chroma-core/chroma · error · ValueError

Invalid task: {self.task}

Error message

Invalid task: {self.task}

What it means

The task attribute routes __call__ to model.embed (task='document') or model.query_embed (task='query'); every other value falls through to this ValueError after the per-call fastembed import. The comparison is exact and case-sensitive - 'documents', 'Document', or None all fail (the constructor default is 'document').

Source

Thrown at chromadb/utils/embedding_functions/fastembed_sparse_embedding_function.py:97

            Embeddings for the documents.
        """
        try:
            from fastembed import SparseTextEmbedding
        except ImportError:
            raise ValueError(
                "The fastembed python package is not installed. Please install it with `pip install fastembed`"
            )
        model = cast(SparseTextEmbedding, self._model)
        if self.task == "document":
            embeddings = model.embed(
                list(input),
            )
        elif self.task == "query":
            embeddings = model.query_embed(
                list(input),
            )
        else:
            raise ValueError(f"Invalid task: {self.task}")

        sparse_vectors: SparseVectors = []

        for vec in embeddings:
            sparse_vectors.append(
                normalize_sparse_vector(
                    indices=vec.indices.tolist(), values=vec.values.tolist()
                )
            )

        return sparse_vectors

    def embed_query(self, input: Documents) -> SparseVectors:
        try:
            from fastembed import SparseTextEmbedding
        except ImportError:
            raise ValueError(
                "The fastembed python package is not installed. Please install it with `pip install fastembed`"

View on GitHub (pinned to aecdd12c8a)

Solutions

1. Use task='document' when embedding corpus documents and task='query' for query-side text.
2. Or call ef.embed_query(texts) directly for queries instead of switching task.
3. If task comes from config or user input, validate it against {'document', 'query'} before constructing.

Example fix

# before
ef = FastembedSparseEmbeddingFunction(model_name='Qdrant/bm25', task='documents')
ef(['hello'])  # ValueError: Invalid task: documents

# after
ef = FastembedSparseEmbeddingFunction(model_name='Qdrant/bm25', task='document')
ef(['hello'])  # for query-side text: ef.embed_query(['hello'])

task = 'document' if mode == 'index' else 'query'
assert task in ('document', 'query'), f'invalid task: {task}'

def is_valid_task(task) -> bool:
    return task in ('document', 'query')

When it happens

Trigger: Constructing FastembedSparseEmbeddingFunction(..., task='documents'), task='Document', task=None, or any value outside {'document', 'query'} and then calling ef(texts).

Common situations: Typos and plurals from hand-written config; task sourced from YAML/user input without validation; assuming None selects a default (it does not at call time).

Related errors

• The fastembed python package is not installed. Please instal
• Invalid task: {task}
• Embedding function provided when already defined in the coll
• Embedding function name not found in config: {ef_config}
• Embedding function {ef_name} not found. Add @register_embedd

AI-assisted analysis of chroma-core/chroma@aecdd12c8a (2026-08-16). Data as JSON: /api/errors/e21d6550ca1771e8. Report an issue: GitHub.