Perplexity ↗

    import chromadb.utils.embedding_functions as embedding_functions

    perplexity_ef = embedding_functions.PerplexityEmbeddingFunction(
        api_key="YOUR_API_KEY",
        model_name="pplx-embed-v1-4b"
    )

    perplexity_ef(input=["document1", "document2"])
    ```
  <span class="tab-end"></span>

  <span class="tab-start" data-tab-title="TypeScript"></span>
```typescript
    // npm install @chroma-core/perplexity

    import { PerplexityEmbeddingFunction } from "@chroma-core/perplexity";

    const embedder = new PerplexityEmbeddingFunction({
        apiKey: "YOUR_API_KEY",
        modelName: "pplx-embed-v1-4b",
    });

    // use directly
    const embeddings = await embedder.generate(["document1", "document2"]);

    // pass documents to query for .add and .query
    const collection = await client.createCollection({
        name: "name",
        embeddingFunction: embedder,
    });
    const collectionGet = await client.getCollection({
        name: "name",
        embeddingFunction: embedder,
    });
    ```
  <span class="tab-end"></span>
<span class="tab-group-end"></span>

## Semantic Search with Chroma

Here's a complete example of using Perplexity embeddings with Chroma for semantic search:

<span class="tab-group-start"></span>
  <span class="tab-start" data-tab-title="Python"></span>
```python
    import chromadb
    import chromadb.utils.embedding_functions as embedding_functions

    # Initialize the embedding function
    perplexity_ef = embedding_functions.PerplexityEmbeddingFunction(
        api_key="YOUR_API_KEY",
        model_name="pplx-embed-v1-4b"
    )

    # Create a Chroma client and collection
    client = chromadb.Client()
    collection = client.create_collection(
        name="my_documents",
        embedding_function=perplexity_ef
    )

    # Add documents
    documents = [
        "Python is a versatile programming language",
        "Machine learning automates analytical model building",
        "The Eiffel Tower is located in Paris, France"
    ]

    collection.add(
        documents=documents,
        ids=["doc1", "doc2", "doc3"]
    )

    # Query for similar documents
    results = collection.query(
        query_texts=["What programming languages are good for data science?"],
        n_results=2
    )

    print("Search results:")
    for doc, distance in zip(results["documents"][0], results["distances"][0]):
        print(f"  {distance:.4f}: {doc}")
    ```
  <span class="tab-end"></span>

  <span class="tab-start" data-tab-title="TypeScript"></span>
```typescript
    import { ChromaClient } from "chromadb";
    import { PerplexityEmbeddingFunction } from "@chroma-core/perplexity";

    // Initialize the embedding function
    const perplexityEf = new PerplexityEmbeddingFunction({
        apiKey: "YOUR_API_KEY",
        modelName: "pplx-embed-v1-4b",
    });

    // Create a Chroma client and collection
    const client = new ChromaClient();
    const collection = await client.createCollection({
        name: "my_documents",
        embeddingFunction: perplexityEf,
    });

    // Add documents
    const documents = [
        "Python is a versatile programming language",
        "Machine learning automates analytical model building",
        "The Eiffel Tower is located in Paris, France",
    ];

    await collection.add({
        documents: documents,
        ids: ["doc1", "doc2", "doc3"],
    });

    // Query for similar documents
    const results = await collection.query({
        queryTexts: ["What programming languages are good for data science?"],
        nResults: 2,
    });

    console.log("Search results:");
    results.documents[0].forEach((doc, i) => {
        console.log(`  ${results.distances[0][i].toFixed(4)}: ${doc}`);
    });
    ```
  <span class="tab-end"></span>
<span class="tab-group-end"></span>

## Available Models

Perplexity offers two embedding models:

| Model                | Dimensions | Context Window | Price             |
| -------------------- | ---------- | -------------- | ----------------- |
| `pplx-embed-v1-0.6b` | 1024       | 32K tokens     | \$0.004/1M tokens |
| `pplx-embed-v1-4b`   | 2560       | 32K tokens     | \$0.03/1M tokens  |

## Matryoshka Dimensions

Both models support [Matryoshka Representation Learning](https://arxiv.org/abs/2205.13147), allowing you to reduce embedding dimensions while maintaining quality. This is useful for reducing storage costs and improving search speed.

<span class="tab-group-start"></span>
  <span class="tab-start" data-tab-title="Python"></span>
```python
    # Reduce dimensions from 2560 to 512 for the 4b model
    perplexity_ef = embedding_functions.PerplexityEmbeddingFunction(
        api_key="YOUR_API_KEY",
        model_name="pplx-embed-v1-4b",
        dimensions=512
    )

    embeddings = perplexity_ef(input=["document1", "document2"])
    print(len(embeddings[0]))  # 512
    ```
  <span class="tab-end"></span>

  <span class="tab-start" data-tab-title="TypeScript"></span>
```typescript
    // Reduce dimensions from 2560 to 512 for the 4b model
    const embedder = new PerplexityEmbeddingFunction({
        apiKey: "YOUR_API_KEY",
        modelName: "pplx-embed-v1-4b",
        dimensions: 512,
    });

    const embeddings = await embedder.generate(["document1", "document2"]);
    console.log(embeddings[0].length);  // 512
    ```
  <span class="tab-end"></span>
<span class="tab-group-end"></span>

Supported dimension ranges:

* `pplx-embed-v1-0.6b`: 128 to 1024
* `pplx-embed-v1-4b`: 128 to 2560

For more details on Perplexity's embedding models, check the [documentation](https://docs.perplexity.ai/docs/embeddings/standard-embeddings).