Whatever message this page gives is out now! Go check it out!
Ollama embedding model configuration options
Last update:
May 18, 2026
Ollama
Field | Description |
|---|---|
Provider | Ollama. The selected embedding model provider for this configuration. |
Model name | Required. Embedding model name on the Ollama host (for example qwen3-embedding, nomic-embed-text, or mxbai-embed-large). Pull the model on the server before use (ollama pull <name>). |
Base URL | Required. URL of the Ollama HTTP API. Default is often http://localhost:11434 for a local daemon; use http://<host>:11434 or HTTPS behind a reverse proxy for remote servers. |
Max retries | Optional. Retries when the host is unreachable or returns transient errors. Default is often 3 when not set. |
Timeout (ms) | Optional. Request timeout in milliseconds. Default is often 60000 when not set; large models may need more time. |
Log API requests | When enabled, logs request details (paths, payloads). Disable after debugging. |
Log API responses | When enabled, logs response details. Disable after debugging. |
Note: Ollama embedding configurations do not use an API key in this UI; security depends on network access to the Ollama host and how you expose the API.
---
We're glad. Tell us how this page helped.
We're sorry. Can you tell us what didn't work for you?
Share additional feedback to help us improve.
0/255
|
