Ability to pass a system prompt for chat completion #902
Conversation
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
eafif
changed the title
| # @param system_prompt [String] Content of the prompt to send as "system" | ||
| # @yield [String] Stream responses back one String at a time | ||
| # @return [String] The answer to the question | ||
| def generate_messages_and_chat(question: , context: , system_prompt: nil, &block) |
There was a problem hiding this comment.
The method signature appears to include extra commas after the keywords 'question:' and 'context:'. It should be defined as 'def generate_messages_and_chat(question:, context:, system_prompt: nil, &block)' to avoid a syntax error.
Suggested change
| def generate_messages_and_chat(question: , context: , system_prompt: nil, &block) | |
| def generate_messages_and_chat(question:, context:, system_prompt: nil, &block) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
One use case is for RAG applications, we can pass a system prompt to the LLM to instruct to only return a response from the provided context and not make up an answer if the context is blank.