Pydantic Validation Error when loading an AmazonTextractPDF from an S3

[ElReyZero]

Checked other resources

• I added a very descriptive title to this issue.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.
• I am sure that this is a bug in LangChain rather than my code.
• The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).

Example Code

The following code causes the exception:

import boto3
from langchain_community.document_loaders import AmazonTextractPDFLoader

session = boto3.Session()
client = session.client('textract', region_name='us-east-1')
s3_path = f"s3://{bucket}/{file_name}"
loader = AmazonTextractPDFLoader(s3_path, client=client)
pdf_pages = loader.load()

Error Message and Stack Trace (if applicable)

1 validation error for Blob
Traceback (most recent call last):
File "/home/lumu/Documents/Projects/trv/Document-Processing-Backend/modules/process_document.py", line 96, in process_document
doc_list, doc_texts = load_files_ensemble(document.doc_name)
File "/home/lumu/Documents/Projects/trv/Document-Processing-Backend/modules/ocr/textract/ensemble.py", line 83, in load_files_ensemble
return load_and_split(file_name)
File "/home/lumu/Documents/Projects/trv/Document-Processing-Backend/modules/ocr/textract/ensemble.py", line 32, in load_and_split
pdf_pages = loader.load()
File "/home/lumu/.local/lib/python3.10/site-packages/langchain_community/document_loaders/pdf.py", line 747, in load
return list(self.lazy_load())
File "/home/lumu/.local/lib/python3.10/site-packages/langchain_community/document_loaders/pdf.py", line 758, in lazy_load
blob = Blob(path=self.web_path) # type: ignore[call-arg] # type: ignore[misc]
File "/home/lumu/.local/lib/python3.10/site-packages/langchain_core/load/serializable.py", line 112, in init
super().init(*args, **kwargs)
File "/home/lumu/.local/lib/python3.10/site-packages/pydantic/main.py", line 212, in init
validated_self = self.pydantic_validator.validate_python(data, self_instance=self)
pydantic_core._pydantic_core.ValidationError: 1 validation error for Blob
data
Field required [type=missing, input_value={'path': 's3://realviewde...77_Walter_Hardwick.pdf'}, input_type=dict]
For further information visit https://errors.pydantic.dev/2.9/v/missing

Description

I'm trying to load a document with the textract pdf loader, however there is a bug and doesn't let it load. I've already checked and the document is on the S3, the error is caused due to a failure with pydantic and not due to a not found document error.

System Info

System Information

OS: Linux
OS Version: #41~22.04.2-Ubuntu SMP PREEMPT_DYNAMIC Mon Jun 3 11:32:55 UTC 2
Python Version: 3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]

Package Information

langchain_core: 0.3.0
langchain: 0.3.0
langchain_community: 0.3.0
langsmith: 0.1.125
langchain_cohere: 0.3.0
langchain_experimental: 0.3.0
langchain_google_genai: 1.0.8
langchain_google_vertexai: 2.0.1
langchain_openai: 0.2.0
langchain_postgres: 0.0.9
langchain_text_splitters: 0.3.0

Optional packages not installed

langgraph
langserve

Other Dependencies

aiohttp: 3.9.5
anthropic[vertexai]: Installed. No version info available.
async-timeout: 4.0.3
cohere: 5.6.2
dataclasses-json: 0.6.3
google-cloud-aiplatform: 1.67.1
google-cloud-storage: 2.18.2
google-generativeai: 0.7.2
httpx: 0.27.0
httpx-sse: 0.4.0
jsonpatch: 1.33
langchain-mistralai: Installed. No version info available.
numpy: 1.26.4
openai: 1.47.1
orjson: 3.10.6
packaging: 23.2
pandas: 2.1.4
pgvector: 0.2.5
pillow: 10.2.0
psycopg: 3.2.1
psycopg-pool: 3.2.2
pydantic: 2.9.2
pydantic-settings: 2.5.2
PyYAML: 5.4.1
requests: 2.31.0
sqlalchemy: 2.0.12
SQLAlchemy: 2.0.12
tabulate: 0.9.0
tenacity: 8.2.3
tiktoken: 0.7.0
typing-extensions: 4.12.2