OpenAI Integration

Best for: building Valyu into your product / agents. Add real-time search to an OpenAI app via Valyu’s provider.

The OpenAIProvider exposes Valyu search as a tool through OpenAI’s Responses API, so your agents can pull real-time information from academic papers, news, financial data, and authoritative sources.

Paste into your AI assistant to wire Valyu search into an OpenAI app.

Open in Cursor

Installation

Install the Valyu and OpenAI packages:

pip install valyu openai

Set your API keys as environment variables:

export VALYU_API_KEY="your-valyu-api-key"
export OPENAI_API_KEY="your-openai-api-key"

Free Credits

Get your API key with $10 free credits ($20 with a work email) from the Valyu Platform.

Basic Usage

The OpenAI provider handles the integration with the Responses API:

from openai import OpenAI
from valyu import OpenAIProvider
from dotenv import load_dotenv

load_dotenv()

# Initialize clients
openai_client = OpenAI()
provider = OpenAIProvider()

# Get Valyu tools
tools = provider.get_tools()

# Create a research request
messages = [
    {
        "role": "user",
        "content": "What are the latest developments in quantum computing? Write a summary of your findings."
    }
]

# Step 1: Call OpenAI Responses API with tools
response = openai_client.responses.create(
    model="gpt-5",
    input=messages,
    tools=tools,
)

# Step 2: Execute tool calls
tool_results = provider.execute_tool_calls(response)

# Step 3: Get final response with search results
if tool_results:
    updated_messages = provider.build_conversation(messages, response, tool_results)
    final_response = openai_client.responses.create(
        model="gpt-5",
        input=updated_messages,
        tools=tools,
    )
    print(final_response.output_text)
else:
    print(response.output_text)

How it works

The OpenAIProvider handles tool registration, execution, and conversation flow for you. The model decides when to search; the provider runs the call and feeds results back.

This uses OpenAI’s Responses API (responses.create()), not Chat Completions.

Search parameters the model can set

The model chooses these per query based on context:

max_num_results - 1-20 for standard keys, up to 100 with a special API key
included_sources / excluded_sources - target or exclude datasets
category - guide search to a topic
start_date / end_date - time-bounded searches
relevance_threshold - filter by relevance (0-1)

Steer behaviour with a system prompt: cite sources, use natural-language queries (not operators). See the Prompting Guide.

OpenAIProvider reference

class OpenAIProvider:
    def __init__(self, valyu_api_key: Optional[str] = None): ...
    def get_tools(self) -> List[Dict]: ...
    def execute_tool_calls(self, response) -> List[Dict]: ...
    def build_conversation(self, input_messages, response, tool_results) -> List[Dict]: ...

Agents & MCP

Automation Platforms

Work Platforms

Framework SDKs

Community SDKs

LLM Providers

OpenAI

Installation

Free Credits

Basic Usage

How it works

Additional Resources

OpenAI Responses API

Valyu API Reference

Python SDK

Get API Key

​Installation

Free Credits

​Basic Usage

​How it works

​Additional Resources

OpenAI Responses API

Valyu API Reference

Python SDK

Get API Key

Installation

Basic Usage

How it works

Additional Resources