MemPalace/mempalace · error · ValueError

qdrant requires query_embeddings; use palace.get_collection

Error message

qdrant requires query_embeddings; use palace.get_collection wrapper

What it means

Raised by QdrantCollection.query() when query_texts is passed. This backend cannot embed text server-side or internally; it accepts only precomputed query_embeddings. The message directs callers to the palace.get_collection wrapper, which embeds query_texts with the configured local model before delegating.

Source

Thrown at mempalace/backends/qdrant.py:956

            ids=outer_ids,
            documents=outer_docs,
            metadatas=outer_metas,
            distances=outer_dists,
            embeddings=outer_embeds if spec.embeddings else None,
        )

    def query(
        self,
        *,
        query_texts=None,
        query_embeddings=None,
        n_results=10,
        where=None,
        where_document=None,
        include=None,
    ) -> QueryResult:
        if query_texts is not None:
            raise ValueError("qdrant requires query_embeddings; use palace.get_collection wrapper")
        if query_embeddings is None:
            raise ValueError("query requires query_embeddings")
        if not query_embeddings:
            raise ValueError("query input must be a non-empty list")
        _validate_where(where)
        _validate_where(where_document)
        if _requires_local_filter(where, where_document):
            return self._query_local_exact(
                query_embeddings=query_embeddings,
                n_results=n_results,
                where=where,
                where_document=where_document,
                include=include,
            )
        if not self._remote_exists():
            if self._marker_exists():
                raise CollectionNotInitializedError(self._collection_name)
            return QueryResult.empty(

View on GitHub (pinned to 06cb6987f0)

Solutions

1. Use the palace wrapper collection (palace.get_collection) which accepts query_texts and embeds them
2. Or embed first: query(query_embeddings=[embedder.embed("hello")])
3. Keep a single search entry point in your code that always goes through the wrapper
4. Confirm the embedder runtime is up so wrapper-based text queries work

Example fix

# before
collection.query(query_texts=["hello"], n_results=5)  # ValueError
// after
res = collection.query(query_embeddings=[embedder.embed("hello")], n_results=5)
# or simply: wrapped = palace.get_collection("notes"); wrapped.query(query_texts=["hello"], n_results=5)

if query_texts is not None:
    query_embeddings = [embedder.embed(t) for t in query_texts]
    query_texts = None

When it happens

Trigger: Calling raw collection.query(query_texts=["hello"], ...) — the natural call shape for Chroma users. Also a search wrapper forwarding user text straight to the backend collection without embedding it first.

Common situations: Porting search code from the default Chroma backend; using a handle from backend.get_collection() rather than palace.get_collection(); a query layer that conditionally passes texts or embeddings but never embeds the texts branch.

Related errors

• qdrant requires explicit embeddings
• query requires query_embeddings
• query input must be a non-empty list
• add ids must be unique
• ids already exist in qdrant collection: {existing.ids}

AI-assisted analysis of MemPalace/mempalace@06cb6987f0 (2026-08-15). Data as JSON: /api/errors/f22df8b8b9637c17. Report an issue: GitHub.