Perplexity integrations

Perplexity is the most powerful way to search the internet with unlimited Pro Search, upgraded AI models, unlimited file upload, image generation, and API credits.

You can check a list of available models.

Installation and setup

Install the Perplexity x LangChain integration package:

pip install langchain-perplexity

uv add langchain-perplexity

Get your API key from the Perplexity API key dashboard and set it as the PERPLEXITY_API_KEY (or PPLX_API_KEY) environment variable. See the Perplexity getting started guide for more details.

Chat models

See a variety of Perplexity usage examples.

from langchain_perplexity import ChatPerplexity

ChatPerplexity can also target the Perplexity Agent API by passing use_responses_api=True (or by passing tools=[{"type": "web_search"}], which auto-enables it). See Agent API support on the chat page for details and examples.

Retriever

You can use the PerplexitySearchRetriever to fetch web search results from the Perplexity Search API as Document objects in a standard retrieval pipeline.

See a usage example.

from langchain_perplexity import PerplexitySearchRetriever

Tools

You can use Perplexity as an agent tool to give your agent access to the Perplexity Search API.

See a usage example.

PerplexitySearchResults

A tool that queries the Perplexity Search API and returns a JSON array of results (title, URL, snippet, date, last updated).

from langchain_perplexity import PerplexitySearchResults

Embedding models

You can use PerplexityEmbeddings to generate embeddings via the Perplexity Embeddings API.

See a usage example.

from langchain_perplexity import PerplexityEmbeddings

Deep Agents Code

Use Perplexity as a first-class provider in Deep Agents Code.

Install Deep Agents Code with the Perplexity extra:

uv tool install 'deepagents-code[perplexity]'

Then set PERPLEXITY_API_KEY and reference Perplexity models with the perplexity: prefix (e.g. perplexity:sonar-pro) in the interactive /model switcher or your config.

Components reference