Hi all, I’m trying to make a api request like this
url = "https://api.perplexity.ai/chat/completions"
payload = {
"model": "llama-3.1-sonar-large-128k-online",
"messages": [
{
"role": "system",
"content": (
"Help find the latest news for the user through as many sources as possible. Compile "
"it in an unbiased way"
),
},
{"role": "user", "content": f"What's the latest news about US stock market"},
],
"return_citations": True,
"search_domain_filter": ["cnbc.com"],
"search_recency_filter": "day",
}
However I end up getting citations outside cnbc.com domain
I see. thanks for flagging we will take a look at it.
I am getting same issue: query had these domains: “search_domain_filter”:[
“ndtv.com”,
“indiatoday.in”,
“thehindu.com”,
“firstpost.com”,
“theprint.in”,
“deccanchronicle.com”,
“financialexpress.com”,
“thehindubusinessline.com”,
“ndtvprofit.com”,
“hindustantimes.com”,
“news18.com”,
“newindianexpress.com”
] but the result refernece links were:
URLs:
(0, ‘Sensex jumps 1,200 points: 3 things to know about today’s stock market bull run - India Today’)
(1, ‘https://www.business-standard.com/markets/news/sensex-zooms-1200-pts-nifty-atop-23-700-what-s-driving-the-markets-today-124112200596_1.html’)
(2, ‘https://www.youtube.com/watch?v=4nYRGUmhG5c’)
(3, ‘Stock Market Today: Market Wrap: RIL, IT stocks fire Sensex 1,960 points higher, Nifty tops 23,900. Top 6 factors behind the bull run - The Economic Times’)
(4, ‘Stock Market Highlights: Nifty rebounds above 23,500 level, 200 DEMA; pullback rally eyes 24k resistance. How to trade on Monday - The Economic Times’)
search_domain_filter
does not work for domain blacklisting either:
"search_domain_filter": ["-domain1.com", "-domain2.com", "-domain3.com"]
I apologize for the mistake on our documentation but the search_domain_filter is a beta feature. If you don’t have access to it the API does not take it into account.