Add key TEI and TGI parameters for handling long retrievals #340
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Outdated suggestions cannot be applied.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.
Description
The default TGI max_total_tokens is 2048, which is not good for long retrieved input context.
Sometimes the TGI will raise an error like
Input validation error: inputs tokens + max_new_tokens must be <= 2048
One fix is to double the max tokens
--max-input-length 2048 --max-total-tokens 4096
The other issue that may sometimes break the flow is in the TEI reranking. It usually occurs with the error log:
Input validation error: inputs must have less than 512 tokens
. TEI has a limit of 512 input tokens and this can be remedied with the--auto-truncate
flag.Issues
n/a
Type of change
List the type of change like below. Please delete options that are not relevant.
Dependencies
None
Tests
None