Open
Conversation
Member
|
@ismaelilloDev can you resolve conflicts? |
RuliLG
requested changes
May 22, 2024
|
|
||
| use App\LLM\DTO\CompletionResponse; | ||
|
|
||
| interface CanSupportPartialRequestInterface |
Member
There was a problem hiding this comment.
Laravel's convention is to not use the word Interface, and that the interface is like an action. i.e. SupportsPartialRequests, what do u think?
| use App\LLM\Contracts\PromptRequest; | ||
| use App\LLM\DTO\CompletionResponse; | ||
|
|
||
| trait CanSupportPartialRequest { |
Member
There was a problem hiding this comment.
Convention option: use WithPartialRequestsSupport; :-)
ismaelilloDev
force-pushed
the
bug/divide-long-files-to-prompt
branch
from
4e7ea6c to
e4d138a
Compare
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The codecoverage ignore in the OpenAi class is due to the fact that the tests are not intended to make many requests to chatgpt each time we launch the tests as it is obvious. However this functionality is tested in the DumbLocalLlm which has been modified to handle partial requests. If the tests are launched all modified files are at 100% coverage.
Also an other bug is fixed. When we document a project, first time we have a request per file but second time don't make the request but make the query to update. As a json_doc is a new field this mean that on the second chance all json_docs field were put to null. Its not important because what we show is the markdown but now this is fixed :)