langchain-ai/langgraph · error · ValueError

Embedding configuration is required for vector operations (f

Error message

Embedding configuration is required for vector operations (for semantic search). Please provide an Embeddings when initializing the {self.__class__.__name__}.

What it means

Error "Embedding configuration is required for vector operations (for semantic search). Please provide an Embeddings when initializing the {self.__class__.__name__}." thrown in langchain-ai/langgraph.

Source

Thrown at libs/checkpoint-sqlite/langgraph/store/sqlite/base.py:1343

                        row = key_to_row.get(key)
                        if row:
                            results[idx] = _row_to_item(
                                namespace, row, loader=self._deserializer
                            )
                        else:
                            results[idx] = None

    def _batch_put_ops(
        self,
        put_ops: Sequence[tuple[int, PutOp]],
        cur: sqlite3.Cursor,
    ) -> None:
        queries, embedding_request = self._prepare_batch_PUT_queries(put_ops)
        if embedding_request:
            if self.embeddings is None:
                # Should not get here since the embedding config is required
                # to return an embedding_request above
                raise ValueError(
                    "Embedding configuration is required for vector operations "
                    f"(for semantic search). "
                    f"Please provide an Embeddings when initializing the {self.__class__.__name__}."
                )
            query, txt_params = embedding_request
            # Update the params to replace the raw text with the vectors
            vectors = self.embeddings.embed_documents(
                [param[-1] for param in txt_params]
            )

            # Convert vectors to SQLite-friendly format
            vector_params = []
            for (ns, k, pathname, _), vector in zip(txt_params, vectors, strict=False):
                vector_params.extend(
                    [ns, k, pathname, sqlite_vec.serialize_float32(vector)]
                )

            queries.append((query, vector_params))

View on GitHub (pinned to 38031739e5)

When it happens

Trigger: Thrown at libs/checkpoint-sqlite/langgraph/store/sqlite/base.py:1343 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of langchain-ai/langgraph@38031739e5 (2026-08-26). Data as JSON: /api/errors/9dfea62755b83005. Report an issue: GitHub.