MemPalace/mempalace · error · ValueError

pgvector requires explicit embeddings

Error message

pgvector requires explicit embeddings

What it means

Error "pgvector requires explicit embeddings" thrown in MemPalace/mempalace.

Source

Thrown at mempalace/backends/pgvector.py:965

        _validate_where(where)
        _validate_where(where_document)
        pushdown = None if _requires_local_filter(where, where_document) else where
        rows = self._scroll(where=pushdown, with_embedding=with_embedding)
        id_set = set(ids) if ids is not None else None
        return [
            row
            for row in rows
            if (id_set is None or row["id"] in id_set)
            and _matches_where(row["metadata"], where)
            and _matches_where_document(row["document"], where_document)
        ]

    def add(self, *, documents, ids, metadatas=None, embeddings=None):
        _validate_write_batch(
            documents=documents, ids=ids, metadatas=metadatas, embeddings=embeddings
        )
        if embeddings is None:
            raise ValueError("pgvector requires explicit embeddings")
        if len(set(ids)) != len(ids):
            raise ValueError("add ids must be unique")
        existing = self.get(ids=list(ids), include=[])
        if existing.ids:
            raise ValueError(f"ids already exist in pgvector collection: {existing.ids}")
        self.upsert(documents=documents, ids=ids, metadatas=metadatas, embeddings=embeddings)

    def upsert(self, *, documents, ids, metadatas=None, embeddings=None):
        _validate_write_batch(
            documents=documents, ids=ids, metadatas=metadatas, embeddings=embeddings
        )
        if embeddings is None:
            raise ValueError("pgvector requires explicit embeddings")
        vectors, dimension = _normalize_vectors(embeddings)
        self._ensure_table(dimension)
        metadatas = metadatas or [{} for _ in ids]
        rows = [
            {

View on GitHub (pinned to 06cb6987f0)

Solutions

1. Compute embeddings explicitly and pass them to add/upsert; pgvector does not embed for you

When it happens

Trigger: Thrown at mempalace/backends/pgvector.py:965 when the library encounters an invalid state.

Common situations: Caller relied on server-side embedding the pgvector backend does not provide.

AI-assisted analysis of MemPalace/mempalace@06cb6987f0 (2026-08-15). Data as JSON: /api/errors/2b649e6c9a1ff293. Report an issue: GitHub.