Ollama
App · 6 actions
Run open models such as Llama, Qwen, Gemma and Mistral on your own Ollama server or on ollama.com: chat, generate text, create embeddings and see which models it has.
Actions
| Action | What it does |
|---|---|
| Chat with a model | Send a message to a model and get its answer, with an optional system prompt and earlier turns of the conversation. |
| Create embeddings | Turn text into embeddings: lists of numbers that place similar meanings close together, for search and matching. |
| Generate a completion | Send one prompt to a model and get the text it writes, with no conversation around it. |
| Get model details | Get a model's details and what it can do, such as tools, vision, thinking or embeddings. |
| List models | List the models downloaded on the Ollama server. |
| List running models | List the models loaded in the server's memory right now, and until when each stays loaded. |
Chat with a model
Send a message to a model and get its answer, with an optional system prompt and earlier turns of the conversation.
Inputs
- Model
modeltextRequired - The model to answer, as the server names it, such as llama3.2 or qwen3:8b. It must be downloaded on the server.
- Prompt
prompttextRequired - What to ask or tell the model.
- System prompt
systemtext - Instructions the model follows for the whole answer, such as its role or the format to answer in.
- Earlier messages
messageslist - Earlier turns of the conversation, oldest first, each like {"role": "user", "content": "Hi"}. Roles are user, assistant and system.
- Temperature
temperaturenumber - How varied the answer is, from 0 (the same answer every time) to 2. Leave empty for the model's own setting.From 0 to 2.0.
- Max tokens
max_tokensnumber - Stop the answer after this many tokens (about three quarters of a word each). Leave empty to let the model finish.From 1 to 131072.
- JSON output
json_outputtrue/false - Make the answer a JSON object a later step can read. Say in the prompt which fields you want.
- Think
thinktrue/false - For thinking models such as qwen3 and deepseek-r1: true to reason before answering, false to answer straight away. Other models refuse true. Leave empty for the model's own setting.
Outputs
done_reasontext- Why the model stopped: stop when it finished, length when it hit the maximum tokens.
duration_secondsnumber- How long the server took, loading the model included.
modeltext- The model that answered.
prompt_tokensnumber- How many tokens the prompt took.
response_tokensnumber- How many tokens the answer took.
texttext- The model's answer.
thinkingtext- The model's reasoning before it answered, from a thinking model; empty for other models.
Example output
{
"done_reason": "stop",
"duration_seconds": 1.42,
"model": "llama3.2",
"prompt_tokens": 26,
"response_tokens": 14,
"text": "The sky looks blue because air scatters blue light more.",
"thinking": ""
}Create embeddings
Turn text into embeddings: lists of numbers that place similar meanings close together, for search and matching. Takes one text or up to 100.
Inputs
- Model
modeltextRequired - An embedding model on the server, such as nomic-embed-text or embeddinggemma. A chat model can't make embeddings.
- Text
inputtextRequired - The text to embed, or a list of up to 100 texts, each embedded separately.
Outputs
countnumber- How many embeddings came back.
dimensionsnumber- How many numbers each embedding has.
embeddingslist- One embedding per text, in the order given; each is a list of numbers.
modeltext- The model that made them.
Example output
{
"count": 1,
"dimensions": 3,
"embeddings": [
[
0.010071029,
-0.0017594862,
0.05007221
]
],
"model": "nomic-embed-text"
}Generate a completion
Send one prompt to a model and get the text it writes, with no conversation around it.
Inputs
- Model
modeltextRequired - The model to write the text, as the server names it, such as llama3.2. It must be downloaded on the server.
- Prompt
prompttextRequired - What to ask or tell the model.
- System prompt
systemtext - Instructions the model follows for the whole answer, such as its role or the format to answer in.
- Temperature
temperaturenumber - How varied the answer is, from 0 (the same answer every time) to 2. Leave empty for the model's own setting.From 0 to 2.0.
- Max tokens
max_tokensnumber - Stop the answer after this many tokens (about three quarters of a word each). Leave empty to let the model finish.From 1 to 131072.
- JSON output
json_outputtrue/false - Make the answer a JSON object a later step can read. Say in the prompt which fields you want.
- Think
thinktrue/false - For thinking models such as qwen3 and deepseek-r1: true to reason before answering, false to answer straight away. Other models refuse true. Leave empty for the model's own setting.
Outputs
done_reasontext- Why the model stopped: stop when it finished, length when it hit the maximum tokens.
duration_secondsnumber- How long the server took, loading the model included.
modeltext- The model that answered.
prompt_tokensnumber- How many tokens the prompt took.
response_tokensnumber- How many tokens the answer took.
texttext- The model's answer.
thinkingtext- The model's reasoning before it answered, from a thinking model; empty for other models.
Example output
{
"done_reason": "stop",
"duration_seconds": 0.87,
"model": "llama3.2",
"prompt_tokens": 12,
"response_tokens": 9,
"text": "Lodol runs your workflows, step by step.",
"thinking": ""
}Get model details
Get a model's details and what it can do, such as tools, vision, thinking or embeddings.
Inputs
- Model
modeltextRequired - The model to describe, as the server names it, such as llama3.2.
Outputs
capabilitieslist- What it can do: completion (writes text), tools, vision, thinking, embedding and others.
context_lengthnumber- The most tokens it can read at once, or null when the server does not say.
familytext- The model family, such as llama.
formattext- The file format, such as gguf.
modeltext- The model asked about.
modified_attext- When it was last downloaded or changed.
parameter_sizetext- How many parameters it has.
parameterstext- Its default settings, one per line, as Ollama shows them.
quantization_leveltext- How its weights are compressed, such as Q4_0.
Example output
{
"capabilities": [
"completion",
"tools"
],
"context_length": 131072,
"family": "llama",
"format": "gguf",
"model": "llama3.2",
"modified_at": "2025-05-04T17:37:44.706015396-07:00",
"parameter_size": "3.2B",
"parameters": "stop \"<|eot_id|>\"",
"quantization_level": "Q4_K_M"
}List models
List the models downloaded on the Ollama server.
Inputs
None.
Outputs
countnumber- How many models there are.
modelslist- The models, most recently changed first.
Example output
{
"count": 2,
"models": [
{
"family": "llama",
"modified_at": "2025-05-04T17:37:44.706015396-07:00",
"name": "llama3.2:latest",
"parameter_size": "3.2B",
"quantization_level": "Q4_K_M",
"size": 2019393189
},
{
"family": "nomic-bert",
"modified_at": "2025-05-02T09:12:03.120511284-07:00",
"name": "nomic-embed-text:latest",
"parameter_size": "137M",
"quantization_level": "F16",
"size": 274302450
}
]
}List running models
List the models loaded in the server's memory right now, and until when each stays loaded.
Inputs
None.
Outputs
countnumber- How many models are loaded.
modelslist- The loaded models.
Example output
{
"count": 1,
"models": [
{
"expires_at": "2024-06-04T14:38:31.83753-07:00",
"family": "llama",
"name": "mistral:latest",
"parameter_size": "7.2B",
"quantization_level": "Q4_0",
"size": 5137025024,
"size_vram": 5137025024
}
]
}