OverviewHistoryStatsSecurity
npx skills add ...
Documentation
SKILL.md
npx skills add rawveg/skillsforge-marketplace --skill ollama
Ollama API Documentation
npx skills add rawveg/skillsforge-marketplace --skill ollama
Comprehensive assistance with Ollama development - the local AI model runtime for running and interacting with large language models programmatically.
This skill should be triggered when:
Generate a simple chat response:
Generate a text response from a prompt:
Use Ollama with the OpenAI Python library:
Ask questions about images:
Create vector embeddings for text:
Get structured JSON responses:
Use Ollama with the OpenAI JavaScript library:
Sign in to use cloud models:
Or use API keys for direct cloud access:
Set environment variables for server configuration:
macOS:
Linux (systemd):
Windows:
Verify if your model is using GPU:
Output shows:
100% GPU - Fully loaded on GPU100% CPU - Fully loaded in system memory48%/52% CPU/GPU - Split between bothhttp://localhost:11434/apihttps://ollama.com/api/v1/ endpoints for OpenAI librarieshttp://localhost:11434ollama signin) or API keyhttps://ollama.com/apigemma3, llama3.2, qwen3)-cloud (e.g., gpt-oss:120b-cloud, qwen3-coder:480b-cloud)llava)OLLAMA_HOST - Change bind address (default: 127.0.0.1:11434)OLLAMA_CONTEXT_LENGTH - Context window size (default: 2048 tokens)OLLAMA_MODELS - Model storage directoryOLLAMA_ORIGINS - Allow additional web origins for CORSHTTPS_PROXY - Proxy server for model downloadsStatus Codes:
200 - Success400 - Bad Request (invalid parameters)404 - Not Found (model doesn't exist)429 - Too Many Requests (rate limit)500 - Internal Server Error502 - Bad Gateway (cloud model unreachable)Error Format:
"stream": false to get complete response in one objectThis skill includes comprehensive documentation in references/:
llms-txt.md - Complete API reference covering:
/api/generate, /api/chat, /api/embed, etc.)llms.md - Documentation index listing all available topics:
Use the reference files when you need:
Start with these common patterns:
/api/generate endpoint with a prompt/api/chat with messages arraybase_url='http://localhost:11434/v1/'ollama ps to verify model loadingRead llms-txt.md section on "Introduction" and "Quickstart" for foundational concepts.
Focus on:
Check the specific API endpoints in llms-txt.md for detailed parameter options.
Explore:
Refer to platform-specific sections in llms.md and configuration details in llms-txt.md.
Building a chatbot:
/api/chat endpointCreating embeddings for search:
/api/embed endpointRunning behind a firewall:
HTTPS_PROXY environment variableUsing cloud models:
ollama signin once-cloud suffixCheck:
Solutions:
Problem: Ollama only accessible from localhost
Solution:
See "How do I configure Ollama server?" in llms-txt.md for platform-specific instructions.
Problem: Cannot download models behind proxy
Solution:
See "How do I use Ollama behind a proxy?" in llms-txt.md.
Problem: Browser extension or web app cannot access Ollama
Solution:
See "How can I allow additional web origins?" in llms-txt.md.
curl http://localhost:11434/api/generate -d '{
"model": "gemma3",
"prompt": "Why is the sky blue?"
}'from openai import OpenAI
client = OpenAI(
base_url='http://localhost:11434/v1/',
api_key='ollama', # required but ignored
)
chat_completion = client.chat.completions.create(
messages=[
{
'role': 'user',
'content': 'Say this is a test',
}
],
model='llama3.2',
)from openai import OpenAI
client = OpenAI(base_url="http://localhost:11434/v1/", api_key="ollama")
response = client.chat.completions.create(
model="llava",
messages=[
{
"role": "user",
"content": [
{"type": "text", "text": "What's in this image?"},
{
"type": "image_url",
"image_url": "data:image/png;base64,iVBORw0KG...",
},
],
}
],
max_tokens=300,
)client = OpenAI(base_url="http://localhost:11434/v1", api_key="ollama")
embeddings = client.embeddings.create(
model="all-minilm",
input=["why is the sky blue?", "why is the grass green?"],
)from pydantic import BaseModel
from openai import OpenAI
client = OpenAI(base_url="http://localhost:11434/v1", api_key="ollama")
class FriendInfo(BaseModel):
name: str
age: int
is_available: bool
class FriendList(BaseModel):
friends: list[FriendInfo]
completion = client.beta.chat.completions.parse(
temperature=0,
model="llama3.1:8b",
messages=[
{"role": "user", "content": "Return a list of friends in JSON format"}
],
response_format=FriendList,
)
friends_response = completion.choices[0].message
if friends_response.parsed:
print(friends_response.parsed)import OpenAI from "openai";
const openai = new OpenAI({
baseURL: "http://localhost:11434/v1/",
apiKey: "ollama", // required but ignored
});
const chatCompletion = await openai.chat.completions.create({
messages: [{ role: "user", content: "Say this is a test" }],
model: "llama3.2",
});# Sign in from CLI
ollama signin
# Then use cloud models
ollama run gpt-oss:120b-cloudexport OLLAMA_API_KEY=your_api_key
curl https://ollama.com/api/generate \
-H "Authorization: Bearer $OLLAMA_API_KEY" \
-d '{
"model": "gpt-oss:120b",
"prompt": "Why is the sky blue?",
"stream": false
}'# Set environment variable
launchctl setenv OLLAMA_HOST "0.0.0.0:11434"
# Restart Ollama application# Edit service
systemctl edit ollama.service
# Add under [Service]
Environment="OLLAMA_HOST=0.0.0.0:11434"
# Reload and restart
systemctl daemon-reload
systemctl restart ollama1. Quit Ollama from task bar
2. Search "environment variables" in Settings
3. Edit or create OLLAMA_HOST variable
4. Set value: 0.0.0.0:11434
5. Restart Ollama from Start menuollama psollama ps{
"error": "the model failed to generate a response"
}# Set OLLAMA_HOST to bind to all interfaces
export OLLAMA_HOST="0.0.0.0:11434"# Set proxy (HTTPS only, not HTTP)
export HTTPS_PROXY=https://proxy.example.com
# Restart Ollama# Allow specific origins
export OLLAMA_ORIGINS="chrome-extension://*,moz-extension://*"# CLI Commands
ollama signin # Sign in to ollama.com
ollama run gemma3 # Run a model interactively
ollama pull gemma3 # Download a model
ollama ps # List running models
ollama list # List installed models
# Check API Status
curl http://localhost:11434/api/version
# Environment Variables (Common)
export OLLAMA_HOST="0.0.0.0:11434"
export OLLAMA_CONTEXT_LENGTH=8192
export OLLAMA_ORIGINS="*"
export HTTPS_PROXY="https://proxy.example.com"