Chroma Cloud Qwen ↗

chroma guide intermediate embeddings models
no

Original Documentation

Documentation Index#

Fetch the complete documentation index at: https://docs.trychroma.com/llms.txt Use this file to discover all available pages before exploring further.

export const Callout = ({title, children}) =>

{title && <p className="block mb-2"><strong>{title}</strong></p>}
{children}

;

Chroma provides a convenient wrapper around Chroma Cloud’s Qwen embedding API. This embedding function runs remotely on Chroma Cloud’s servers, and requires a Chroma API key. You can get an API key by signing up for an account at Chroma Cloud.

This embedding function relies on the httpx python package, which you can install with pip install httpx.

    from chromadb.utils.embedding_functions import ChromaCloudQwenEmbeddingFunction, ChromaCloudQwenEmbeddingModel
    import os

    os.environ["CHROMA_API_KEY"] = "YOUR_API_KEY"
    qwen_ef = ChromaCloudQwenEmbeddingFunction(
        model=ChromaCloudQwenEmbeddingModel.QWEN3_EMBEDDING_0p6B,
        task="nl_to_code"
    )

    texts = ["Hello, world!", "How are you?"]
    embeddings = qwen_ef(texts)
    ```

You must pass in a `model` argument and `task` argument. The `task` parameter specifies the task for which embeddings are being generated. You can optionally provide custom `instructions` for both documents and queries.
  <span class="tab-end"></span>

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

    import { ChromaCloudQwenEmbeddingFunction, ChromaCloudQwenEmbeddingModel } from "@chroma-core/chroma-cloud-qwen";

    const embedder = new ChromaCloudQwenEmbeddingFunction({
      apiKeyEnvVar: "CHROMA_API_KEY", // Or set CHROMA_API_KEY env var
      model: ChromaCloudQwenEmbeddingModel.QWEN3_EMBEDDING_0p6B,
      task: "nl_to_code",
    });

    // 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,
    });
    ```
  <span class="tab-end"></span>
<span class="tab-group-end"></span>

<span class="callout-start" data-callout-type="note"></span>
  Visit Chroma Cloud [documentation](/) for more information on available models and configuration.
<span class="callout-end"></span>
Link last verified June 7, 2026. View original ↗
Source: Chroma Docs
Link last verified: 2026-03-04