Implementation:CrewAIInc CrewAI YouTube Channel Search Tool

Knowledge Sources	CrewAI
Domains	Tools, RAG, YouTube
Last Updated	2026-02-11 00:00 GMT

Overview

YoutubeChannelSearchTool performs RAG-based semantic search across a YouTube channel's video content using vector embeddings.

Description

The YoutubeChannelSearchTool extends RagTool and uses the dual-schema pattern: YoutubeChannelSearchToolSchema requires both search_query and youtube_channel_handle, while FixedYoutubeChannelSearchToolSchema requires only search_query (used when a channel is pre-configured). During initialization, if a youtube_channel_handle is provided, it is added to the RAG index and the schema switches to the fixed variant. The add method ensures the channel handle is prefixed with @ if not already present, then delegates to RagTool.add with DataType.YOUTUBE_CHANNEL, signaling the RAG infrastructure to process YouTube channel content accordingly. The _run method optionally adds a new channel at runtime before delegating semantic search to the parent with configurable similarity_threshold and limit.

Usage

Use this tool when a CrewAI agent needs to semantically search through YouTube channel content, extracting information from video transcripts for research, competitive analysis, or content discovery workflows.

Code Reference

Source Location

• Repository: CrewAI
• File: lib/crewai-tools/src/crewai_tools/tools/youtube_channel_search_tool/youtube_channel_search_tool.py
• Lines: 1-56

Signature

class FixedYoutubeChannelSearchToolSchema(BaseModel):
    search_query: str = Field(..., description="Mandatory search query ...")

class YoutubeChannelSearchToolSchema(FixedYoutubeChannelSearchToolSchema):
    youtube_channel_handle: str = Field(..., description="Mandatory youtube_channel_handle path you want to search")

class YoutubeChannelSearchTool(RagTool):
    name: str = "Search a Youtube Channels content"
    description: str = "A tool that can be used to semantic search a query from a Youtube Channels content."
    args_schema: type[BaseModel] = YoutubeChannelSearchToolSchema

    def __init__(self, youtube_channel_handle: str | None = None, **kwargs):
        ...
    def add(self, youtube_channel_handle: str) -> None:
        ...
    def _run(self, search_query: str, youtube_channel_handle: str | None = None,
             similarity_threshold: float | None = None, limit: int | None = None) -> str:
        ...

Import

from crewai_tools import YoutubeChannelSearchTool

I/O Contract

Inputs

Name	Type	Required	Description
search_query	str	Yes	The semantic search query to run against the YouTube channel content
youtube_channel_handle	str	No	YouTube channel handle (with or without @ prefix; can be set at init or runtime)
similarity_threshold	float	No	Minimum similarity score for results
limit	int	No	Maximum number of results to return

Outputs

Name	Type	Description
_run() returns	str	Semantically relevant text passages from the YouTube channel's video transcripts

Usage Examples

Basic Usage

from crewai_tools import YoutubeChannelSearchTool

tool = YoutubeChannelSearchTool(youtube_channel_handle="@crewaboratory")
result = tool._run(search_query="how to build agents")

Dynamic Channel

from crewai_tools import YoutubeChannelSearchTool

tool = YoutubeChannelSearchTool()
result = tool._run(search_query="tutorials", youtube_channel_handle="crewaboratory")

Related Pages

• Principle:CrewAIInc_CrewAI_Built_In_Tool_Selection