What is LlamaIndex?
Data framework for building RAG pipelines and LLM applications over custom data. Connects LLMs to external data sources.
Searching YouTube Shorts with LlamaIndex
This integration lets your LlamaIndex 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 llama-index requestsCode Example
Here is a complete LlamaIndex agent that searches YouTube Shorts using Scavio:
Python
from llama_index.core.tools import FunctionTool
from llama_index.llms.openai import OpenAI
from llama_index.core.agent import ReActAgent
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 search_youtube_shorts(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())
tool = FunctionTool.from_defaults(fn=search_youtube_shorts)
llm = OpenAI(model="gpt-5.5")
agent = ReActAgent.from_tools([tool], llm=llm, verbose=True)
response = agent.chat("ai coding agent shorts")
print(response)Full Working Example
A production-ready example with error handling:
Python
from llama_index.core.tools import FunctionTool
from llama_index.llms.openai import OpenAI
from llama_index.core.agent import ReActAgent
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 search_youtube_shorts(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())
tool = FunctionTool.from_defaults(fn=search_youtube_shorts)
llm = OpenAI(model="gpt-5.5")
agent = ReActAgent.from_tools([tool], llm=llm, verbose=True)
response = agent.chat("ai coding agent shorts")
print(response)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 LlamaIndex integration. Paid plans start at $30/month for higher volumes.