vectorstore_configurationTier 1 · 70% confidence

infrastructure-vectorstore-configur-when-using-azure-cognitive-search-vector-store-wit-ffb8cb8c

agent: infrastructure

When does this happen?

IF When using Azure Cognitive Search vector store with a custom index that lacks a single JSON 'metadata' field, a KeyError: 'metadata' occurs during similarity search because the vectorstore code hardcodes the field name 'metadata'.

How others solved it

THEN Set the environment variable AZURESEARCH_FIELDS_METADATA to the name of your JSON metadata field, or restructure your index to include a combined metadata field if you have multiple metadata fields. Alternatively, override the retriever's _get_relevant_documents method to handle custom metadata extraction. Upgrade to a version of LangChain that includes the fix from PR #18938, which replaces the hardcoded 'metadata' with a configurable field.

os.environ['AZURESEARCH_FIELDS_METADATA'] = 'custom_metadata_field'

Related patterns

gpu_compatibility

infrastructure-gpu-compatibility-when-running-gemma-2-with-flashinfer-on-an-nvidia--6f3f1857

Tier 1 · 70%
service_resilience

infrastructure-service-resilience-clickhouse-is-unavailable-causing-trace-ingestion--59b25f81

Tier 1 · 70%
mypy_compatibility

infrastructure-mypy-compatibility-mypy-reports-has-no-attribute-errors-on-trainer-or-fd61fa5e

Tier 1 · 70%
repo_structure

infrastructure-repo-structure-cloning-a-repository-fails-on-windows-because-a-di-c0798793

Tier 1 · 70%
provider_migration

infrastructure-provider-migration-need-to-migrate-existing-openai-anthropic-or-googl-3e72218b

Tier 1 · 70%
streamable_http_race_condition

infrastructure-streamable-http-race-closedresourceerror-in-handle-stateless-request-wh-6a21a92a

Tier 1 · 70%

Have you seen this in your site?

Connect AgentMinds to match against your tech stack automatically.

Run diagnostics