What is CrewAI?
Framework for orchestrating autonomous AI agents that collaborate to complete tasks. Supports multi-agent crews with defined roles.
Searching YouTube Playlists with CrewAI
This integration lets your CrewAI agent search YouTube Playlists in real time via the Scavio API. The agent gets back structured JSON with playlist entries from search, video results, channel results, shorts results -- ready for reasoning and decision-making.
Setup
Bash
pip install crewai requestsCode Example
Here is a complete CrewAI agent that searches YouTube Playlists using Scavio:
Python
from crewai import Agent, Task, Crew
from crewai.tools import tool
import json
import os
import requests
# Playlist data is not available: POST /api/v1/youtube/search accepts type: playlist but the provider returns an empty playlists array, so there is no playlist title, video count, creator or visibility to read, and no removal tracking. This sample returns the videos for the query; type: channel does work if you want creators instead.
@tool("Scavio Search")
def scavio_search(query: str) -> str:
"""Query YouTube Playlists through the Scavio API (POST /api/v1/youtube/search)."""
response = requests.post(
"https://api.scavio.dev/api/v1/youtube/search",
headers={
"Authorization": "Bearer " + os.environ["SCAVIO_API_KEY"],
"Content-Type": "application/json",
},
json={"search": query},
timeout=60,
)
response.raise_for_status()
return json.dumps(response.json())
researcher = Agent(
role="YouTube Playlists Research Specialist",
goal="Find accurate, up-to-date information using YouTube Playlists data",
backstory="You are an expert researcher with access to real-time search data.",
tools=[scavio_search],
)
task = Task(
description="Research: best rag tutorials playlist",
expected_output="A detailed summary with sources",
agent=researcher,
)
crew = Crew(agents=[researcher], tasks=[task])
result = crew.kickoff()
print(result)Full Working Example
A production-ready example with error handling:
Python
from crewai import Agent, Task, Crew
from crewai.tools import tool
import json
import os
import requests
# Playlist data is not available: POST /api/v1/youtube/search accepts type: playlist but the provider returns an empty playlists array, so there is no playlist title, video count, creator or visibility to read, and no removal tracking. This sample returns the videos for the query; type: channel does work if you want creators instead.
@tool("Scavio Search")
def scavio_search(query: str) -> str:
"""Query YouTube Playlists through the Scavio API (POST /api/v1/youtube/search)."""
response = requests.post(
"https://api.scavio.dev/api/v1/youtube/search",
headers={
"Authorization": "Bearer " + os.environ["SCAVIO_API_KEY"],
"Content-Type": "application/json",
},
json={"search": query},
timeout=60,
)
response.raise_for_status()
return json.dumps(response.json())
researcher = Agent(
role="YouTube Playlists Research Specialist",
goal="Find accurate, up-to-date information",
backstory="Expert researcher with real-time search access.",
tools=[scavio_search],
)
task = Task(
description="Research: best rag tutorials playlist",
expected_output="Detailed summary with key findings and sources",
agent=researcher,
)
crew = Crew(agents=[researcher], tasks=[task], verbose=True)
result = crew.kickoff()
print(result)Pricing
Scavio offers a free tier with 50 credits on signup (1 credit per search). No credit card required. This is enough to build and test your CrewAI integration. Paid plans start at $30/month for higher volumes.