> ## 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.

# PerplexityEmbeddings integration

> Integrate with Perplexity's embedding models using LangChain Python.

This will help you get started with Perplexity embedding models using LangChain. For detailed documentation on `PerplexityEmbeddings` features and configuration options, please refer to the [API reference](https://reference.langchain.com/python/langchain-perplexity/embeddings/PerplexityEmbeddings).

## Overview

### Integration details

| Class                                                                                                                 | Package                                                                                                  | Local | Py support |                                           Package downloads                                           |                                           Package latest                                           |
| :-------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------- | :---: | :--------: | :---------------------------------------------------------------------------------------------------: | :------------------------------------------------------------------------------------------------: |
| [`PerplexityEmbeddings`](https://reference.langchain.com/python/langchain-perplexity/embeddings/PerplexityEmbeddings) | [`langchain-perplexity`](https://github.com/langchain-ai/langchain/tree/master/libs/partners/perplexity) |   ❌   |      ✅     | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-perplexity?style=flat-square\&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-perplexity?style=flat-square\&label=%20) |

## Setup

To access Perplexity embedding models you'll need to create a Perplexity account, get an API key, and install the `langchain-perplexity` integration package.

### Credentials

Head to [https://www.perplexity.ai/account/api/keys](https://www.perplexity.ai/account/api/keys) to sign up for the Perplexity API and generate an API key. Once you've done this, set the `PPLX_API_KEY` (or `PERPLEXITY_API_KEY`) environment variable:

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

if not os.getenv("PPLX_API_KEY"):
    os.environ["PPLX_API_KEY"] = getpass.getpass("Enter your Perplexity API key: ")
```

To enable automated tracing of your model calls, set your [LangSmith](/langsmith/observability) API key:

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
os.environ["LANGSMITH_TRACING"] = "true"
os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")
```

### Installation

The LangChain Perplexity integration lives in the `langchain-perplexity` package:

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

## Instantiation

Now we can instantiate our embedding model object and generate embeddings:

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

embeddings = PerplexityEmbeddings(
    model="pplx-embed-v1-4b",
    # api_key="...",       # if you prefer to pass the key explicitly
    # request_timeout=60,
    # max_retries=6,
)
```

Available models include `pplx-embed-v1-4b` (default) and `pplx-embed-v1-0.6b`. See the [Perplexity Embeddings API reference](https://docs.perplexity.ai/api-reference/embeddings-post) for the current list and dimensions.

## Indexing and retrieval

Embedding models are often used in retrieval-augmented generation (RAG) flows, both as part of indexing data as well as later retrieving it. For more detailed instructions, please see our [RAG tutorials](/oss/python/langchain/rag).

Below, see how to index and retrieve data using the `embeddings` object we initialized above. In this example, we will index and retrieve a sample document in the `InMemoryVectorStore`.

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
# Create a vector store with a sample text
from langchain_core.vectorstores import InMemoryVectorStore

text = "LangChain is the framework for building context-aware reasoning applications"

vectorstore = InMemoryVectorStore.from_texts(
    [text],
    embedding=embeddings,
)

# Use the vectorstore as a retriever
retriever = vectorstore.as_retriever()

# Retrieve the most similar text
retrieved_documents = retriever.invoke("What is LangChain?")

# show the retrieved document's content
retrieved_documents[0].page_content
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
'LangChain is the framework for building context-aware reasoning applications'
```

## Direct usage

Under the hood, the vectorstore and retriever implementations are calling `embeddings.embed_documents(...)` and `embeddings.embed_query(...)` to create embeddings for the text(s) used in `from_texts` and retrieval `invoke` operations, respectively.

You can directly call these methods to get embeddings for your own use cases.

### Embed single texts

You can embed single texts or documents with `embed_query`:

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
single_vector = embeddings.embed_query(text)
print(str(single_vector)[:100])  # Show the first 100 characters of the vector
```

### Embed multiple texts

You can embed multiple texts with `embed_documents`:

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
text2 = (
    "LangGraph is a library for building stateful, multi-actor applications with LLMs"
)
two_vectors = embeddings.embed_documents([text, text2])
for vector in two_vectors:
    print(str(vector)[:100])  # Show the first 100 characters of the vector
```

### Async usage

`PerplexityEmbeddings` also exposes async methods:

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
single_vector = await embeddings.aembed_query(text)
two_vectors = await embeddings.aembed_documents([text, text2])
```

<Note>
  Perplexity returns base64-encoded signed int8 embeddings. `PerplexityEmbeddings` decodes these into `list[float]` values in the range `[-128, 127]`. The magnitude is preserved from the API's quantized output; cosine similarity is unaffected by the lack of unit-length normalization.
</Note>

***

## API reference

For detailed documentation on `PerplexityEmbeddings` features and configuration options, please refer to the [API reference](https://reference.langchain.com/python/langchain-perplexity/embeddings/PerplexityEmbeddings) and the [Perplexity Embeddings API documentation](https://docs.perplexity.ai/api-reference/embeddings-post).

***

<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/embeddings/perplexity.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>
</div>