README.md

metadata

license: apache-2.0
pipeline_tag: feature-extraction
tags:
  - feature-extraction
  - sentence-similarity
  - conteb
  - contextual-embeddings
language:
  - multilingual

pplx-embed-1: Diffusion-LM for Dense and Contextual Retrieval

pplx-embed-1 and pplx-embed-1-context are state-of-the-art text embedding models optimized for real-world, web-scale retrieval tasks.

• Use pplx-embed-1 for independent text embedding (queries, documents, semantic search)
• Use pplx-embed-1-context for document chunks in RAG systems where surrounding context matters

Models

Model	Dimensions	Context	MRL	Quantization	Instruction	Pooling
pplx-embed-1-0.6B	1024	32K	Yes	INT8/BINARY	No	Mean
pplx-embed-1-4B	2560	32K	Yes	INT8/BINARY	No	Mean
pplx-embed-1-context-0.6B	1024	32K	Yes	INT8/BINARY	No	Mean
pplx-embed-1-context-4B	2560	32K	Yes	INT8/BINARY	No	Mean

_{All models are built on diffusion continued pre-trained Qwen3 at Perplexity AI.}

_{Many modern embedding models rely on instruction tuning, where users prepend an instruction string to the text being embedded. This can yield a 2%-3% lift on benchmarks, but it also introduces prompt-selection overhead and can make indexing pipelines brittle (small instruction changes can shift embedding space). We deliberately avoid this requirement: you can embed the text you want to index directly, without having to choose or maintain an instruction prefix.}

Usage

Via API (Contextualized Embeddings)

curl -X POST https://api.perplexity.ai/v1/contextualizedembeddings \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "inputs": [
      [
        "Curiosity begins in childhood with endless questions about the world.",
        "As we grow, curiosity drives us to explore new ideas and challenge assumptions.",
        "Scientific breakthroughs often start with a simple curious question."
      ],
      [
        "The curiosity rover explores Mars, searching for signs of ancient life.",
        "Each discovery on Mars sparks new questions about our place in the universe."
      ]
    ],
    "model": "pplx-embed-1-context-4B"
  }'

Using Transformers

from transformers import AutoModel

model_ctx = AutoModel.from_pretrained(
    "perplexity-ai/pplx-embed-1-context-4B",
    trust_remote_code=True
)

doc_chunks = [
    [
        "Curiosity begins in childhood with endless questions about the world.",
        "As we grow, curiosity drives us to explore new ideas.",
        "Scientific breakthroughs often start with a curious question."
    ],
    [
        "The curiosity rover explores Mars searching for ancient life.",
        "Each discovery on Mars sparks new questions about the universe."
    ]
]
# Returns list of numpy arrays (one per document)
# embeddings[0].shape = (3, 1024), embeddings[1].shape = (2, 1024)
embeddings = model_ctx.encode(doc_chunks)

Technical Details

For comprehensive technical details and evaluation results, see our paper on arXiv.

Contact

• Website: https://perplexity.ai
• API Support: api-support@perplexity.ai