> ## Documentation Index
> Fetch the complete documentation index at: https://docs.budecosystem.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickstart

> Get started with the BudAI Foundry Python SDK in minutes

## Installation

Install the SDK from GitHub:

```bash theme={null}
pip install git+https://github.com/BudEcosystem/BudAIFoundry-SDK
```

## Initialize the Client

Create a client instance with your API key:

```python theme={null}
from bud import BudClient

# Using API key
client = BudClient(api_key="your-api-key-here")

# Or using environment variable BUD_API_KEY
client = BudClient()
```

## Your First API Call

### Chat Completion

```python theme={null}
response = client.chat.completions.create(
    model="gpt-4",
    messages=[
        {"role": "user", "content": "What is artificial intelligence?"}
    ],
    temperature=0.7
)

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

### Generate Embeddings

```python theme={null}
response = client.embeddings.create(
    model="text-embedding-3-small",
    input="Machine learning is transforming industries"
)

print(f"Embedding vector: {response.data[0].embedding}")
```

### Streaming Response

```python theme={null}
stream = client.chat.completions.create(
    model="gpt-4",
    messages=[{"role": "user", "content": "Tell me a story"}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")
```

## Create and Run a Pipeline

```python theme={null}
from bud import Pipeline, Action

# Define a pipeline
with Pipeline("my-first-pipeline") as p:
    start = Action("start", type="log").with_config(
        message="Pipeline started"
    )

    process = Action("process", type="transform").after(start)

    end = Action("end", type="log").after(process).with_config(
        message="Pipeline completed"
    )

# Create the pipeline
pipeline = client.pipelines.create(
    dag=p.to_dag(),
    name=p.name,
    description="My first pipeline"
)

# Execute the pipeline
execution = client.executions.create(
    pipeline_id=pipeline.id,
    params={"input_data": "Hello, World!"}
)

print(f"Execution ID: {execution.id}")
print(f"Status: {execution.status}")
```

## Using the CLI

The SDK includes a CLI tool accessible via the `bud` command:

```bash theme={null}
# Login
bud auth login

# List available actions
bud action list

# Create a pipeline from YAML
bud pipeline create pipeline.yaml --name my-pipeline

# Execute a pipeline
bud run my-pipeline --param key=value --wait

# View execution history
bud execution list --status completed
```

## Next Steps

<CardGroup cols={3}>
  <Card title="Authentication" icon="key" href="./authentication">
    Configure auth methods
  </Card>

  <Card title="Pipelines" icon="diagram-project" href="./pipelines">
    Build DAG pipelines
  </Card>

  <Card title="CLI Reference" icon="terminal" href="./cli-reference">
    Learn CLI commands
  </Card>
</CardGroup>