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: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.Retriever
You can use thePerplexitySearchRetriever to fetch web search results from the Perplexity Search API as Document objects in a standard retrieval pipeline.
See a usage example.
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).Embedding models
You can usePerplexityEmbeddings to generate embeddings via the Perplexity Embeddings API.
See a usage example.
Deep Agents CLI
Use Perplexity as a first-class provider in the Deep Agents CLI. Install the CLI with the Perplexity extra: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
| Class | Abstraction | Import path | Description |
|---|---|---|---|
ChatPerplexity | Chat model | from langchain_perplexity import ChatPerplexity | Chat model wrapping the Perplexity API for grounded chat completions. |
PerplexitySearchRetriever | Retriever | from langchain_perplexity import PerplexitySearchRetriever | Retriever that returns Document objects from the Perplexity Search API. |
PerplexitySearchResults | Tool | from langchain_perplexity import PerplexitySearchResults | Tool that returns Perplexity Search API results as a JSON array for agents. |
PerplexityEmbeddings | Embeddings | from langchain_perplexity import PerplexityEmbeddings | Embedding model wrapping the Perplexity Embeddings API. |
Connect these docs to Claude, VSCode, and more via MCP for real-time answers.

