microsoft/semantic-kernel · error · ServiceResponseException

Remove failed due to

Error message

Remove failed due to: {e}

What it means

Raised as a ServiceResponseException in MilvusMemoryStore.remove_batch when .load(), .delete(), or .flush() throws any Exception during record deletion. The original exception is chained and its message interpolated, exposing the underlying Milvus SDK error.

Solutions

1. Read the interpolated {e} to find the root cause.
2. Ensure keys form a valid Milvus 'in' expression.
3. Retry on transient connection/server errors with backoff.
4. Check Milvus server logs and query-node health.

Example fix

// before
await store.remove_batch('docs', keys)  # ServiceResponseException: Remove failed due to: ...
// after
try:
    await store.remove_batch('docs', keys)
except ServiceResponseException as e:
    logging.error('Milvus remove failed: %s', e)
    raise

def valid_milvus_keys(keys: list[str]) -> bool:
    return bool(keys) and all(isinstance(k, str) and k for k in keys)

if not valid_milvus_keys(keys):
    raise ValueError('Invalid keys for Milvus delete expression')

from semantic_kernel.exceptions import ServiceResponseException

try:
    await store.remove_batch('docs', keys)
except ServiceResponseException as e:
    logging.error('Milvus remove failed: %s', e)
    raise

When it happens

Trigger: Milvus delete fails due to connection errors, an invalid delete expression (built as expr=f'{SEARCH_FIELD_ID} in {keys}'), server-side issues, or flush timeouts.

Common situations: Network interruption during delete/flush. Malformed keys list producing an invalid expression. Milvus query node under memory pressure during load(). SDK/server version mismatch.

Related errors

• Get failed due to
• Search failed
• Upsert failed due to
• Collection does not exist, cannot remove.
• Failed to remove all keys

AI-assisted analysis of microsoft/semantic-kernel@c028a0c7dc (2026-08-13). Data as JSON: /api/errors/83999b32d96fccbe. Report an issue: GitHub.

Appendix: source

Thrown at python/semantic_kernel/connectors/memory_stores/milvus/milvus_memory_store.py:377

            collection_name (str): Collection to remove from
            keys (List[str]): The list of keys.

        Raises:
            Exception: Collection doesnt exist.
            e: Failure to remove key.
        """
        if collection_name not in utility.list_collections():
            logger.debug(f"Collection {collection_name} does not exist, cannot remove.")
            raise ServiceResourceNotFoundError(f"Collection {collection_name} does not exist, cannot remove.")
        try:
            self.collections[collection_name].load()
            result = self.collections[collection_name].delete(
                expr=f"{SEARCH_FIELD_ID} in {keys}",
            )
            self.collections[collection_name].flush()
        except Exception as e:
            logger.debug(f"Remove failed due to: {e}")
            raise ServiceResponseException(f"Remove failed due to: {e}") from e
        if result.delete_count != len(keys):
            logger.debug(f"Failed to remove all keys, {result.delete_count} removed out of {len(keys)}")
            raise ServiceResponseException(
                f"Failed to remove all keys, {result.delete_count} removed out of {len(keys)}"
            )

    async def get_nearest_matches(
        self,
        collection_name: str,
        embedding: ndarray,
        limit: int,
        min_relevance_score: float = 0.0,
        with_embeddings: bool = False,
    ) -> list[tuple[MemoryRecord, float]]:
        """Find the nearest `limit` matches for an embedding.

        Args:
            collection_name (str): The collection to search.

View on GitHub (pinned to c028a0c7dc)