Embeddings

Batch embedding values with OpenAI, Google Gemini, and Mistral.

Embeddings are supported through OpenAI, Google Gemini, and Mistral.

Submit embeddings

from batchwork import BatchEmbeddingRequest, Batchwork

requests = [
    BatchEmbeddingRequest(custom_id="doc-1", value="First document"),
    BatchEmbeddingRequest(custom_id="doc-2", value="Second document"),
]

async with Batchwork() as client:
    job = await client.batch_embeddings(
        model="openai/text-embedding-3-small",
        requests=requests,
    )
    await job.wait(timeout=3600)
    vectors = {
        result.custom_id: result.embedding
        for result in await job.collect()
        if result.status == "succeeded"
    }

Each request contains one value. Results expose the vector through result.embedding.

Provider coverage

Provider	Submission	Results	Notes
OpenAI	JSONL file through `/v1/embeddings`	Output/error JSONL files	Supports dimensions through OpenAI provider options.
Google	Inline `:asyncBatchEmbedContent` operation	Inline response	Supports output dimensionality, task type, and title.
Mistral	JSONL file and Batch Job	Output/error JSONL files	Embedding provider options are currently ignored.

Anthropic, Groq, Together AI, and xAI raise UnsupportedProviderError before network I/O.

OpenAI dimensions

request = BatchEmbeddingRequest(
    custom_id="doc-1",
    value="Document text",
    provider_options={"openai": {"dimensions": 256}},
)

Google embedding configuration

request = BatchEmbeddingRequest(
    custom_id="search-document",
    value="Document text",
    provider_options={
        "google": {
            "outputDimensionality": 256,
            "taskType": "RETRIEVAL_DOCUMENT",
            "title": "Document title",
        }
    },
)

Batchwork moves these values into Google’s batch-level embedContentConfig where required.

Correlation and failures

Output order is not stable. Join vectors through custom_id and handle item-level errors before storing embeddings.

async for result in job.results():
    if result.status == "succeeded" and result.embedding is not None:
        await vector_store.put(result.custom_id, result.embedding)
    elif result.status == "errored":
        await record_failure(result.custom_id, result.error)

Model IDs in examples are illustrative. Select a current batch-compatible embedding model from the provider’s documentation.