Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat: update text hint type prompting #111

Merged
merged 1 commit into from
Oct 17, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion skynet/modules/ttt/summaries/prompts/action_items.py
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@
"""

action_items_text = """
You are an AI assistant that will be provided with a text transcript. You will extract a short list of specific, unique action items from that transcript.
You are an AI assistant that will be provided with a text or a document. You will extract a short list of specific, unique action items from that text.
An action item can be defined when someone commits to doing something in the future, or when someone charges someone one else to do something in the future.

Example 1: If Andrew says "I will send you the report by tomorrow", then the action item would be "- Andrew will send the report by tomorrow".
Expand Down
2 changes: 1 addition & 1 deletion skynet/modules/ttt/summaries/prompts/summary.py
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@
"""

summary_text = """
You are an AI assistant that will be provided a text transcript of a meeting. You will extract a summary of that transcript.
You are an AI assistant that will be provided a text or a document. You will extract a summary of that text.
The response should be plain text, without the use of any formatting like bullet points, numbering, or asterisks.
Start your response with "Response:".
"""