fix(document_loaders): fallback to TextLoader for unsupported Unstructured file types#541
Open
Mohammad Mohtashim (keenborder786) wants to merge 5 commits intolangchain-ai:mainfrom
Conversation
Mohammad Mohtashim (keenborder786)
changed the title
Mohammad Mohtashim (keenborder786)
changed the title
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Add a per-file TextLoader fallback when UnstructuredFileLoader hits UnsupportedFileFormatError, apply post-processors, and log a warning. Includes unit tests and a small async mock fix in test_recursive_url_loader to restore expected test behavior.
We fall back to TextLoader because UnstructuredFileLoader can refuse files it can’t classify (e.g., .rs with a leading blank line) and raise UnsupportedFileFormatError. TextLoader is the simplest, dependency‑light way to still ingest the file as raw text (with encoding auto‑detect), so the loader doesn’t fail on otherwise readable content.
PS: Slight change in
test_octai.pyandtest_networkx.pybecause those tests were failing in CI pipeline (Don't know why and had nothing do with the change of this PR)Fixes: #485