Use Search API with the Google Gemini SDK

pip install google-genai perplexityai
export GEMINI_API_KEY="your_gemini_key"
export PERPLEXITY_API_KEY="your_perplexity_key"

from google.genai import types

WEB_SEARCH_TOOL_DESCRIPTION = """\
Searches the web for current and factual information to answer user queries, returning relevant results with titles, URLs, and content snippets, similar to Google or Bing. Intended for questions about up-to-date or externally verified information beyond your knowledge cutoff. The tool works best with an array of short, keyword-focused queries. Complex queries that require multi-step reasoning are not supported. Time-sensitive queries are supported if the date is included in the query.

Best practices for using this tool:
- Limit the number of queries in each request to a maximum of three to maintain efficiency.
- For multi-entity questions, break them into separate, single-entity queries:
  - Preferred:
    [
      "Brand A protein powder review",
      "Brand B protein powder review"
    ]
  - Not recommended:
    [
      "Brand A vs Brand B protein powder review"
    ]

- For simple queries, keep each query straightforward and focused:
  - Preferred: ["inflation rate Canada"]
  - Not recommended: ["What is the inflation rate in Canada?"]

Each query should be short to ensure optimal tool performance. Make sure all provided examples and generated queries follow this guideline."""

QUERIES_PARAM_DESCRIPTION = (
    "An array of keyword-based search queries. Each query should be short, "
    "as longer queries may reduce performance. Do not provide more than three "
    "queries to maintain efficiency."
)

WEB_SEARCH_FUNCTION = types.FunctionDeclaration(
    name="web_search",
    description=WEB_SEARCH_TOOL_DESCRIPTION,
    parameters_json_schema={
        "type": "object",
        "properties": {
            "queries": {
                "type": "array",
                "description": QUERIES_PARAM_DESCRIPTION,
                "items": {"type": "string"},
                "minItems": 1,
                "maxItems": 3,
            },
        },
        "required": ["queries"],
    },
)

WEB_SEARCH_TOOL = types.Tool(function_declarations=[WEB_SEARCH_FUNCTION])

from perplexity import Perplexity

perplexity = Perplexity()

def run_web_search(queries: list[str]) -> str:
    """Call Perplexity Search and format the results for the model."""
    response = perplexity.search.create(query=queries, max_results=5)

    lines = []
    for result in response.results:
        snippet = (result.snippet or "").strip().replace("\n", " ")
        if len(snippet) > 400:
            snippet = snippet[:400] + "…"
        lines.append(f"- {result.title}\n  {result.url}\n  {snippet}")
    return "\n\n".join(lines) if lines else "No results."

import json
from google import genai
from google.genai import types

gemini = genai.Client()

def chat_with_search(user_prompt: str, model: str = "gemini-2.5-flash") -> str:
    contents: list[types.Content] = [
        types.Content(
            role="user",
            parts=[types.Part.from_text(text=user_prompt)],
        ),
    ]

    config = types.GenerateContentConfig(
        tools=[WEB_SEARCH_TOOL],
        automatic_function_calling=types.AutomaticFunctionCallingConfig(disable=True),
    )

    while True:
        response = gemini.models.generate_content(
            model=model,
            contents=contents,
            config=config,
        )

        function_calls = response.function_calls or []

        if not function_calls:
            return response.text

        # Persist the assistant's function_call parts.
        contents.append(response.candidates[0].content)

        # Run each function call and pair results by name (Gemini matches
        # function_response → function_call positionally within the turn).
        response_parts: list[types.Part] = []
        for call in function_calls:
            if call.name == "web_search":
                queries = call.args.get("queries", [])
                output = run_web_search(queries)
                result = {"result": output}
            else:
                result = {"error": f"unknown tool: {call.name}"}
            response_parts.append(
                types.Part.from_function_response(name=call.name, response=result)
            )

        contents.append(types.Content(role="user", parts=response_parts))


if __name__ == "__main__":
    answer = chat_with_search(
        "What were the major AI infrastructure announcements this week?"
    )
    print(answer)

for chunk in gemini.models.generate_content_stream(
    model="gemini-2.5-flash",
    contents=contents,
    config=config,
):
    if chunk.text:
        print(chunk.text, end="", flush=True)
    # Accumulate function-call parts across chunks before executing.