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.

Sign up for GitHub

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

Jump to bottom

improvement/intent extractor prompt #161

Merged
merged 1 commit into from
Aug 13, 2023
Merged

improvement/intent extractor prompt #161

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
43 changes: 7 additions & 36 deletions pkg/extractors/prompts.go
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,13 +1,16 @@
package extractors

const intentPromptTemplate = `
You are an AI assistant helping to provide intents. Whenever I ask a question, respond back with the intent.
You respond back with the Intent of the question rather than providing the answer to the question. If you can't derive an Intent then simply respond back with Intent: None.
Identify the intent of the subject's statement or question below.

If you can't derive an Intent then simply respond back with Intent: None.

EXAMPLE
Human: Does Nike make running shoes?
Subject: Does Nike make running shoes?
Intent: The subject is inquiring about whether Nike, a specific brand, manufactures running shoes.

Subject:{{.Input}}
Subject: {{.Input}}
Intent:
`

type IntentPromptTemplateData struct {
Expand Down Expand Up @@ -43,35 +46,3 @@ type SummaryPromptTemplateData struct {
PrevSummary string
MessagesJoined string
}

// // Source: Langchain
//
//nolint:unused
const entityExtractorTemplate = `You are an AI assistant helping a human keep track of facts about relevant people,
places, and concepts in their life. Update the summary of the provided entity in the "Entity" section based on the last
line of your conversation with the human. If you are writing the summary for the first time, return a single sentence.
The update should only include facts that are relayed in the last line of conversation about the provided entity, and
should only contain facts about the provided entity.

If there is no new information about the provided entity or the information is not worth noting (not an important or
relevant fact to remember long-term), return the existing summary unchanged.

Full conversation history (for context):
{.History}

Entity to summarize:
{.Entity}

Existing summary of {entity}:
{.Content}

Last line of conversation:
Human: {.Input}
Updated summary:`

type EntityExtractorPromptTemplateData struct {
History string
Entity string
Summary string
Input string
}