Slightly improve error handling for external providers #220
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
Catch specific OpenAI errors and re-raise with a clear message
…pecific module In addition, the `transformers` module is very insisstent, so I added their dedicated mechanism for silencing warnings
Instead, individual RecordEncoders and LLMs would need to raise their own errors
To detect errors early
…ts - both LLM and RecordEncoder
Catch the error in RecordEncoder base class, then format for each inhertor differently
miararoy
previously requested changes
Dec 13, 2023
1. Needed to change after code was changed. 2. Added a few more test cases 3. Added more assertions on the naive create()
Some error types changed
The CLI shouldn't mention `delete_index()`
Sending just "hello" without any limitations can use many tokens
acatav
approved these changes
Dec 13, 2023
| async def _aencode_documents_batch(self, | ||
| documents: List[KBDocChunk] | ||
| ) -> List[KBEncodedDocChunk]: | ||
| raise NotImplementedError | ||
|
|
||
| async def _aencode_queries_batch(self, queries: List[Query]) -> List[KBQuery]: | ||
| raise NotImplementedError | ||
|
|
||
| def _format_error(self, err): |
There was a problem hiding this comment.
Maybe we should resuse this code in the LLM too? I think it's can improve the experience
There was a problem hiding this comment.
Yeah, that's the plan. We'll do it as part of the planned BaseLLM refactor anyway
| try: | ||
| encoder = OpenAIEncoder(model_name, **kwargs) | ||
| except OpenAIError as e: | ||
| raise RuntimeError( |
There was a problem hiding this comment.
Probably for the future, but I guess it's reasonable to have our own auth and rate limit errors. For many services we are going to use this issue might occur, even pinecone by itself
There was a problem hiding this comment.
Yeah, that's definitely the plan!
This was referenced Dec 14, 2023
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.
Solution
This is a very initial and partial solution for #183.
We will need to improve error handling much further.
Type of Change