langgenius/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-07-21 20:15:31 -04:00
Code Issues 775 Packages Projects Releases 10 Wiki Activity

Fire crawl duplicate pages #4717

New Issue
Closed
opened 2026-02-21 18:07:43 -05:00 by yindo · 2 comments
yindo commented 2026-02-21 18:07:43 -05:00
Owner
Copy Link
Copy Source

Originally created by @djav1985 on GitHub (Jul 22, 2024).

Self Checks

  • This is only for bug report, if you would like to ask a question, please head to Discussions.
  • I have searched for existing issues search for existing issues, including closed ones.
  • I confirm that I am using English to submit this 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.

Dify version

0.6.14

Cloud or Self Hosted

Self Hosted (Docker)

Steps to reproduce

Crawl your website

✔️ Expected Behavior

To get one copy of eachpage

❌ Actual Behavior

Some life pages show up twice in a list. Like it's picking up duplicates. Has anyone else experienced this problem? Or know why it's doing this is it something to do the way dify is using it or is it something with the project itself?

Originally created by @djav1985 on GitHub (Jul 22, 2024). ### Self Checks - [X] This is only for bug report, if you would like to ask a question, please head to [Discussions](https://github.com/langgenius/dify/discussions/categories/general). - [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 this 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. ### Dify version 0.6.14 ### Cloud or Self Hosted Self Hosted (Docker) ### Steps to reproduce Crawl your website ### ✔️ Expected Behavior To get one copy of eachpage ### ❌ Actual Behavior Some life pages show up twice in a list. Like it's picking up duplicates. Has anyone else experienced this problem? Or know why it's doing this is it something to do the way dify is using it or is it something with the project itself?
yindo added the 🐞 bug label 2026-02-21 18:07:43 -05:00
yindo closed this issue 2026-02-21 18:07:43 -05:00
yindo commented 2026-02-21 18:07:44 -05:00
Author
Owner
Copy Link
Copy Source

@dosubot[bot] commented on GitHub (Jul 22, 2024):

Hello @djav1985! I'm here to help you with any bugs, questions, or contribution requests related to the Dify project. Feel free to ask me anything while you wait for a human maintainer to assist you.

There are several configurations in the Docker environment that could affect the crawling behavior and lead to duplicate entries. Here are some key settings to check:

  1. Indexing Configuration:

    • INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH: 1000

  2. Database Connection Pool:

    • SQLALCHEMY_POOL_SIZE
    • SQLALCHEMY_POOL_RECYCLE

  3. Redis Configuration:

    • REDIS_HOST
    • REDIS_PORT
    • REDIS_DB

  4. Celery Configuration:

    • CELERY_WORKER_AMOUNT
    • CELERY_BROKER_URL

  5. Vector Store Configuration:

    • VECTOR_STORE
    • PGVECTOR_HOST
    • PGVECTOR_PORT
    • PGVECTOR_USER
    • PGVECTOR_PASSWORD
    • PGVECTOR_DATABASE

  6. Chroma Configuration:

    • CHROMA_HOST
    • CHROMA_PORT
    • CHROMA_TENANT
    • CHROMA_DATABASE
    • CHROMA_AUTH_PROVIDER
    • CHROMA_AUTH_CREDENTIALS

  7. OpenSearch Configuration:

    • discovery.type=single-node
    • bootstrap.memory_lock=true
    • OPENSEARCH_JAVA_OPTS=-Xms512m -Xmx1024m
    • OPENSEARCH_INITIAL_ADMIN_PASSWORD

Misconfigurations in any of these settings could potentially lead to issues such as duplicate entries during crawling [1][2].

Additionally, Dify provides logging and debugging tools that can help identify why certain pages are being crawled more than once. Specifically, Dify offers LLMOps features to monitor and analyze application logs and performance over time. The Firecrawl feature provides detailed logging and error reporting for crawl jobs, which can help identify and troubleshoot issues related to pages being crawled multiple times [3][4].

To continue talking to Dosu, mention @dosu.

@dosubot[bot] commented on GitHub (Jul 22, 2024): <!-- Greeting --> Hello @djav1985! I'm here to help you with any bugs, questions, or contribution requests related to the Dify project. Feel free to ask me anything while you wait for a human maintainer to assist you. <!-- Answer --> There are several configurations in the Docker environment that could affect the crawling behavior and lead to duplicate entries. Here are some key settings to check: 1. **Indexing Configuration**: - `INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH: 1000` 2. **Database Connection Pool**: - `SQLALCHEMY_POOL_SIZE` - `SQLALCHEMY_POOL_RECYCLE` 3. **Redis Configuration**: - `REDIS_HOST` - `REDIS_PORT` - `REDIS_DB` 4. **Celery Configuration**: - `CELERY_WORKER_AMOUNT` - `CELERY_BROKER_URL` 5. **Vector Store Configuration**: - `VECTOR_STORE` - `PGVECTOR_HOST` - `PGVECTOR_PORT` - `PGVECTOR_USER` - `PGVECTOR_PASSWORD` - `PGVECTOR_DATABASE` 6. **Chroma Configuration**: - `CHROMA_HOST` - `CHROMA_PORT` - `CHROMA_TENANT` - `CHROMA_DATABASE` - `CHROMA_AUTH_PROVIDER` - `CHROMA_AUTH_CREDENTIALS` 7. **OpenSearch Configuration**: - `discovery.type=single-node` - `bootstrap.memory_lock=true` - `OPENSEARCH_JAVA_OPTS=-Xms512m -Xmx1024m` - `OPENSEARCH_INITIAL_ADMIN_PASSWORD` Misconfigurations in any of these settings could potentially lead to issues such as duplicate entries during crawling <sup>[[1]](https://github.com/langgenius/dify/blob/main/docker/docker-compose.yaml)</sup><sup>[[2]](https://github.com/langgenius/dify/blob/main/docker-legacy/docker-compose.opensearch.yml)</sup>. Additionally, Dify provides logging and debugging tools that can help identify why certain pages are being crawled more than once. Specifically, Dify offers LLMOps features to monitor and analyze application logs and performance over time. The Firecrawl feature provides detailed logging and error reporting for crawl jobs, which can help identify and troubleshoot issues related to pages being crawled multiple times <sup>[[3]](https://github.com/langgenius/dify/blob/main/README_KL.md)</sup><sup>[[4]](https://github.com/langgenius/dify/blob/main/web/i18n/en-US/dataset-creation.ts)</sup>. <!-- Dosu Comment Footer --> *To continue talking to [Dosu](https://dosu.dev), mention @dosu.*
yindo commented 2026-02-21 18:07:44 -05:00
Author
Owner
Copy Link
Copy Source

@crazywoola commented on GitHub (Jul 22, 2024):

I don't think it's related to our side, because we only call apis to get data from firecrawl.

@crazywoola commented on GitHub (Jul 22, 2024): I don't think it's related to our side, because we only call apis to get data from firecrawl.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Knowledge Pipeline
Proposal
WIP
cloud
dependencies
feat:webapp
good first issue
outdated
performance
pull-request
Mirrored from GitHub Pull Request
 python:uv
refactor
size:L
stale
status: accepting prs
status: blocked
status: in discussion
stt & tts
vulnerablity
web
wont-fix
🌊 feat:workflow
🌚 invalid
🐞 bug
👻 feat:rag
💪 enhancement
📚 documentation
🔨 feat:tools
🙋‍♂️ question
🙏 help wanted
🤔 cant-reproduce
🤖 feat:agent
No Label 🐞 bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langgenius/dify#4717
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?