The local deployed Oracle 23ai vector database connection error in Dify.

[qujch]

Self Checks

• 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.

Content

I deployed Oracle 23ai free version as the vector database in local Linux VM, and then I deployed Docker + Ollama + Dify in the same local Linux VM. When I upload the file to do embedding in Dify, there is an error happened: vector database connection error.
How to resolve the error? How should I configure the local oracle 23ai as dify vector database?

[dosubot[bot]]

Hi @qujch! I'm Dosu and I’m helping the dify team.

Dify does support Oracle 23ai as a vector database backend, but connection errors are usually caused by misconfiguration or network issues. Here’s how to set it up and troubleshoot:

Configuration:
Set these environment variables in your docker-compose.yaml or .env file to match your Oracle 23ai instance:

• ORACLE_USER (e.g., dify)
• ORACLE_PASSWORD (e.g., dify)
• ORACLE_DSN (e.g., localhost:1521/FREEPDB1 for local, or the correct host:port/service_name)
• ORACLE_CONFIG_DIR, ORACLE_WALLET_LOCATION, ORACLE_WALLET_PASSWORD (only for autonomous DB)
• ORACLE_IS_AUTONOMOUS (false for standard, true for autonomous DB)

Example:

ORACLE_USER: dify
ORACLE_PASSWORD: dify
ORACLE_DSN: localhost:1521/FREEPDB1
ORACLE_IS_AUTONOMOUS: false

See docker-compose.yaml reference and OracleVectorConfig details.

Checklist for troubleshooting:

1. Make sure the Oracle 23ai service is running and accessible from the Dify container. Test with telnet <host> <port> or similar from inside the container.
2. Double-check all Oracle-related environment variables for typos or incorrect values.
3. If using Docker, confirm that the network allows the Dify container to reach the Oracle service (use host.docker.internal or your VM’s IP if needed).
4. Check Dify backend logs for the exact error message—this will help pinpoint if it’s a credentials, DSN, or network issue.
5. Restart all related containers after making changes.

Common causes of connection errors:

• Oracle service not running or not reachable from Dify.
• Wrong DSN format or credentials.
• Docker network isolation.
• Missing required Python packages (oracledb must be installed in the API container).

If you still see errors, please share the exact error message from the Dify logs for more targeted help.

References:

• OracleVector implementation and config
• Oracle config class
• docker-compose.yaml Oracle section
• Integration test example

To reply, just mention @dosu.

---

^{How did I do? Good | Irrelevant | Incorrect | Verbose | Hallucination | Report 🐛 | Other}