Skip to content

fix: When there is an empty string in the context, the conversation reports an error #2947

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
shaohuzhang1 merged 1 commit into from
Apr 22, 2025
Merged

fix: When there is an empty string in the context, the conversation reports an error #2947

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
8 changes: 6 additions & 2 deletions apps/application/models/application.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
from django.contrib.postgres.fields import ArrayField
from django.db import models
from langchain.schema import HumanMessage, AIMessage

from django.utils.translation import gettext as _
from common.encoder.encoder import SystemEncoder
from common.mixins.app_model_mixin import AppModelMixin
from dataset.models.data_set import DataSet
Expand Down Expand Up @@ -167,7 +167,11 @@ def get_human_message(self):
return HumanMessage(content=self.problem_text)

def get_ai_message(self):
return AIMessage(content=self.answer_text)
answer_text = self.answer_text
if answer_text is None or len(str(answer_text).strip()) == 0:
answer_text = _(
'Sorry, no relevant content was found. Please re-describe your problem or provide more information. ')
return AIMessage(content=answer_text)

def get_node_details_runtime_node_id(self, runtime_node_id):
return self.details.get(runtime_node_id, None)
Copy link
Copy Markdown
Contributor Author

@shaohuzhang1 shaohuzhang1 Apr 22, 2025

Choose a reason for hiding this comment

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

The code appears to be well-written, but there are a couple of optimizations you might consider:

  1. String Formatting: In get_ai_message, using an inline string concatenation directly within _.format() can be less efficient than constructing the entire string first. Consider extracting the result into a variable.

  2. Variable Naming Consistency: Ensure that all variables (like answer_text) use consistent naming conventions throughout the method.

Here's revised version with some of these suggestions implemented:

from django.contrib.postgres.fields import ArrayField
from django.db import models
from langchain.schema import HumanMessage, AIMessage
from django.utils.translation import gettext as _

from common.encoder.encoder import SystemEncoder
from common.mixins.app_model_mixin import AppModelMixin
from dataset.models.data_set import DataSet


def construct_answer_message(text):
    if not text or str(text).strip() == "":
        return _(
            'Sorry, no relevant content was found. Please re-describe your problem or provide more information.'
        )
    else:
        return text

class YourClassName(AppModelMixin):  # Replace with actual class name
    problem_text = models.TextField()
    answer_text = models.TextField()

    def get_human_message(self):
        return HumanMessage(content=self.problem_text)

    def get_ai_message(self):
        return AIMessage(content=construct_answer_message(self.answer_text))

    def get_node_details_runtime_node_id(self, runtime_node_id):
        return self.details.get(runtime_node_id, None)

This change refactors the construction of the AI message into a separate function (construct_answer_message), making it easier to test and reuse if needed. The rest of the logic remains mostly unchanged.

Expand Down