Adding tgis params to caikit api #324
Merged
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
added 11 commits
February 15, 2024 10:43
Signed-off-by: waleedqk <waleedqk@ibm.com>
Signed-off-by: waleedqk <waleedqk@ibm.com>
Signed-off-by: waleedqk <waleedqk@ibm.com>
Signed-off-by: waleedqk <waleedqk@ibm.com>
Signed-off-by: waleedqk <waleedqk@ibm.com>
git push origin $BRANCH e remote-tracking branch 'origin/main' into ResponseOptions
Signed-off-by: waleedqk <waleedqk@ibm.com>
Signed-off-by: waleedqk <waleedqk@ibm.com>
Signed-off-by: waleedqk <waleedqk@ibm.com>
Signed-off-by: waleedqk <waleedqk@ibm.com>
Signed-off-by: waleedqk <waleedqk@ibm.com>
waleedqk
requested review from
alex-jw-brooks,
gkumbhat,
evaline-ju,
gabe-l-hart,
tharapalanivel and
Ssukriti
as code owners
added 2 commits
March 26, 2024 09:13
Signed-off-by: waleedqk <waleedqk@ibm.com>
Signed-off-by: waleedqk <waleedqk@ibm.com>
waleedqk
changed the title
evaline-ju
requested changes
Mar 26, 2024
| token_logprobs: str | ||
| Whether or not to include logprob for each returned token. | ||
| Applicable only if generated_tokens == true and/or input_tokens == true | ||
| token_ranks: str |
There was a problem hiding this comment.
Based on the module runtime parameters these all appear to be bool not str? (Seems preserve_input_text might not have been accurate either, if that could also be updated here)
Signed-off-by: waleedqk <waleedqk@ibm.com>
evaline-ju
reviewed
Apr 1, 2024
| Whether or not to include logprob for each returned token. | ||
| Applicable only if generated_tokens == true and/or input_tokens == true | ||
| token_ranks: bool | ||
| Whether or not to include rank of each returned token. |
There was a problem hiding this comment.
token_ranks is added but there is no output allowing for rank information to be exposed. Is this intentional?
There was a problem hiding this comment.
yes, I had some trouble initially with figuring out the output for the token_ranks parameter.
Since it wasnt to core ask, I exposed the parameter but have not adjusted the output for it in the data-model or guardrails
added 3 commits
April 2, 2024 12:06
Signed-off-by: waleedqk <waleedqk@ibm.com>
Signed-off-by: waleedqk <waleedqk@ibm.com>
Signed-off-by: waleedqk <waleedqk@ibm.com>
evaline-ju
approved these changes
Apr 2, 2024
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.
Add support for ReturnOptions, GeneratedTokens and InputTokens
As part of caikit there are some parameters that are hard-coded to default values in code.
In the TGIS implementation, users can set these options and get the appropriate response.
The parameters in questions are part of the ResponseOptions proto found here.
This PR updates the data-model so that the return from inference server can be part of the result if the appropriate parameter is set in caikit FastAPI endpoint.