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.

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

HTTPConnectionPool(host='weaviate', por 8080): Read timed out. (read timeout=60) when creating knowledge base #7997

Closed
5 tasks done
iray1991 opened this issue Sep 4, 2024 · 2 comments
Labels
🤔 cant-reproduce We can not reproduce it or the information is limited 👻 feat:rag Embedding related issue, like qdrant, weaviate, milvus, vector database.

Comments

@iray1991
Copy link

iray1991 commented Sep 4, 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).
  • [FOR CHINESE USERS] 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

Dify 0.7.3

Cloud or Self Hosted

Self Hosted (Docker)

Steps to reproduce

image

✔️ Expected Behavior

No response

❌ Actual Behavior

No response

Copy link

dosubot bot commented Sep 4, 2024

I found a similar issue that might help you resolve the "HTTPConnectionPool(host='weaviate', port 8080): Read timed out. (read timeout=60)" error when creating a knowledge base in Dify 0.7.3 using a self-hosted Docker setup. Here are the steps to troubleshoot and resolve the issue:

  1. Check Container Status: Ensure all containers are up and running.

    docker compose ps
  2. Inspect Weaviate Logs: Check the logs of the weaviate container for any errors or issues.

    docker logs docker-weaviate-1
  3. Network Configuration: Ensure that the network configuration allows communication between the containers. You can inspect the network settings and ensure that the weaviate container is correctly configured to listen on port 8080.

  4. Increase Timeout: If the weaviate service is slow to respond, you might need to increase the timeout settings in your application or Docker configuration.

  5. Restart Containers: Sometimes, simply restarting the containers can resolve connectivity issues.

    docker compose down
    docker compose up -d
  6. Update Environment Variables: Ensure that the environment variables in the .env file are correctly set and match the configuration required for your setup. If there are updates in the .env.example file, make sure to sync them with your .env file.

    cp .env.example .env
  7. Verify System Requirements: Ensure that your system meets the minimum requirements for running Dify. For example, make sure your Docker setup has at least 2 virtual CPUs and 8 GB of memory allocated, as insufficient resources can cause services to time out.

  8. Clone and Start Dify: If you haven't already, clone the Dify source code and start the Docker containers as follows:

    git clone https://github.com/langgenius/dify.git
    cd dify/docker
    cp .env.example .env
    docker compose up -d

By following these steps, you should be able to resolve the timeout error and successfully create a knowledge base in Dify [1][2][3].

To continue talking to Dosu, mention @dosu.

@dosubot dosubot bot added the 👻 feat:rag Embedding related issue, like qdrant, weaviate, milvus, vector database. label Sep 4, 2024
@crazywoola crazywoola added the 🤔 cant-reproduce We can not reproduce it or the information is limited label Sep 5, 2024
@crazywoola
Copy link
Member

Please attach the logs of the vector db container.

Maybe you can try docker compose --profile weaviate -p dify up -d.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
🤔 cant-reproduce We can not reproduce it or the information is limited 👻 feat:rag Embedding related issue, like qdrant, weaviate, milvus, vector database.
Projects
None yet
Development

No branches or pull requests

2 participants