Refactor llm_* Function Call Structure for Enhanced Flexibility in Prompt Specification
#61
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
dorbanianas
changed the base branch from
main
to
feat/batching-on-output-max-size
dorbanianas
force-pushed
the
feat/batching-on-output-max-size
branch
from
3d1b17e to
a200ef3
Compare
dorbanianas
force-pushed
the
feat/different-prompt-types-handling
branch
from
8ad113d to
757bbca
Compare
dorbanianas
force-pushed
the
feat/different-prompt-types-handling
branch
from
ddb3672 to
227ce6b
Compare
queryproc
approved these changes
Nov 17, 2024
| @@ -19,6 +20,31 @@ std::vector<nlohmann::json> CastVectorOfStructsToJson(Vector &struct_vector, int | |||
| return vector_json; | |||
| } | |||
|
|
|||
| PromptDetails CreatePromptDetails(Connection &con, const nlohmann::json prompt_details_json) { | |||
There was a problem hiding this comment.
This should exist in some PromptRender type of class
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Outdated suggestions cannot be applied.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 change updates the
llm_*function call format to allow a more flexible and abstracted specification of prompts and prompt names. The previous structure, which requiredllm_filter('validate-email', {'model_name': 'default'}, {'email': email}), is now updated to accept parameters in the following format:llm_filter({'model_name': 'default'}, {'prompt': 'return the invalid emails'}, {'email': email})llm_filter({'model_name': 'default'}, {'prompt-name': 'validate-email'}, {'email': email})This refactor allows for easier adaptation to various prompt names and specifications, enhancing modularity and reusability across different use cases.