LangChain Integration

pip install langchain-valyu python-dotenv

# .env
VALYU_API_KEY=your-valyu-api-key-here
ANTHROPIC_API_KEY=your-anthropic-api-key-here # Optional for later examples
OPENAI_API_KEY=your-openai-api-key-here # Optional for later examples

from langchain_valyu import ValyuSearchTool
from dotenv import load_dotenv

load_dotenv()

# Initialize the search tool
tool = ValyuSearchTool()

# Perform a search
search_results = tool._run(
    query="What are agentic search-enhanced large reasoning models?",
    search_type="proprietary",  # "all", "web", or "proprietary"
    max_num_results=10,
    relevance_threshold=0.5,
    max_price=30.0,
)

print("Search Results:", search_results)

pip install langchain-anthropic

from langchain_valyu import ValyuSearchTool
from langchain_anthropic import ChatAnthropic
from langgraph.prebuilt import create_react_agent
from datetime import datetime
from dotenv import load_dotenv

# Load environment variables from .env file
load_dotenv()

# Initialize agent components
llm = ChatAnthropic(model="claude-sonnet-4-20250514")
valyu_search_tool = ValyuSearchTool()

# Create agent with Valyu Deepsearch
agent = create_react_agent(
    llm,
    [valyu_search_tool],
    prompt=f"Today is ${datetime.now().strftime('%Y-%m-%d')}. You are a helpful assistant that has access to a tool to search for information.",
)

# User message
input_message = {
    "role": "user",
    "content": "What are the benchmarks of the new Grok 4 model from xAI, and how does it compare to the previous models?",
}

# Stream agent tool calls and response
for step in agent.stream(
    {"messages": [input_message]},
    stream_mode="values",
):
    step["messages"][-1].pretty_print()

from langchain_valyu import ValyuSearchTool

tool = ValyuSearchTool()

# Advanced search with specific parameters
results = tool._run(
    query="quantum computing breakthroughs 2024",
    search_type="proprietary",  # Focus on academic sources
    max_num_results=10,
    relevance_threshold=0.6,  # Higher relevance threshold
    max_price=30.0,  # Increase budget for better results
    is_tool_call=True,  # Optimized for agent usage
    start_date="2024-01-01",  # Time-filtered search
    end_date="2024-12-31",
)

from langchain_valyu import ValyuSearchTool
from langchain_anthropic import ChatAnthropic
from langchain_openai import ChatOpenAI
from langgraph.prebuilt import create_react_agent
from langchain_core.messages import HumanMessage

# Create specialized research agent
research_llm = ChatAnthropic(model="claude-3-5-sonnet-20241022", temperature=0.1)
research_tool = ValyuSearchTool()

research_agent = create_react_agent(
    research_llm,
    [research_tool]
)

# Create analysis agent
analysis_llm = ChatOpenAI(model="gpt-4o", temperature=0.3)
analysis_agent = create_react_agent(
    analysis_llm,
    [research_tool]
)

# Coordinate agents for complex queries
research_query = "Find recent papers on transformer architecture improvements"
analysis_query = "Analyze market trends in AI chip demand"

# Execute research agent
for step in research_agent.stream(
    {"messages": [HumanMessage(content=research_query)]},
    stream_mode="values",
):
    step["messages"][-1].pretty_print()

# Execute analysis agent
for step in analysis_agent.stream(
    {"messages": [HumanMessage(content=analysis_query)]},
    stream_mode="values",
):
    step["messages"][-1].pretty_print()

from langchain_valyu import ValyuSearchTool
from langchain_anthropic import ChatAnthropic
from langgraph.prebuilt import create_react_agent
from langchain_core.messages import HumanMessage, SystemMessage

# Create financial research agent
financial_llm = ChatAnthropic(model="claude-sonnet-4-20250514")
valyu_tool = ValyuSearchTool()

financial_agent = create_react_agent(financial_llm, [valyu_tool])

# Query financial markets with system context
query = "What are the latest developments in cryptocurrency regulation and their impact on institutional adoption?"

system_context = SystemMessage(content="""You are a financial research assistant. Use Valyu to search for:
- Real-time market data and news
- Academic research on financial models
- Economic indicators and analysis

Always cite your sources and provide context about data recency.""")

for step in financial_agent.stream(
    {"messages": [system_context, HumanMessage(content=query)]},
    stream_mode="values",
):
    step["messages"][-1].pretty_print()

from langchain_valyu import ValyuSearchTool

# Configure for academic research
academic_tool = ValyuSearchTool()

# Search academic sources specifically
academic_results = academic_tool._run(
    query="CRISPR gene editing safety protocols",
    search_type="proprietary",  # Focus on academic datasets
    max_num_results=8,
    relevance_threshold=0.6,
)

print("Academic Sources Found:", len(academic_results.results))

# Set appropriate price limits based on use case
tool = ValyuSearchTool()

# For quick lookups
quick_search = tool._run(
    query="current bitcoin price",
    max_price=30.0,  # Lower cost for simple queries
    max_num_results=3
)

# For comprehensive research
detailed_search = tool._run(
    query="comprehensive analysis of renewable energy trends",
    max_price=50.0,  # Higher budget for complex queries
    max_num_results=15,
    search_type="all"
)

# Web search for current events
web_results = tool._run(
    query="latest AI policy developments",
    search_type="web",
    max_num_results=5
)

# Proprietary search for academic research
academic_results = tool._run(
    query="machine learning interpretability methods",
    search_type="proprietary",
    max_num_results=8
)

# Combined search for comprehensive coverage
all_results = tool._run(
    query="climate change economic impact",
    search_type="all",
    max_num_results=10
)

from langchain_valyu import ValyuSearchTool

def robust_search(query: str, fallback_query: str = None):
    tool = ValyuSearchTool()

    try:
        # Primary search
        results = tool._run(
            query=query,
            max_price=30.0,
            max_num_results=5
        )
        return results
    except Exception as e:
        print(f"Primary search failed: {e}")

        if fallback_query:
            try:
                # Fallback with simpler query
                results = tool._run(
                    query=fallback_query,
                    max_price=30.0,
                    max_num_results=3,
                    search_type="web"
                )
                return results
            except Exception as e2:
                print(f"Fallback search also failed: {e2}")
                return "Search unavailable"

        return "Search failed"

# Usage
results = robust_search(
    "complex quantum entanglement applications",
    "quantum entanglement basics"
)

from langchain_core.messages import SystemMessage, HumanMessage

# Optimize agent behavior with good system messages
system_message = SystemMessage(content="""You are an AI research assistant with access to Valyu search.

SEARCH GUIDELINES:
- Use search_type="proprietary" for academic/scientific queries
- Use search_type="web" for current events and news
- Use search_type="all" for comprehensive research
- Set higher relevance_threshold (0.6+) for precise results
- Use category parameter to guide search context
- Always cite sources from search results

RESPONSE FORMAT:
- Provide direct answers based on search results
- Include source citations with URLs when available
- Mention publication dates for time-sensitive information
- Indicate if information might be outdated""")

agent = create_react_agent(llm, [ValyuSearchTool()])

# Use the agent with system context
for step in agent.stream(
    {"messages": [system_message, HumanMessage(content="Your query here")]},
    stream_mode="values",
):
    step["messages"][-1].pretty_print()

from langchain_valyu import ValyuRetriever
from langchain_core.documents import Document

# Initialize retriever
retriever = ValyuRetriever(
    k=5,  # Number of results
    search_type="proprietary",
    relevance_threshold=0.6,
    max_price=30.0
)

# Use with LangChain
docs = retriever.get_relevant_documents("quantum computing advances")
for doc in docs:
    print(f"Title: {doc.metadata['title']}")
    print(f"Content: {doc.page_content[:200]}...")

from langchain.retrievers.base import BaseRetriever
from langchain_valyu import ValyuSearchTool
from langchain.schema import Document

class ValyuRetriever(BaseRetriever):
    def __init__(self, search_type="all", max_results=5):
        self.tool = ValyuSearchTool()
        self.search_type = search_type
        self.max_results = max_results

    def _get_relevant_documents(self, query: str):
        search_response = self.tool._run(
            query=query,
            search_type=self.search_type,
            max_num_results=self.max_results
        )

        # Convert to LangChain Documents
        documents = []
        for result in search_response.results:
            doc = Document(
                page_content=result.get('content', ''),
                metadata={
                    'source': result.get('url', ''),
                    'title': result.get('title', ''),
                    'relevance_score': result.get('relevance_score', 0)
                }
            )
            documents.append(doc)

        return documents

# Use custom retriever
retriever = ValyuRetriever(search_type="proprietary", max_results=8)
docs = retriever.get_relevant_documents("machine learning safety")