Skip to main content
View source

Ollama

View as Markdown

A RocketRide LLM node that routes pipeline traffic through a locally-hosted Ollama server.

What it does

Provides text generation against an Ollama server running on your own hardware. The node acts as an llm connection for agents and other nodes, and can also be driven directly through its questions and answers lanes. Because inference stays on-premise and requires no external API key, it fits privacy-sensitive or air-gapped deployments. Internally, it uses langchain-openai (ChatOpenAI) against Ollama's OpenAI-compatible /v1 endpoint.

Lanes

Lane inLane outDescription
questionsanswersSend a question directly, receive a generated answer

Profiles

Default: Llama 3.3 (llama3_3).

ProfileModelContext
llama3_3 (default)llama3.3:latest128,000
llama4-latestllama4:latest10,000,000
qwen3-latestqwen3:latest128,000
View 20 more models
ProfileModelContext
custom(user-specified)16,385
llama3_1-8bllama3.1:8b128,000
llama3_1-70bllama3.1:70b128,000
llama3_1-405bllama3.1:405b128,000
phi4-14bphi416,000
llama3_2-3bllama3.2128,000
llama3_2-1bllama3.2:1b128,000
mistral-7bmistral32,000
qwen2_5-7bqwen2.5128,000
qwen2_5-0_5bqwen2.5:0.5b128,000
qwen2_5-1_5bqwen2.5:1.5b128,000
qwen2_5-3bqwen2.5:3b128,000
qwen2_5-14bqwen2.5:14b128,000
qwen2_5-32bqwen2.5:32b128,000
qwen2_5-72bqwen2.5:72b128,000
deepseek-r1-1_5bdeepseek-r1:1.5b128,000
deepseek-r1-7bdeepseek-r1:7b128,000
deepseek-r1-14bdeepseek-r1:14b128,000
deepseek-r1-32bdeepseek-r1:32b128,000
deepseek-r1-671bdeepseek-r1:671b128,000

Configuration

Pick a profile to prefill the Ollama model, context limit, and server URL. Use custom to supply another Ollama tag, context token count, and endpoint; its initial context value is 16,385 tokens.

Server base URL

Point the node at the Ollama server, normally http://localhost:11434. If the URL does not end in /v1, the node appends it automatically, so both http://localhost:11434 and http://localhost:11434/v1 work.

Temperature and reasoning effort

Temperature defaults to 0. When it is left unset for a reasoning model such as gpt-oss, the node uses 1.0; set reasoning_effort to low, medium, or high when the selected model supports that control.

The OpenAI client requires a non-empty API key, so the node sends the placeholder dummy-key, which Ollama ignores.

Upstream docs


Schema

FieldTypeDescriptionDefault
modelstringModel
Ollama model
modelTotalTokensnumberTokens
Total Tokens
ollama.profilestringModel
LLM model
"llama3_3"
reasoning_effortstringReasoning Effort
Optional reasoning budget for reasoning models: low, medium, or high. Leave unset to let reasoning models auto-use 'low'; a value set here always wins. Ignored by non-reasoning models.
temperaturenumberTemperature
Sampling temperature. Left unset by default so ollama.py can choose: 0 for standard models, and 1.0 for reasoning models (gpt-oss, deepseek-r1, qwen3, qwq, ...) so they emit a final answer instead of looping on empty output. Set an explicit value here to override the auto behavior.

Dependencies

  • langchain-openai
  • langchain-core
  • langchain