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

# Perplexity search integration

> Integrate with the Perplexity search tool using LangChain Python.

[Perplexity Search](https://docs.perplexity.ai/docs/search/quickstart) is a web search API that returns ranked, source-attributed results designed for use by LLMs and agents. It powers the answer engine at [perplexity.ai](https://www.perplexity.ai/) and is exposed through the dedicated [Search API endpoint](https://docs.perplexity.ai/api-reference/search-post).

This page goes over how to use the Perplexity Search API as a LangChain tool.

## Setup

### Installation

Install the LangChain Perplexity integration package:

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
pip install -qU langchain-perplexity

# and some deps for this notebook
pip install -qU langchain langchain-openai
```

### Credentials

You'll need a Perplexity API key to use this integration. Create one in the [Perplexity API key dashboard](https://www.perplexity.ai/account/api/keys).

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import getpass
import os

if not os.environ.get("PPLX_API_KEY"):
    os.environ["PPLX_API_KEY"] = getpass.getpass("Perplexity API key:\n")
```

The integration also accepts `PERPLEXITY_API_KEY` if you prefer that name.

## Using PerplexitySearchResults tool

`PerplexitySearchResults` is a tool that can be used with LangChain agents to perform Perplexity searches. Calling it returns a JSON array of search results, each containing a `title`, `url`, `snippet`, `date`, and `last_updated` field.

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain_perplexity import PerplexitySearchResults

# Initialize the PerplexitySearchResults tool
search_tool = PerplexitySearchResults(max_results=5)

# Perform a search query
search_results = search_tool.invoke("When was the last time the New York Knicks won the NBA Championship?")

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

### Advanced features for PerplexitySearchResults

The tool accepts the following constructor and call-time arguments:

* `max_results` — number of results to return.
* `country` — ISO country code to bias results (e.g. `"US"`).
* `search_domain_filter` — list of domains to include or exclude (max 20). Prefix a domain with `-` to exclude it. See the [domain filter docs](https://docs.perplexity.ai/docs/search/filters/domain-filter).
* `search_recency_filter` — one of `"day"`, `"week"`, `"month"`, `"year"`. See the [date and time filter docs](https://docs.perplexity.ai/docs/search/filters/date-time-filters).
* `search_after_date` / `search_before_date` — date strings in `MM/DD/YYYY` format.

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain_perplexity import PerplexitySearchResults

# Restrict results to a recent timeframe and a specific set of domains
search_tool = PerplexitySearchResults(
    max_results=10,
    country="US",
    search_recency_filter="week",
    search_domain_filter=["nytimes.com", "reuters.com", "-pinterest.com"],
)

results = search_tool.invoke("Latest AI research papers")
print(results)
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain_perplexity import PerplexitySearchResults

# Restrict results to a specific date range
search_tool = PerplexitySearchResults(
    max_results=5,
    search_after_date="01/01/2025",
    search_before_date="06/30/2025",
)

results = search_tool.invoke("US Federal Reserve interest rate decisions")
print(results)
```

## Use within an Agent

We can use the `PerplexitySearchResults` tool with a LangGraph agent. This gives the agent the ability to dynamically search the web for grounded, source-attributed information.

First, set up the language model. You'll need to provide your OpenAI API key:

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import getpass

if not os.environ.get("OPENAI_API_KEY"):
    os.environ["OPENAI_API_KEY"] = getpass.getpass("OpenAI API key:\n")
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain.agents import create_agent
from langchain.chat_models import init_chat_model
from langchain_perplexity import PerplexitySearchResults


# Initialize the language model
model = init_chat_model(model="gpt-5.5", temperature=0)

# Initialize the Perplexity search tool
perplexity_search = PerplexitySearchResults(
    max_results=5,
    search_recency_filter="month",
)

# Create the agent
agent = create_agent(model, [perplexity_search])

# Run the agent
user_input = "What are the latest developments in quantum computing?"

stream = agent.stream_events(
    {"messages": [{"role": "user", "content": user_input}]},
    version="v3",
)
for snapshot in stream.values:
    snapshot["messages"][-1].pretty_print()
```

***

## API reference

For detailed documentation of the Perplexity Search API and all of its options, see the [Search API reference](https://docs.perplexity.ai/api-reference/search-post) and the [Perplexity API documentation](https://docs.perplexity.ai).

***

<div className="source-links">
  <Callout icon="terminal-2">
    [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
  </Callout>

  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/oss/python/integrations/tools/perplexity_search.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>
</div>