CommencerCommencer gratuitement

Building Confidence with LLM Sources

You're building a financial analysis assistant that needs to provide users with current stock market information. Since LLMs have knowledge cutoffs, you need to enable web search to access real-time data. Additionally, for transparency and credibility, you want to show users which sources were consulted during the search.

The OpenAI client has been initialized as client, and you'll be querying for the current price of Netflix stock.

Cet exercice fait partie du cours

Working with the OpenAI Responses API

Afficher le cours

Instructions

  • Create a web search-enabled request, making sure to include the web search sources in the response.
  • Loop through the response items and extract only items with type "web_search_call", then print the .sources from each web search call's .action attribute.

Exercice interactif pratique

Essayez cet exercice en complétant cet exemple de code.

# Create a response with web search enabled and sources included
response = client.responses.create(
    model="gpt-5-mini",
    tools=[{"type": "web_search"}],
    input="What is the current stock price of Netflix?",
    include=["web_search_call.____.____"]
)

# Extract and print sources from web search calls
for item in response.output:
    if ____:
        print(item.action.sources)
        
print(response.output_text)
Modifier et exécuter le code