ingest exception: type object '_HashedDocument' has no attribute 'from_document'

[kientv]

Checked other resources

• I added a very descriptive title to this question.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• I commit to help with one of those options 👆

Example Code

from langchain.document_loaders.base import BaseLoader
from langchain_core.indexing.api import (IndexingResult, _batch, _deduplicate_in_order, _get_source_id_assigner, _HashedDocument)
from langchain_community.indexes.base import RecordManager
...
    # Mark when the update started.
    index_start_dt = record_manager.get_time()
    logging.info("Knowledge base update started")
    num_added = 0
    num_skipped = 0
    num_updated = 0
    num_deleted = 0

    for doc_batch in _batch(batch_size, doc_iterator):
        hashed_docs = list(
            _deduplicate_in_order(
                [_HashedDocument.from_document(doc) for doc in doc_batch]
            )
        )

Description

This problem happen after upgrading langchain.

System Info

pip freeze | grep langchain
langchain==0.3.26
langchain-anthropic==0.3.5
langchain-community==0.3.23
langchain-core==0.3.68
langchain-google-genai==2.0.10
langchain-google-vertexai==2.0.21
langchain-openai==0.3.27
langchain-qdrant==0.2.0
langchain-text-splitters==0.3.8

platform: linux
python: 3.11.3

[kientv]

I'm fixed, Use _get_document_with_hash instead of _HashedDocument.from_document