LlamaIndex

pip install llama-index-tools-valyu

export VALYU_API_KEY="your-api-key-here"

import os
from llama_index.tools.valyu import ValyuToolSpec

# Set your API key
os.environ["VALYU_API_KEY"] = "your-api-key-here"

# Initialize the tool with comprehensive configuration
valyu_tool = ValyuToolSpec(
    api_key=os.environ["VALYU_API_KEY"],
    verbose=True,
    # Search API parameters
    max_price=100,  # Maximum cost (optional - adjusts automatically if not provided)
    relevance_threshold=0.5,  # Minimum relevance score
    fast_mode=False,  # Quality vs speed trade-off
    included_sources=None,  # Optional source filtering
    excluded_sources=None,  # Optional source exclusion
    response_length=None,  # Content length control
    country_code=None,  # Geographic bias
)

# Perform a search
search_results = valyu_tool.search(
    query="What are agentic search-enhanced large reasoning models?",
    search_type="all",  # "all", "web", or "proprietary"
    max_num_results=5,
    start_date=None,  # Optional time filtering
    end_date=None,
    fast_mode=None  # Uses tool default if None
)

print("Search Results:")
for doc in search_results:
    print(f"Title: {doc.metadata['title']}")
    print(f"Content: {doc.text[:200]}...")
    print(f"Source: {doc.metadata['url']}")
    print(f"Relevance: {doc.metadata['relevance_score']}")
    print("---")

import os
from llama_index.tools.valyu import ValyuToolSpec

# Initialize tool with content extraction configuration
valyu_tool = ValyuToolSpec(
    api_key=os.environ["VALYU_API_KEY"],
    verbose=True,
    contents_summary=True,  # Enable AI summarization
    contents_extract_effort="high",  # Thorough extraction
    contents_response_length="medium",  # More detailed content
)

# Extract content from URLs
urls = [
    "https://arxiv.org/abs/1706.03762",  # Attention is All You Need paper
    "https://en.wikipedia.org/wiki/Transformer_(machine_learning_model)"
]

content_results = valyu_tool.get_contents(urls=urls)

print("Extracted Content:")
for doc in content_results:
    print(f"URL: {doc.metadata['url']}")
    print(f"Title: {doc.metadata['title']}")
    print(f"Content: {doc.text[:300]}...")
    if 'summary' in doc.metadata:
        print(f"Summary: {doc.metadata['summary']}")
    print("---")

import os
from llama_index.agent.openai import OpenAIAgent
from llama_index.tools.valyu import ValyuToolSpec

# Set API keys
os.environ["VALYU_API_KEY"] = "your-valyu-api-key"
os.environ["OPENAI_API_KEY"] = "your-openai-api-key"

# Initialize Valyu tool with comprehensive configuration
valyu_tool = ValyuToolSpec(
    api_key=os.environ["VALYU_API_KEY"],
    max_price=100,  # Maximum cost (optional - adjusts automatically if not provided)
    fast_mode=True,  # Enable fast mode for quicker responses
    # Contents API configuration
    contents_summary=True,  # Enable AI summarization for content extraction
    contents_extract_effort="normal",  # Extraction thoroughness
    contents_response_length="medium",  # Content length per URL
)

# Create OpenAI agent with Valyu tools
agent = OpenAIAgent.from_tools(
    valyu_tool.to_tool_list(),
    verbose=True,
)

# Example 1: search query
print("=== Search Example ===")
search_response = agent.chat(
    "What are the key considerations and empirical evidence for implementing statistical arbitrage strategies using cointegrated pairs trading, specifically focusing on the optimal lookback period for calculating correlation coefficients and the impact of transaction costs on strategy profitability in high-frequency trading environments?"
)
print(search_response)

# Example 2: URL content extraction
print("\n=== URL Content Extraction Example ===")
content_response = agent.chat(
    "Please extract and summarize the content from these URLs: https://arxiv.org/abs/1706.03762 and https://en.wikipedia.org/wiki/Transformer_(machine_learning_model)"
)
print(content_response)