Skip to main content

​
Get Your API Key

  1. Log in to Bud AI Foundry
  2. Navigate to API Keys & Security
  3. Click + Create API Key
  4. Name it “Quickstart” and click Create
  5. Copy the key (starts with bud_)
Save your API key securely. It won’t be shown again after creation.

​
Python SDK

​
Install

pip install git+https://github.com/BudEcosystem/BudAIFoundry-SDK

​
Your First Request

from budai import BudClient

# Initialize client
client = BudClient(api_key="bud_your_key_here")

# Make inference request
response = client.chat.completions.create(
    model="llama-3.2-1b",
    messages=[
        {"role": "user", "content": "Explain quantum computing in one sentence"}
    ]
)

print(response.choices[0].message.content)
Output: 
Quantum computing uses quantum mechanical phenomena like superposition and
entanglement to perform calculations exponentially faster than classical computers
for certain problems.

​
Run a Pipeline

# Create a deployment pipeline
pipeline = client.pipelines.create(
    name="Deploy Llama",
    definition={
        "steps": [
            {
                "id": "add_model",
                "action": "model_add",
                "params": {
                    "model_uri": "meta-llama/Llama-3.2-1B-Instruct",
                    "model_source": "hugging_face"
                }
            },
            {
                "id": "deploy",
                "action": "deployment_create",
                "params": {
                    "model_id": "{{steps.add_model.output.model_id}}",
                    "cluster_id": "cluster_prod"
                },
                "depends_on": ["add_model"]
            }
        ]
    }
)

# Execute the pipeline
execution = client.executions.create(pipeline_id=pipeline.id)
print(f"Deployment created: {execution.outputs['deployment_id']}")

​
Gateway API (cURL)

​
Direct API Call

curl https://gateway.bud.studio/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer bud_your_key_here" \
  -d '{
    "model": "llama-3.2-1b",
    "messages": [
      {"role": "user", "content": "What is machine learning?"}
    ]
  }'

​
Response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1706554800,
  "model": "llama-3.2-1b",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Machine learning is a subset of artificial intelligence..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 45,
    "total_tokens": 57
  }
}

​
Environment Setup

​
Environment Variables

# Set your API key
export BUD_API_KEY="bud_your_key_here"

# Set custom endpoint (optional)
export BUD_BASE_URL="https://gateway.bud.studio/v1"

​
Configuration File

Create ~/.budai/config.yaml: 
api_key: bud_your_key_here
base_url: https://gateway.bud.studio/v1
timeout: 30
The SDK automatically loads this configuration.

​
Check Available Models

# List all available models
models = client.models.list()

for model in models:
    print(f"{model.id}: {model.description}")
Output: 
llama-3.2-1b: Llama 3.2 1B Instruct
llama-3.2-3b: Llama 3.2 3B Instruct
gpt-4o: OpenAI GPT-4 Omni (cloud)
claude-3-5-sonnet: Anthropic Claude 3.5 Sonnet (cloud)

​
Error Handling

from budai.exceptions import BudAPIError

try:
    response = client.chat.completions.create(
        model="nonexistent-model",
        messages=[{"role": "user", "content": "Hello"}]
    )
except BudAPIError as e:
    print(f"Error: {e.status_code} - {e.message}")

​
Next Steps

Python SDK Guide

Deep dive into Python SDK features

Gateway API

REST API reference and examples

Authentication

Secure your API access

CLI Tools

Command-line interface guide