Ollama
Note
This feature is available in Lite, Enterprise, and Ultimate editions only.
To use Ollama as an AI provider in DBeaver, configure it as follows:
Ensure that Ollama is already installed and running on a server. For installation instructions, see the Ollama docs. You will need the host address where Ollama is installed to proceed.
- In DBeaver, go to Window -> Preferences -> AI -> Model configurations
- Click + and choose Ollama as the engine to create a profile
- Specify the host address of your Ollama server in the Instance host field, ensuring it follows the
format
http://host:port - Use the refresh control next to the Model selector to load the available models from your Ollama server
- Select the model you need for your integration
- Click Test connection to verify that the server and model work correctly
- Apply the changes
Settings¶
| Setting | Description | Default |
|---|---|---|
| Instance host | Specify the address of the Ollama server in the format http://host:port, for example http://localhost:11434. If you omit the port, DBeaver uses port 11434. |
|
| Model | Choose the AI model. | |
| Context size | A larger number allows the AI to use more data for better answers but may slow down response time. | 30000 |
| Temperature | Control AI's creativity from 0.0 (more precise) to 0.9 (more diverse). Note that higher temperature can lead to less predictable results. |
0.0 |
| Request timeout (sec) | Maximum time DBeaver waits for a response from the AI engine before the request fails. | 30 |
| Write Ollama queries to debug log | Logs your AI requests. For more details on logging, see Log Viewer. | disabled |
Tip
If you use Ollama with a model that supports tool calling, AI tools are available.