Valyu allows AI applications and agents to search the internet and proprietary data sources for relevant LLM ready information.
This notebook goes over how to use Valyu deep search tool in LangChain. First, get an Valyu API key and add it as an environment variable. Get $10 free credit by signing up here.

​
Setup

The integration lives in the langchain-valyu package. 
%pip install -qU langchain-valyu
In order to use the package, you will also need to set the VALYU_API_KEY environment variable to your Valyu API key. 
import os

valyu_api_key = os.environ["VALYU_API_KEY"]

​
Instantiation

Now we can instantiate our retriever: The ValyuContextRetriever can be configured with several parameters:
  • k: int = 5 The number of top results to return for each query.
  • search_type: str = "all" The type of search to perform: ‘all’, ‘proprietary’, or ‘web’. Defaults to ‘all’.
  • relevance_threshold: float = 0.5 The minimum relevance score (between 0 and 1) required for a document to be considered relevant. Defaults to 0.5.
  • max_price: float = 20.0 The maximum price (in USD) you are willing to spend per query. Defaults to 20.0.
  • start_date: Optional[str] = None Start date for time filtering in YYYY-MM-DD format (optional).
  • end_date: Optional[str] = None End date for time filtering in YYYY-MM-DD format (optional).
  • client: Optional[Valyu] = None An optional custom Valyu client instance. If not provided, a new client will be created internally.
  • valyu_api_key: Optional[str] = None Your Valyu API key. If not provided, the retriever will look for the VALYU_API_KEY environment variable. 
from langchain_valyu import ValyuRetriever

retriever = ValyuRetriever(
    k=5,
    search_type="all",
    relevance_threshold=0.5,
    max_price=20.0,
    start_date="2024-01-01",
    end_date="2024-12-31",
    client=None,
    valyu_api_key=os.environ["VALYU_API_KEY"],
)

​
Usage

query = "What are the benefits of renewable energy?"
docs = retriever.invoke(query)

for doc in docs:
    print(doc.page_content)
    print(doc.metadata)

​
Use within a chain

We can easily combine this retriever in to a chain. 
from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnablePassthrough
from langchain_openai import ChatOpenAI

prompt = ChatPromptTemplate.from_template(
    """Answer the question based only on the context provided.

Context: {context}

Question: {question}"""
)

llm = ChatOpenAI(model="gpt-4o-mini")


def format_docs(docs):
    return "\n\n".join(doc.page_content for doc in docs)


chain = (
    {"context": retriever | format_docs, "question": RunnablePassthrough()}
    | prompt
    | llm
    | StrOutputParser()
)

​
API reference

For detailed documentation of all Valyu Context API features and configurations head to the API reference: docs.valyu.network/overview