langchain_community: add error handling in HuggingFaceInferenceAPIEmbeddings #29792
Conversation
This file contains 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
dosubot
bot
added
the
size:M
|
The latest updates on your projects. Learn more about Vercel for Git ↗︎ 1 Skipped Deployment
|
dosubot
bot
added
community
wasn't registered per the contribution guide: https://python.langchain.com/docs/contributing/how_to/integrations/
These appear to pass.
Removing trailing whitespace from newline Linting a bit more :q Even more linting Lint + test failure Trailing commas, linting indentation Call me lintman Gonna have to squash these commits eventually Gonna have to squash these commits eventually again Gonna have to squash these commits eventually again again fix fix fix fix
brian-ogrady
force-pushed
the
add-hf-api-error-check
branch
from
5026f3b to
aaf105e
Compare
dosubot
bot
added
size:L
|
woops! @efriis please ignore this last commit here. Accidentally committed some unstaged changes when squashing my commits. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
When using a custom HuggingFace API Endpoint there can be an error in the JSON response. I propose added two checks when calling the
embed_documentsmethod of theHuggingFaceInferenceAPIEmbeddingsclass:JSONDecodeErrorWhile working with the
HuggingFaceInferenceAPIEmbeddingsclass, I sometimes receive a nebulous errorValueError: could not convert string to float: 'e'This results because the
embed_documentsmethod, which is called during the execution of theadd_documentsmethod of a vector store, can return a JSON response like the following:{'error': 'Input validation error:inputscannot be empty', 'error_type': 'Validation'}The initial
ValueErrorraised fromadd_documentsis misleading because it makes the underlying error returned in the JSON response. I propose surfacing this error by adding a check duringembed_documentsto return the JSON error in a Pythonic manner.I have detailed this request in the discussions.
If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.