PerplexityTextEmbedder

Embed a query string using Perplexity AI embedding models. Use this component in query pipelines to transform user queries into vectors for embedding-based retrieval.

Key Features

• Uses Perplexity AI embedding models to produce dense vector representations of text.
• Outputs a float vector embedding suitable for use with embedding retrievers.
• Supports two quantized encoding formats: base64_int8 (default) and base64_binary for efficient storage and retrieval.
• Compatible with Perplexity's pplx-embed-v1-0.6b and pplx-embed-v1-4b models.
• The model must match the one used in the corresponding PerplexityDocumentEmbedder in the indexing pipeline.

Configuration

1. Drag the PerplexityTextEmbedder 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 same embedding model you used for indexing. Available models are listed in the Perplexity Embeddings API reference.
4. Go to the Advanced tab to configure encoding_format and timeout.

Connections

PerplexityTextEmbedder receives the user query as a text string through its text input, typically from the Input component. It outputs a float vector through its embedding output, which you connect to an embedding retriever such as OpenSearchEmbeddingRetriever.

Source Code

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

Usage Examples

Basic Configuration

  PerplexityTextEmbedder:
    type: haystack_integrations.components.embedders.perplexity.text_embedder.PerplexityTextEmbedder
    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

Using the Component in a Pipeline

This example shows a query pipeline with PerplexityTextEmbedder that embeds the user query and sends it to OpenSearchEmbeddingRetriever to find matching documents.

# haystack-pipeline
components:
  PerplexityTextEmbedder:
    type: haystack_integrations.components.embedders.perplexity.text_embedder.PerplexityTextEmbedder
    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
      prefix: ""
      suffix: ""
  OpenSearchEmbeddingRetriever:
    type: haystack_integrations.components.retrievers.opensearch.embedding_retriever.OpenSearchEmbeddingRetriever
    init_parameters:
      filters:
      top_k: 10
      filter_policy: replace
      custom_query:
      raise_on_failure: true
      efficient_filtering: true
      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: PerplexityTextEmbedder.embedding
  receiver: OpenSearchEmbeddingRetriever.query_embedding

max_runs_per_component: 100

metadata: {}

inputs:
  query:
  - PerplexityTextEmbedder.text

Parameters

Inputs

Parameter	Type	Description
text	str	The text to embed.

Outputs

Parameter	Type	Description
embedding	List[float]	The embedding of the input text.
meta	Dict[str, Any]	Metadata about the 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 the text.
suffix	str	""	A string to add to the end of the 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
text	str	The text to embed.

Related Information

• PerplexityDocumentEmbedder
• Pipeline Components