the segmentation results are empty #4469

Closed
opened 2026-02-21 18:06:35 -05:00 by yindo · 1 comment
Owner

Originally created by @silence-pan84 on GitHub (Jul 5, 2024).

Self Checks

  • I have searched for existing issues search for existing issues, including closed ones.
  • I confirm that I am using English to submit report (我已阅读并同意 Language Policy).
  • 请务必使用英文提交 Issue,否则会被关闭。谢谢!:)
  • Please do not modify this template :) and fill in all the required fields.

Provide a description of requested docs changes

The Nomic-embed-text embedding model uses the Q&A segmentation pattern, and the segmentation results are empty。#5764 The problem is not solved
image

Originally created by @silence-pan84 on GitHub (Jul 5, 2024). ### Self Checks - [X] I have searched for existing issues [search for existing issues](https://github.com/langgenius/dify/issues), including closed ones. - [X] I confirm that I am using English to submit report (我已阅读并同意 [Language Policy](https://github.com/langgenius/dify/issues/1542)). - [X] 请务必使用英文提交 Issue,否则会被关闭。谢谢!:) - [X] Please do not modify this template :) and fill in all the required fields. ### Provide a description of requested docs changes The Nomic-embed-text embedding model uses the Q&A segmentation pattern, and the segmentation results are empty。#5764 The problem is not solved ![image](https://github.com/langgenius/dify/assets/174668054/88909246-2dbb-4f0d-a65b-8add5f2a8849)
yindo closed this issue 2026-02-21 18:06:35 -05:00
Author
Owner

@dosubot[bot] commented on GitHub (Jul 5, 2024):

The segmentation results are likely empty because the max_chunks property is set to 1 in the embed-qa-4.yaml configuration file. This means that the model is only processing a single chunk of text, which might not be sufficient for generating meaningful segmentation results.

model: NV-Embed-QA
model_type: text-embedding
model_properties:
  context_size: 512
  max_chunks: 1

To resolve this issue, you may need to increase the max_chunks value to allow the model to process more chunks of text, which could lead to more meaningful segmentation results [1].

To continue talking to Dosu, mention @dosu.

@dosubot[bot] commented on GitHub (Jul 5, 2024): <!-- Answer --> The segmentation results are likely empty because the `max_chunks` property is set to 1 in the `embed-qa-4.yaml` configuration file. This means that the model is only processing a single chunk of text, which might not be sufficient for generating meaningful segmentation results. ```yaml model: NV-Embed-QA model_type: text-embedding model_properties: context_size: 512 max_chunks: 1 ``` To resolve this issue, you may need to increase the `max_chunks` value to allow the model to process more chunks of text, which could lead to more meaningful segmentation results <sup>[[1]](https://github.com/langgenius/dify/blob/main/api/core/model_runtime/model_providers/nvidia/text_embedding/embed-qa-4.yaml)</sup>. <!-- Dosu Comment Footer --> *To continue talking to [Dosu](https://dosu.dev), mention @dosu.*
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langgenius/dify#4469