Whatever message this page gives is out now! Go check it out!
Ollama- LLM configuration field reference
Last update:
May 18, 2026
This document describes settings for the Ollama provider in the LLM configuration UI: basic connection, model parameters, proxy, and advanced options.
Behavior notes
- Leaving numeric or optional text fields blank uses the provider or integration default for that parameter.
- Ollama does not use an API key in this integration; authentication is handled by your host, network, and how Ollama is exposed.
- Logging fields include inline security guidance in the descriptions below (suitable for UI help text).
For official Ollama concepts (models, local API, options), see Ollama documentation
. Basic configuration
Field | Description |
|---|---|
Config alias | Required. Unique name for this configuration. Use only letters, numbers, hyphens, and underscores (for example llama3-local-dev). |
Provider | Ollama. The provider for this saved configuration. |
Model name | Required. The model name as Ollama knows it on the server (for example llama3.2 or mistral). Must match a model you have pulled or installed on the Ollama host (ollama pull <name>). |
Base URL | Required. Root URL of your Ollama HTTP API—typically http://localhost:11434 for a local daemon, or http://<host>:11434 (or HTTPS behind a reverse proxy) for remote access. Must be reachable from the application server. |
---
Model parameters
These map to options Ollama accepts when generating text. Exact names may follow your product’s mapping to Ollama’s API (for example
options in the generate/chat request).Field | Description |
|---|---|
Temperature | Leave blank to use the default. When set, use 0 or greater. Higher values increase randomness; typical values are often between 0 and 2 depending on the model. |
Max tokens | Leave blank to use the default. When set, enter a positive integer to cap response length in tokens (subject to model context limits). |
Top P | Leave blank to use the default. When set, use 0 or greater (often 0–1). Nucleus sampling; adjusts how many probability mass is considered for the next token. |
Top K | Leave blank to use the default. When set, use a non-negative integer to limit how many of the highest-probability tokens are considered at each step. |
Repeat penalty | Leave blank to use the default. When set, use 0 or greater. Reduces repetition of the same tokens across the output (Ollama’s repeat-penalty style parameter; your integration may map this from a shared “repeat penalty” field). |
Seed | Leave blank to use the default. When set, use a positive integer for more deterministic sampling when the runner supports it; local hardware and version can still affect outputs. |
Stop sequences | Optional. Comma-separated sequences that stop generation (for example END or newline tokens your API accepts). |
---
Proxy settings
Use these when HTTP traffic to Ollama must go through a forward proxy (uncommon for
localhost, typical for locked-down egress to a remote Ollama endpoint).Field | Description |
|---|---|
Proxy host | Optional. HTTP proxy hostname or IP. If you set a host, you must set Proxy port. |
Proxy port | Optional. Integer from 1 through 65535. Required when proxy host is set. |
Proxy username | Optional. User name for proxy authentication. Leave blank if the proxy does not require credentials. |
Proxy password | Optional. Proxy password. Stored credentials are sensitive—follow your organization’s secret-handling rules. Leave blank if not required. |
---
Advanced settings
Field | Description |
|---|---|
Max retries | Leave blank to use the default. When set, enter a positive integer for how many times to retry a failed request (for example when the Ollama host is temporarily unreachable). |
Timeout (seconds) | Leave blank to use the default. When set, enter a positive integer for the maximum wait time per request (large local models may need higher values). |
Log API requests | When enabled, request details are written to logs. Requests can include prompts and paths to your Ollama instance—use only while troubleshooting and disable afterward. Follow your organization’s logging and privacy requirements. |
Log API responses | When enabled, response details are written to logs. Responses can contain generated text and personal data—use only while troubleshooting and disable afterward. Follow your organization’s logging and privacy requirements. |
---
Parameters not shown for Ollama in the default form
Your product may hide provider-specific controls that do not apply here. For Ollama, API key, response format (as used by cloud APIs), presence penalty, and frequency penalty in the cloud sense are typically not used the same way as on other providers—see
LLM_PROVIDER_PARAMETERS.md for the Ollama column (Y / --).---
Related reference
- Parameter inventory and validation rules:
LLM_PROVIDER_PARAMETERS.md(Ollama column: Y = supported, -- = not shown for that provider).
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
|
