> ## Documentation Index
> Fetch the complete documentation index at: https://langchain.idochub.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Valyu Deep Search

> [Valyu](https://www.valyu.network/) 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 in LangChain.

First, get an Valyu API key and add it as an environment variable. Get \$10 free credit  by [signing up here](https://platform.valyu.network/).

## Setup

The integration lives in the `langchain-valyu` package.

```python theme={null}
%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.

## Context Retriever

You can use the [`ValyuContextRetriever`](https://pypi.org/project/langchain-valyu/) in a standard retrieval pipeline.

```python theme={null}
from langchain_valyu import ValyuRetriever

valyu_api_key = "YOUR API KEY"

# Create a new instance of the ValyuRetriever
valyu_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",
    valyu_api_key=valyu_api_key,
)

# Search for a query and save the results
docs = valyu_retriever.invoke("What are the benefits of renewable energy?")

# Print the results
for doc in docs:
    print(doc.page_content)
    print(doc.metadata)
```

## Context Search Tool

You can use the `ValyuSearchTool` for advanced search queries.

```python theme={null}
from langchain_valyu import ValyuSearchTool

# Initialize the ValyuSearchTool
search_tool = ValyuSearchTool(valyu_api_key="YOUR API KEY")

# Perform a search query
search_results = search_tool._run(
    query="What are agentic search-enhanced large reasoning models?",
    search_type="all",
    max_num_results=5,
    relevance_threshold=0.5,
    max_price=20.0,
    start_date="2024-01-01",
    end_date="2024-12-31",
)

print("Search Results:", search_results)
```