feat: invoke newly created callLLM() function from A4D extension #2
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
…ode-service-provider
…d more instructions for system and user prompts
… generated for the current Apex class
…nd the constructed prompt to the XGen LLM - does not work because this operates outside a VSCode extension environment
…ate an XGen prompt, and get an OpenAPI v3 specification back from the LLM
…ent YAML File to LLM' command is running
Co-authored-by: peternhale <[email protected]>
…ML file in 'results' folder
…not providing the desired format
…pt through vscode-service-provider in sendYamlPromptToLLM.ts
…pt through vscode-service-provider in sendApexPromptToLLM.ts
peternhale
approved these changes
Jan 2, 2025
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Outdated suggestions cannot be applied.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 is a continuation of the previous PR, which was not merged due to a dependency on the daphne/W-17250453-send-prompt-to-llm-getChatStream branch of vscode-service-provider.
What does this PR do?
Previously, A4D extension exposed
AiApiClientas a way to allow other extensions to integrate with the XGen LLM. This produced a working solution, but required some duplicate code to be copied from salesforcedx-vscode-einstein-gpt to salesforcedx-vscode-service-provider. It also required any extension that implements thegetChatStream()function, such as the Prompt Engineering Playground, to handle the guts of streaming.As a result, A4D Team has created a new function
callLLM(), which packages the functionality ofgetChatStream()such that streaming is now handled by A4D rather than the extension that invokes it. Instead of exposingAiApiClient, A4D extension now exposesLLMService, which contains thecallLLM()function.What issues does this PR fix or reference?
@W-17396859@