Step 3: Connect the LLM to the web

To fact-check a claim, the model needs to find evidence online, and this step builds the function that connects the LLM to the web.

Notice a few fields:

• objective field: Bold text Natural language intent rather than keywords.

• one-shot mode: For simplicity and speed, this guide stick to a one-shot setup, which gives high-quality excerpts in a single call.

def search_web(query: str, num: int = 5, mode: str = "one-shot"):
    """
    Search the web using Parallel's Search API.

    Returns a list of dicts with:
      - url
      - title
      - publish_date
      - excerpts (list of strings)
    """

    # Instruct the LLM find quality sources.
    objective = (
        f"Find high-quality, up-to-date sources that answer the question:\n\n{query}\n\n"
        "Prefer authoritative sites (e.g., .gov, .edu, major news, or official org websites)."
    )

    # Initiatiate the LLM for web search
    search = parallel_client.beta.search(
        objective=objective,
        search_queries=[query],
        mode=mode,
        max_results=num,
        excerpts={
            "max_chars_per_result": 8000,
        },
    )

    results = []
    # Process the search results and extract information like URL, title, and excerpts.
    for r in search.results:
        results.append(
            {
                "url": r.url,
                "title": getattr(r, "title", None),
                "publish_date": getattr(r, "publish_date", None),
                "excerpts": list(r.excerpts or []),
            }
        )
    return results