server: allow filtering llama server response fields #10940
Merged
63
−1
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
4 tasks
ngxson
requested changes
Dec 22, 2024
ngxson
reviewed
Dec 22, 2024
ngxson
reviewed
Dec 22, 2024
ngxson
approved these changes
Dec 24, 2024
|
When filtering nested response fields, is this new option un-nesting them? In the example provided: curl --request POST \
--url http://localhost:8080/completion \
--header "Content-Type: application/json" \
--data '{"prompt": "Building a website can be done in 10 simple steps:","n_predict": 128, "response_fields": ["content", "generation_settings/n_predict"]}'{"content":" 1. Choose a domain name...","generation_settings/n_predict":128}It seems like it's changing the previous format of Is this intended or am I misunderstanding somewhere? If it's intended it should probably be mentioned in the docs for the server, since it's a bit confusing behavior for a "filter" to actually change the response format IMO. |
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Outdated suggestions cannot be applied.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.
This adds a new feature. Allow Filtering LLama Server Response Fields from #10819.
Usage:
Curl:
curl --request POST \ --url http://localhost:8080/completion \ --header "Content-Type: application/json" \ --data '{"prompt": "Building a website can be done in 10 simple steps:","n_predict": 128, "response_fields": ["content", "generation_settings/n_predict"]}'Response:
{"content":" 1. Choose a domain name...","generation_settings/n_predict":128}Retrievals from multiple nested lists are also supported, example: Given the original data: {"key1" : {"key2": 3}} With response_fields = ["key1/key2"] Then, the final response will be: {"key1/key2": 3}.If response does not contain a path, we will return empty json for path.