What is LlamaIndex?
Data framework for building RAG pipelines and LLM applications over custom data. Connects LLMs to external data sources.
Searching Meta Ad Library with LlamaIndex
This integration lets your LlamaIndex agent search Meta Ad Library in real time via the Scavio API. The agent gets back structured JSON with ad creatives, page_name and page_id, start_date and end_date, publisher_platform -- ready for reasoning and decision-making.
Setup
Bash
pip install llama-index requestsCode Example
Here is a complete LlamaIndex agent that searches Meta Ad Library 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
# This page has no dedicated endpoint yet, so the sample runs a Google web search.
def search_meta_ads(query: str) -> str:
"""Query Meta Ad Library through the Scavio API (POST /api/v2/google)."""
response = requests.post(
"https://api.scavio.dev/api/v2/google",
headers={
"Authorization": "Bearer " + os.environ["SCAVIO_API_KEY"],
"Content-Type": "application/json",
},
json={"query": query},
timeout=60,
)
response.raise_for_status()
return json.dumps(response.json())
tool = FunctionTool.from_defaults(fn=search_meta_ads)
llm = OpenAI(model="gpt-5.5")
agent = ReActAgent.from_tools([tool], llm=llm, verbose=True)
response = agent.chat("notion")
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
# This page has no dedicated endpoint yet, so the sample runs a Google web search.
def search_meta_ads(query: str) -> str:
"""Query Meta Ad Library through the Scavio API (POST /api/v2/google)."""
response = requests.post(
"https://api.scavio.dev/api/v2/google",
headers={
"Authorization": "Bearer " + os.environ["SCAVIO_API_KEY"],
"Content-Type": "application/json",
},
json={"query": query},
timeout=60,
)
response.raise_for_status()
return json.dumps(response.json())
tool = FunctionTool.from_defaults(fn=search_meta_ads)
llm = OpenAI(model="gpt-5.5")
agent = ReActAgent.from_tools([tool], llm=llm, verbose=True)
response = agent.chat("notion")
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 from $24/mo billed yearly for higher volumes.