Add Perplexity embedding models

[CaioSBC]

Checked other resources

• This is a feature request, not a bug report or usage question.
• I added a clear and descriptive title that summarizes the feature request.
• I used the GitHub search to find a similar feature request and didn't find it.
• I checked the LangChain documentation and API reference to see if this feature already exists.
• This is not related to the langchain-community package.

Package (Required)

• langchain
• langchain-openai
• langchain-anthropic
• langchain-classic
• langchain-core
• langchain-model-profiles
• langchain-tests
• langchain-text-splitters
• langchain-chroma
• langchain-deepseek
• langchain-exa
• langchain-fireworks
• langchain-groq
• langchain-huggingface
• langchain-mistralai
• langchain-nomic
• langchain-ollama
• langchain-openrouter
• langchain-perplexity
• langchain-qdrant
• langchain-xai
• Other / not sure / general

Feature Description

I am proposing native support for Perplexity embedding models within the langchain-perplexity module. This integration would enable users to build end-to-end RAG agents exclusively powered by Perplexity services.

Use Case

Currently, developers must manually implement a PerplexityEmbeddings class to build a RAG agent using Perplexity services. Integrating this feature directly into LangChain would significantly streamline the process.

Proposed Solution

A PerplexityEmbeddings class can be implemented within langchain_perplexity.embeddings, mirroring the standard structure of other LangChain embeddings. This implementation leverages the perplexityai SDK to handle service interactions.

Alternatives Considered

No response

Additional Context

No response

[sohail22dec]

Hey team! I would love to take ownership of this feature.

I am already deeply familiar with LangChain's base Embeddings architecture and the exact requirements for implementing both the sync (embed_documents) and async (aembed_documents) methods.

I have a Perplexity API key ready for active testing and can build out a clean PerplexityEmbeddings class within langchain-perplexity that seamlessly mirrors your standard integration patterns.

Could you assign this issue to me so I can start drafting the PR?