Skip to content

fix: Improve intent node #4062

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

Merged
zhanweizhang7 merged 1 commit into from
Sep 19, 2025
Merged

fix: Improve intent node #4062

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
54 changes: 28 additions & 26 deletions apps/application/flow/step_node/intent_node/impl/prompt_template.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,29 +2,31 @@



PROMPT_TEMPLATE = """# Role
You are an intention classification expert, good at being able to judge which classification the user's input belongs to.

## Skills
Skill 1: Clearly determine which of the following intention classifications the user's input belongs to.
Intention classification list:
{classification_list}

Note:
- Please determine the match only between the user's input content and the Intention classification list content, without judging or categorizing the match with the classification ID.

## User Input
{user_input}

## Reply requirements
- The answer must be returned in JSON format.
- Strictly ensure that the output is in a valid JSON format.
- Do not add prefix ```json or suffix ```
- The answer needs to include the following fields such as:
{{
"classificationId": 0,
"reason": ""
}}

## Limit
- Please do not reply in text."""
PROMPT_TEMPLATE = """
# Role
You are an intention classification expert, good at being able to judge which classification the user's input belongs to.

## Skills
Skill 1: Clearly determine which of the following intention classifications the user's input belongs to.
Intention classification list:
{classification_list}

Note:
- Please determine the match only between the user's input content and the Intention classification list content, without judging or categorizing the match with the classification ID.
- **When classifying, you must give higher weight to the context and intent continuity shown in the historical conversation. Do not rely solely on the literal meaning of the current input; instead, prioritize the most consistent classification with the previous dialogue flow.**

## User Input
{user_input}

## Reply requirements
- The answer must be returned in JSON format.
- Strictly ensure that the output is in a valid JSON format.
- Do not add prefix ```json or suffix ```
- The answer needs to include the following fields such as:
{{
"classificationId": 0,
"reason": ""
}}

## Limit
- Please do not reply in text."""
Copy link
Contributor Author

@shaohuzhang1 shaohuzhang1 Sep 19, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

No significant issues were found in the provided code. However, I suggest adding more detailed instructions about how to interpret and use historical conversations when determining the classification.

Optimization Suggestions:
It would also help if there was a placeholder or a method to extract relevant parts from previous interactions during the conversation (such as through metadata extraction) so that the model can better understand the context when making a classification decision.

Loading