Perplexity with Haystack

Use Perplexity’s Agent API, Embeddings API, and grounded Search API in Haystack pipelines.

Overview

The perplexity-haystack package provides Haystack components for Perplexity’s Agent API, Embeddings API, and grounded Search API, so you can build retrieval-augmented and agentic pipelines that combine chat, embeddings, and live web search.

Haystack is an open-source Python framework by deepset for building production-ready LLM applications, including RAG pipelines and agentic workflows. Learn more at haystack.deepset.ai.

The integration includes:

• PerplexityChatGenerator — Chat completions through the Agent API (OpenAI-compatible).
• PerplexityTextEmbedder and PerplexityDocumentEmbedder — Embeddings through the Embeddings API.
• PerplexityWebSearch — Ranked, grounded web results through the Search API.

Installation

pip

pip install perplexity-haystack

uv

uv add perplexity-haystack

API Key Setup

Set your Perplexity API key as an environment variable:

import os

os.environ["PERPLEXITY_API_KEY"] = "your_api_key_here"

Get API Key

Generate your API key from the Perplexity dashboard.

Quick Start: Chat (Agent API)

PerplexityChatGenerator is powered by the Perplexity Agent API and defaults to openai/gpt-5.4.

import os

from haystack.dataclasses import ChatMessage
from haystack_integrations.components.generators.perplexity import PerplexityChatGenerator

os.environ["PERPLEXITY_API_KEY"] = "your_api_key_here"

client = PerplexityChatGenerator()
response = client.run(
    messages=[ChatMessage.from_user("What are Agentic Pipelines? Be brief.")]
)

print(response["replies"])

Selecting a Model

You can pick any of the supported Agent API models via the model parameter:

client = PerplexityChatGenerator(model="anthropic/claude-sonnet-4-6")

Supported models include openai/gpt-5.4 (default), openai/gpt-5.5, anthropic/claude-sonnet-4-6, xai/grok-4.5, and google/gemini-3-flash-preview. See the Agent API models page for the full list.

Quick Start: Embeddings

Embed a single query with PerplexityTextEmbedder:

import os

from haystack_integrations.components.embedders.perplexity import PerplexityTextEmbedder

os.environ["PERPLEXITY_API_KEY"] = "your_api_key_here"

embedder = PerplexityTextEmbedder()
response = embedder.run(text="What is Haystack by deepset?")

print(response["embedding"])

Embed a list of documents with PerplexityDocumentEmbedder:

from haystack import Document
from haystack_integrations.components.embedders.perplexity import PerplexityDocumentEmbedder

docs = [Document(content="What is Haystack by deepset?")]
result = PerplexityDocumentEmbedder().run(documents=docs)

print(result["documents"][0].embedding)

Both embedders default to pplx-embed-v1-0.6b. The larger pplx-embed-v1-4b model is also available — set it via the model parameter.

Quick Start: Web Search (Search API)

Use PerplexityWebSearch to get ranked, grounded web results inside a Haystack pipeline:

import os

from haystack.utils import Secret
from haystack_integrations.components.websearch.perplexity import PerplexityWebSearch

os.environ["PERPLEXITY_API_KEY"] = "your_api_key_here"

websearch = PerplexityWebSearch(
    api_key=Secret.from_env_var("PERPLEXITY_API_KEY"),
    top_k=5,
)
result = websearch.run(query="What is Haystack by deepset?")

documents = result["documents"]
links = result["links"]

print(documents)
print(links)

Links & Resources

Haystack Integrations

Catalog entry on haystack.deepset.ai

Source Code

perplexity-haystack on GitHub

PyPI Package

View on PyPI

Haystack Docs

Full Haystack documentation

Support

Need help with the integration?

• Check the Haystack documentation
• Open an issue at haystack-core-integrations
• Review our FAQ