What is AutoGen?
Microsoft's framework for building multi-agent conversational AI systems. Agents can converse, use tools, and collaborate autonomously.
Searching YouTube Shorts with AutoGen
This integration lets your AutoGen agent search YouTube Shorts in real time via the Scavio API. The agent gets back structured JSON with short video results, video ids, view counts, published time -- ready for reasoning and decision-making.
Setup
Bash
pip install autogen-agentchat requestsCode Example
Here is a complete AutoGen agent that searches YouTube Shorts using Scavio:
Python
from autogen import ConversableAgent
import json
import os
import requests
# Shorts search takes search (not query). channel.name is often empty on Shorts rows - resolve it with POST /api/v1/youtube/video when you need it.
def scavio_search(query: str) -> str:
"""Query YouTube Shorts through the Scavio API (POST /api/v1/youtube/shorts)."""
response = requests.post(
"https://api.scavio.dev/api/v1/youtube/shorts",
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())
assistant = ConversableAgent(
"assistant",
llm_config={"model": "gpt-5.5"},
system_message="You are a helpful research assistant.",
)
user = ConversableAgent("user", human_input_mode="NEVER")
assistant.register_for_llm(name="search", description="Query YouTube Shorts")(scavio_search)
user.register_for_execution(name="search")(scavio_search)
user.initiate_chat(assistant, message="Research: ai coding agent shorts")Full Working Example
A production-ready example with error handling:
Python
from autogen import ConversableAgent
import json
import os
import requests
# Shorts search takes search (not query). channel.name is often empty on Shorts rows - resolve it with POST /api/v1/youtube/video when you need it.
def scavio_search(query: str) -> str:
"""Query YouTube Shorts through the Scavio API (POST /api/v1/youtube/shorts)."""
response = requests.post(
"https://api.scavio.dev/api/v1/youtube/shorts",
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())
assistant = ConversableAgent(
"assistant",
llm_config={"model": "gpt-5.5"},
system_message="You are a helpful research assistant with real-time search.",
)
user = ConversableAgent("user", human_input_mode="NEVER", max_consecutive_auto_reply=3)
assistant.register_for_llm(name="search", description="Query YouTube Shorts")(scavio_search)
user.register_for_execution(name="search")(scavio_search)
user.initiate_chat(assistant, message="Research: ai coding agent shorts")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 AutoGen integration. Paid plans start at $30/month for higher volumes.