🦙

curl http://localhost:11434/api/generate -d '{
  "model": "llama3",
  "prompt": "Why is the sky blue?",
  "stream": false
}'

curl http://localhost:11434/api/chat -d '{
  "model": "llama3",
  "messages": [
    { "role": "system", "content": "You are a helpful assistant." },
    { "role": "user", "content": "Hello!" }
  ],
  "stream": false
}'

curl http://localhost:11434/api/embeddings -d '{
  "model": "nomic-embed-text",
  "prompt": "Hello world"
}'

curl http://localhost:11434/api/tags

# pip install ollama

import ollama

# Generate
response = ollama.generate(
    model='llama3',
    prompt='Why is the sky blue?'
)
print(response['response'])

# Chat
response = ollama.chat(
    model='llama3',
    messages=[
        {'role': 'user', 'content': 'Hello!'}
    ]
)
print(response['message']['content'])

import ollama

# Streaming response
stream = ollama.chat(
    model='llama3',
    messages=[{'role': 'user', 'content': 'Tell me a story'}],
    stream=True
)

for chunk in stream:
    print(chunk['message']['content'], end='', flush=True)

import ollama

response = ollama.embeddings(
    model='nomic-embed-text',
    prompt='Hello world'
)

embedding = response['embedding']
print(f'Dimension: {len(embedding)}')

import ollama

# List models
models = ollama.list()
for model in models['models']:
    print(model['name'])

# Pull model
ollama.pull('llama3')

# Show model info
info = ollama.show('llama3')
print(info)

// npm install ollama

import { Ollama } from 'ollama';

const ollama = new Ollama();

// Generate
const response = await ollama.generate({
  model: 'llama3',
  prompt: 'Why is the sky blue?'
});
console.log(response.response);

// Chat
const chatResponse = await ollama.chat({
  model: 'llama3',
  messages: [{ role: 'user', content: 'Hello!' }]
});
console.log(chatResponse.message.content);

const stream = await ollama.chat({
  model: 'llama3',
  messages: [{ role: 'user', content: 'Tell me a story' }],
  stream: true
});

for await (const chunk of stream) {
  process.stdout.write(chunk.message.content);
}

# Modelfile
FROM llama3

# Set parameters
PARAMETER temperature 0.7
PARAMETER top_p 0.9
PARAMETER top_k 40
PARAMETER num_ctx 4096
PARAMETER stop "<|end|>"

# Set system prompt
SYSTEM You are a helpful coding assistant.

# Create model
# ollama create mymodel -f Modelfile

# Modelfile
FROM ./my-model.gguf

TEMPLATE """{{ if .System }}<|system|>
{{ .System }}<|end|>
{{ end }}{{ if .Prompt }}<|user|>
{{ .Prompt }}<|end|>
{{ end }}<|assistant|>
"""

ollama.generate(
    model='llama3',
    prompt='Hello',
    options={
        'temperature': 0.7,    # Creativity (0-2)
        'top_p': 0.9,          # Nucleus sampling
        'top_k': 40,           # Top-k sampling
        'num_predict': 128,    # Max tokens
        'num_ctx': 4096,       # Context window
        'repeat_penalty': 1.1, # Repetition penalty
        'seed': 42,            # Random seed
    }
)

from langchain_community.llms import Ollama
from langchain_community.chat_models import ChatOllama
from langchain_core.messages import HumanMessage

# LLM
llm = Ollama(model="llama3")
response = llm.invoke("Hello!")

# Chat model
chat = ChatOllama(model="llama3")
response = chat.invoke([HumanMessage(content="Hello!")])

# Embeddings
from langchain_community.embeddings import OllamaEmbeddings

embeddings = OllamaEmbeddings(model="nomic-embed-text")
vector = embeddings.embed_query("Hello world")

# Ollama exposes OpenAI-compatible endpoint
from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:11434/v1",
    api_key="ollama"  # Any string works
)

response = client.chat.completions.create(
    model="llama3",
    messages=[{"role": "user", "content": "Hello!"}]
)

print(response.choices[0].message.content)

# Model storage location
export OLLAMA_MODELS=/path/to/models

# Server host/port
export OLLAMA_HOST=0.0.0.0:11434

# Keep model loaded
export OLLAMA_KEEP_ALIVE=5m

# GPU settings
export OLLAMA_NUM_GPU=1
export CUDA_VISIBLE_DEVICES=0

# Debug mode
export OLLAMA_DEBUG=1