Blob.as_bytes_io() raises NotImplementedError for string data

[chang923]

Checked other resources

• This is a bug, not a usage question.
• I added a clear and descriptive title that summarizes this issue.
• 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).
• This is not related to the langchain-community package.
• I posted a self-contained, minimal, reproducible example. A maintainer can copy it and run it AS IS.

Package (Required)

• langchain
• langchain-openai
• langchain-anthropic
• langchain-classic
• langchain-core
• langchain-model-profiles
• langchain-tests
• langchain-text-splitters
• langchain-chroma
• langchain-deepseek
• langchain-exa
• langchain-fireworks
• langchain-groq
• langchain-huggingface
• langchain-mistralai
• langchain-nomic
• langchain-ollama
• langchain-openrouter
• langchain-perplexity
• langchain-qdrant
• langchain-xai
• Other / not sure / general

Related Issues / PRs

#36666

Reproduction Steps / Example Code (Python)

from langchain_core.documents.base import Blob

blob = Blob.from_data("hello")
with blob.as_bytes_io() as f:
    print(f.read())

Error Message and Stack Trace (if applicable)

NotImplementedError: Unable to convert blob Blob 0x... metadata={} data='hello'

Description

I'm trying to use Blob.as_bytes_io() on a blob created with string data. I expect it to return a byte stream of the string, just like as_bytes() does. Instead, it raises NotImplementedError.

This is an API inconsistency: as_string() and as_bytes() both work with string data, but as_bytes_io() does not.

System Info

System Information

OS: Linux
OS Version: #1 SMP Tue Nov 5 00:21:55 UTC 2024
Python Version: 3.10.20 (main, Mar 11 2026, 17:46:40) [GCC 14.3.0]

Package Information

langchain_core: 1.2.19
langchain: 1.2.13
langchain_community: 0.4.1
langsmith: 0.7.17
langchain_chroma: 1.1.0
langchain_classic: 1.0.3
langchain_deepseek: 1.0.1
langchain_huggingface: 1.2.1
langchain_openai: 1.1.11
langchain_text_splitters: 1.1.1
langgraph_sdk: 0.3.11

Optional packages not installed

deepagents
deepagents-cli

Other Dependencies

aiohttp: 3.13.3
async-timeout: 4.0.3
chromadb: 1.5.5
dataclasses-json: 0.6.7
httpx: 0.28.1
httpx-sse: 0.4.3
huggingface-hub: 1.7.1
jsonpatch: 1.33
langgraph: 1.1.2
numpy: 2.2.6
openai: 2.28.0
opentelemetry-api: 1.40.0
opentelemetry-sdk: 1.40.0
orjson: 3.11.7
packaging: 25.0
pydantic: 2.12.5
pydantic-settings: 2.13.1
pytest: 9.0.3
pyyaml: 6.0.3
PyYAML: 6.0.3
requests: 2.32.5
requests-toolbelt: 1.0.0
rich: 14.3.3
sentence-transformers: 5.3.0
sqlalchemy: 2.0.48
SQLAlchemy: 2.0.48
tenacity: 9.1.4
tiktoken: 0.12.0
tokenizers: 0.22.2
transformers: 5.3.0
typing-extensions: 4.15.0
uuid-utils: 0.14.1
websockets: 16.0
xxhash: 3.6.0
zstandard: 0.25.0

[chang923]

Eugene Yurtsev (@eyurtsev) Could you please assign this issue to me? The fix and unit test are already prepared in PR #36666. Thanks!

[jackjin1997]

Ran the repro locally — Blob.from_data("hello").as_bytes_io() hits the fallthrough NotImplementedError because the code only branches on isinstance(self.data, bytes) and delegates to self.path otherwise. as_string() and as_bytes() both already handle the isinstance(self.data, str) case, so the inconsistency is just a missed branch in as_bytes_io. Happy to put up a fix (wrap self.data.encode(self.encoding) in BytesIO when data is a string, mirroring as_bytes) with a unit test covering string/bytes/path — could I get assigned?

[vigneshakaviki]

Hi, I'd like to work on this. I have a fix ready — added the missing isinstance(self.data, str) branch in as_bytes_io() to encode string data using self.encoding, consistent with how as_bytes() handles it. Could you assign this to me so my PR (#36674) can be reopened? Thanks.