Enforces the RPM limit, builds a fresh message list, then iterates LLM cal
lib/crewai/src/crewai/agents/step_executor.py:132
↓ 2 callersMethodexecute
(self, sql: str, *args: object)
lib/crewai/tests/storage/test_kickoff_task_outputs_storage.py:78
↓ 2 callersMethodexecute
(self, *args: Any, **kwargs: Any)
lib/crewai/tests/hooks/test_deny_reaches_the_caller.py:112
↓ 2 callersMethodexecute_todos_parallel
Execute multiple independent todos concurrently via StepExecutor. Uses the same StepExecutor path as sequential execution so that par
lib/crewai/src/crewai/agents/agent_executor.py:1448
↓ 2 callersMethodexecute_tool_action
Execute the tool action and handle the result.
lib/crewai/src/crewai/agents/agent_executor.py:1920
↓ 2 callersMethodexport
(self, spans: Sequence[ReadableSpan])
lib/crewai/src/crewai/telemetry/tracing/ephemeral.py:92
↓ 2 callersMethodexport_evaluation
The evaluation's full data as files (crewai eval export): `{"id", "kind", "files": {relative path: text}}`. TIMEOUT replaces the defau
lib/cli/src/crewai_cli/plus_api.py:119
↓ 2 callersFunctionextract_a2ui_json_objects
Extract JSON objects containing A2UI keys from text. Uses ``json.JSONDecoder.raw_decode`` for robust parsing that correctly handles braces in
lib/crewai/src/crewai/a2a/extensions/a2ui/models.py:257
↓ 2 callersFunctionextract_a2ui_v09_json_objects
Extract JSON objects containing A2UI v0.9 keys from text. Uses ``json.JSONDecoder.raw_decode`` for robust parsing that correctly handles brac
lib/crewai/src/crewai/a2a/extensions/a2ui/v0_9.py:811
↓ 2 callersMethodextract_id
Extract the checkpoint ID from a ``db_path#id`` string.
lib/crewai/src/crewai/state/provider/sqlite_provider.py:123
↓ 2 callersMethodextract_memories
Extract discrete memories from content; delegates to underlying Memory.
lib/crewai/src/crewai/memory/memory_scope.py:172
↓ 2 callersFunctionextract_memories_from_content
Use the LLM to extract discrete memory statements from raw content. This is a pure helper: it does NOT store anything. Callers should call me
lib/crewai/src/crewai/memory/analyze.py:155
↓ 2 callersMethodextract_model
(self, spec: ModelSpec)
lib/crewai/src/crewai/flow/skill.py:352
↓ 2 callersFunctionextract_task_section
Extract the ## Task body from a structured enriched instruction. For structured descriptions (e.g. with ## Task and ## Instructions sections),
lib/crewai/src/crewai/utilities/agent_utils.py:318
↓ 2 callersFunctionextract_tool_info
Extract tool information from various schema formats. Handles both OpenAI/standard format and direct format: - OpenAI format: {"type": "funct
lib/crewai/src/crewai/llms/providers/utils/common.py:59
↓ 2 callersMethodextract_tool_info
(self, tool_class: type[BaseTool])
lib/crewai-tools/src/crewai_tools/generate_tool_specs.py:41
↓ 2 callersFunctionfail
(message: str, exc_type: type[Exception] = JSONProjectError)
lib/crewai/src/crewai/project/json_loader.py:397
↓ 2 callersMethodfind_element
(self, by: str, selector: str)
lib/crewai-tools/tests/tools/selenium_scraping_tool_test.py:152
↓ 2 callersFunctionfind_sheet
The sheet named ``sheet`` (case-insensitive), or the first for empty. Raises: QueryError: No such sheet, or it wasn't read; the message s
lib/crewai-files/src/crewai_files/spreadsheets/answers.py:328
↓ 2 callersMethodfinish_spans
Drain event handlers, then close spans missing completion events.
lib/crewai/src/crewai/telemetry/tracing/session.py:230
↓ 2 callersMethodflow_creation_span
Records the creation of a new flow.
lib/crewai-core/src/crewai_core/telemetry.py:667
↓ 2 callersMethodflow_creation_span
Records the creation of a new flow. Args: flow_name: Name of the flow being created.
lib/crewai/src/crewai/telemetry/telemetry.py:982
↓ 2 callersMethodflow_execution_span
Records the execution of a flow. Args: flow_name: Name of the flow being executed. node_names: List of nodes being ex
lib/crewai/src/crewai/telemetry/telemetry.py:1017
↓ 2 callersFunctionflow_project
(folder: Path)
lib/cli/tests/test_api_keys.py:50
↓ 2 callersFunctionflush_and_shutdown
Export what is still buffered, waiting at most ``FINAL_FLUSH_SECONDS``. ``BatchSpanProcessor.force_flush`` ignores its timeout and runs the expor
lib/crewai-core/src/crewai_core/telemetry.py:150
↓ 2 callersMethodforget
Delete memories matching criteria. Args: scope: Scope to delete from. If None and root_scope is set, deletes only
lib/crewai/src/crewai/memory/unified_memory.py:828
↓ 2 callersFunctionformat_answer
Format a response from the LLM into an AgentAction or AgentFinish. Args: answer: The raw response from the LLM Returns: Eith
lib/crewai/src/crewai/utilities/agent_utils.py:444
↓ 2 callersMethodformat_block
Format a resolved file into a Gemini content block. Args: resolved: Resolved file. Returns: Content block di
lib/crewai-files/src/crewai_files/formatting/gemini.py:21
↓ 2 callersFunctionformat_description_for_llm
Compose the LLM-facing tool description. Combines the tool name, its argument JSON schema, and the authored description into the prompt block
lib/crewai/src/crewai/tools/structured_tool.py:145
↓ 2 callersFunctionformat_native_tool_output_for_agent
Format native tool output when a tool explicitly defines a formatter.
lib/crewai/src/crewai/utilities/agent_utils.py:1501
↓ 2 callersMethodformat_output_for_agent
Format a raw tool result into the string representation sent to an agent.
lib/crewai/src/crewai/tools/base_tool.py:406
↓ 2 callersMethodfrom_checkpoint
Read a checkpoint from the SQLite database. Args: location: A location string returned by ``checkpoint()``. Returns:
lib/crewai/src/crewai/state/provider/sqlite_provider.py:127
↓ 2 callersMethodfrom_job
(cls, job: JobRecord)
lib/crewai/src/crewai/experimental/flow_replies.py:36
↓ 2 callersMethodfrom_tuple
Create a GuardrailResult from a validation tuple. Args: result: A tuple of (success, data) where data is either the validated res
lib/crewai/src/crewai/utilities/guardrail.py:101
↓ 2 callersMethodgenerate_content
(self)
lib/cli/src/crewai_cli/templates/flow/main.py:31
↓ 2 callersFunctiongenerate_crew_description_with_ai
Generate a brief description of the crew using AI. Args: crew: The crew object. chat_llm: The chat language model to use for AI c
lib/crewai/src/crewai/utilities/crew_chat.py:488
← previousnext →2,801–2,900 of 19,663, ranked by callers