apache/beam · error · ValueError

Item {embeddable_item.id} missing both text content and spar

Error message

Item {embeddable_item.id} missing both text content and sparse embedding required for keyword search

What it means

For keyword (or hybrid) search, _get_keyword_search_data requires each EmbeddableItem to supply at least one query input: text content or a sparse embedding. If both are absent, Milvus has nothing to search with and the enricher raises this ValueError naming the item id.

Source

Thrown at sdks/python/apache_beam/ml/rag/enrichment/milvus_search.py:498

        param=self.search_strategy.keyword.search_params,
        limit=self.search_strategy.keyword.limit,
        expr=self.search_strategy.keyword.filter)

    reqs = [vector_search_req, keyword_search_req]
    return reqs

  def _get_vector_search_data(self, embeddable_item: EmbeddableItem):
    if not embeddable_item.dense_embedding:
      raise ValueError(
          f"Item {embeddable_item.id} missing dense embedding required for"
          " vector search")
    return embeddable_item.dense_embedding

  def _get_keyword_search_data(self, embeddable_item: EmbeddableItem):
    has_no_text = not embeddable_item.content.text
    has_no_sparse = not embeddable_item.sparse_embedding
    if has_no_text and has_no_sparse:
      raise ValueError(
          f"Item {embeddable_item.id} missing both text content and sparse "
          "embedding required for keyword search")
    sparse_embedding = MilvusHelpers.sparse_embedding(
        embeddable_item.sparse_embedding)
    return embeddable_item.content.text or sparse_embedding

  def _get_call_response(
      self,
      embeddable_items: list[EmbeddableItem],
      search_result: SearchResult[Hits]):
    response = []
    for i in range(len(embeddable_items)):
      embeddable_item = embeddable_items[i]
      hits: Hits = search_result[i]
      result = MilvusSearchResult()
      for j in range(len(hits)):
        hit: Hit = hits[j]
        normalized_fields = self._normalize_milvus_fields(hit.fields)

View on GitHub (pinned to 12126d8942)

Solutions

1. Populate item.content.text (or the sparse embedding) before enrichment
2. Add sparse embedding generation to the pipeline when using keyword/hybrid search
3. Filter out empty-content items before the enricher

Example fix

// before
item = EmbeddableItem(id='1', content=Content(text=''))  # no sparse either
// after
item = EmbeddableItem(id='1', content=Content(text='chunk body'))
# or provide item.embedding.sparse_embedding via a sparse embedder

bad = [it.id for it in items if not it.content.text and not it.sparse_embedding]
assert not bad, f'items missing text and sparse embedding: {bad}'

def keyword_searchable(item) -> bool:
    return bool(item.content.text) or bool(item.sparse_embedding)

try:
    enriched = enricher(items)
except ValueError as e:
    if 'missing both text content and sparse' in str(e): fallback_to_vector_search(items)
    else: raise

When it happens

Trigger: An EmbeddableItem with empty content.text and empty/None sparse_embedding flows through MilvusEnricher configured with KeywordSearchStrategy or HybridSearchStrategy.

Common situations: Documents with empty bodies ingested from a sparse source; sparse embedding step omitted in the pipeline; hybrid search where only dense embeddings were generated and text was cleared after chunking.

Understand the failure class

Background: "missing required argument" and "the following required arguments were not provided": what required-argument errors mean and how to fix them — this error's family across 20 libraries.

Related errors

• Item {embeddable_item.id} missing dense embedding required f
• Search strategy must be provided
• Not supported search strategy yet: {self.search_strategy}
• EmbeddableItem must contain dense embedding
• Subclasses must implement get_splitter_transform

AI-assisted analysis of apache/beam@12126d8942 (2026-09-13). Data as JSON: /api/errors/658be9cd70483fe8. Report an issue: GitHub.