PerplexityDocumentEmbedder

Compute document embeddings using Perplexity AI embedding models. Use this component in indexing pipelines to embed documents before writing them to a document store.

Key Features

• Uses Perplexity AI embedding models to produce dense vector representations of documents.
• Stores the computed embedding in each document's embedding field, making documents ready for semantic search and retrieval.
• Supports two quantized encoding formats: base64_int8 (default) and base64_binary for efficient storage and retrieval.
• Configurable batch size and progress bar for large document sets.
• Supports embedding additional metadata fields alongside document content.
• Compatible with Perplexity's pplx-embed-v1-0.6b and pplx-embed-v1-4b models.

Embedding Models in Pipelines and Indexes

The embedding model you use to embed documents in your index must be the same as the embedding model you use to embed the query in your pipeline.

This means the embedders for your indexes and pipelines must match. For example, if you use CohereDocumentEmbedder to embed your documents, you should use CohereTextEmbedder with the same model to embed your queries.

Configuration

1. Drag the PerplexityDocumentEmbedder component onto the canvas from the Component Library.
2. Click on the component to open the configuration panel.
3. On the General tab:
   1. Create a secret with your Perplexity API key. Use PERPLEXITY_API_KEY as the secret key. For instructions, see Create Secrets. Get your API key from Perplexity AI.
   2. Select the embedding model to use. Available models are listed in the Perplexity Embeddings API reference.
4. Go to the Advanced tab to configure encoding_format, batch_size, meta_fields_to_embed, and timeout.

Connections

PerplexityDocumentEmbedder receives a list of documents through its documents input. It outputs the same documents with their embeddings added through its documents output.

Connect it after converters (such as TextFileToDocument or HTMLToDocument) or after DocumentSplitter to embed chunks. Connect its documents output to DocumentWriter to store embedded documents in a document store.

Source Code

To check this component's source code, open document_embedder.py in the Haystack Core Integrations repository.

Usage Examples

Basic Configuration

  PerplexityDocumentEmbedder:
    type: haystack_integrations.components.embedders.perplexity.document_embedder.PerplexityDocumentEmbedder
    init_parameters:
      api_key:
        type: env_var
        env_vars:
        - PERPLEXITY_API_KEY
        strict: false
      model: pplx-embed-v1-0.6b
      api_base_url: https://api.perplexity.ai/v1
      encoding_format: base64_int8
      batch_size: 32
      progress_bar: true
      embedding_separator: "\n"

Using the Component in a Pipeline

This example shows an indexing pipeline that reads text files, splits them into chunks, embeds them using Perplexity, and writes them to an OpenSearch document store.

# haystack-pipeline
components:
  TextFileToDocument:
    type: haystack.components.converters.txt.TextFileToDocument
    init_parameters:
      encoding: utf-8
      store_full_path: false
  DocumentSplitter:
    type: haystack.components.preprocessors.document_splitter.DocumentSplitter
    init_parameters:
      split_by: sentence
      split_length: 100
      split_overlap: 0
      split_threshold: 0
      splitting_function:
  PerplexityDocumentEmbedder:
    type: haystack_integrations.components.embedders.perplexity.document_embedder.PerplexityDocumentEmbedder
    init_parameters:
      api_key:
        type: env_var
        env_vars:
        - PERPLEXITY_API_KEY
        strict: false
      model: pplx-embed-v1-0.6b
      api_base_url: https://api.perplexity.ai/v1
      encoding_format: base64_int8
      batch_size: 32
      progress_bar: true
      meta_fields_to_embed:
      embedding_separator: "\n"
  DocumentWriter:
    type: haystack.components.writers.document_writer.DocumentWriter
    init_parameters:
      policy: OVERWRITE
      document_store:
        type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
        init_parameters:
          hosts:
          index: Standard-Index-English
          max_chunk_bytes: 104857600
          embedding_dim: 768
          return_embedding: false
          method:
          mappings:
          settings:
          create_index: true
          http_auth:
          use_ssl:
          verify_certs:
          timeout:

connections:
- sender: TextFileToDocument.documents
  receiver: DocumentSplitter.documents
- sender: DocumentSplitter.documents
  receiver: PerplexityDocumentEmbedder.documents
- sender: PerplexityDocumentEmbedder.documents
  receiver: DocumentWriter.documents

max_runs_per_component: 100

metadata: {}

inputs:
  files:
  - TextFileToDocument.sources

Parameters

Inputs

Parameter	Type	Description
documents	List[Document]	A list of Documents to embed.

Outputs

Parameter	Type	Description
documents	List[Document]	Documents with their embedding field populated.
meta	Dict[str, Any]	Metadata about the embedding request, including model name and usage statistics.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
api_key	Secret	Secret.from_env_var('PERPLEXITY_API_KEY')	The Perplexity API key.
model	str	pplx-embed-v1-0.6b	The Perplexity embedding model to use. See Perplexity Embeddings API reference for available models.
api_base_url	Optional[str]	https://api.perplexity.ai/v1	The Perplexity API base URL.
prefix	str	""	A string to add to the beginning of each text.
suffix	str	""	A string to add to the end of each text.
batch_size	int	32	Number of Documents to encode at once.
progress_bar	bool	True	Whether to show a progress bar. Disable in production to keep logs clean.
meta_fields_to_embed	Optional[List[str]]	None	Metadata fields to embed alongside the Document text.
embedding_separator	str	\n	Separator used to concatenate metadata fields and Document text.
encoding_format	str	base64_int8	The embedding encoding format. Supported values: base64_int8 and base64_binary.
timeout	Optional[float]	None	Timeout for API calls in seconds. Defaults to the OPENAI_TIMEOUT environment variable or 30 seconds.
max_retries	Optional[int]	None	Maximum number of retries after an internal error. Defaults to the OPENAI_MAX_RETRIES environment variable or 5.
http_client_kwargs	Optional[Dict[str, Any]]	None	Keyword arguments for a custom httpx.Client or httpx.AsyncClient.

Run Method Parameters

These are the parameters you can configure for the component's run() method. This means you can pass these parameters at query time through the API, in Playground, or when running a job. For details, see Modify Pipeline Parameters at Query Time.

Parameter	Type	Description
documents	List[Document]	A list of Documents to embed.

Related Information

• PerplexityTextEmbedder
• Pipeline Components