upsert() — langchain Function Reference

Architecture documentation for the upsert() function in in_memory.py from the langchain codebase.

Function python DataProcessing VectorStores

Entity Profile

DataProcessing→ VectorStores→ upsert() — langchain Function Reference

Dependency Diagram

graph TD
  d6b519d2_9c69_7fcd_1cc8_eb8ecb55cc54["upsert()"]
  1d0fbace_6fae_3047_1833_452998c80662["InMemoryDocumentIndex"]
  d6b519d2_9c69_7fcd_1cc8_eb8ecb55cc54 -->|defined in| 1d0fbace_6fae_3047_1833_452998c80662
  style d6b519d2_9c69_7fcd_1cc8_eb8ecb55cc54 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/core/langchain_core/indexing/in_memory.py lines 32–58

    def upsert(self, items: Sequence[Document], /, **kwargs: Any) -> UpsertResponse:
        """Upsert documents into the index.

        Args:
            items: Sequence of documents to add to the index.
            **kwargs: Additional keyword arguments.

        Returns:
            A response object that contains the list of IDs that were
            successfully added or updated in the index and the list of IDs that
            failed to be added or updated.
        """
        ok_ids = []

        for item in items:
            if item.id is None:
                id_ = str(uuid.uuid4())
                item_ = item.model_copy()
                item_.id = id_
            else:
                item_ = item
                id_ = item.id

            self.store[id_] = item_
            ok_ids.append(cast("str", item_.id))

        return UpsertResponse(succeeded=ok_ids, failed=[])