### Install Dependencies and Start Dev Server

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/README.md

Navigate to the project directory, install Node.js dependencies, and start the local development server. Changes are reflected live.

```bash
cd aparavi-docusaurus
npm install
npx docusaurus start
```

--------------------------------

### Start from a Pipeline Configuration Object (Python)

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/api/use-method/use-method.md

Example of starting a pipeline by directly providing a pipeline configuration object in Python.

```APIDOC
## Start from a Pipeline Configuration Object (Python)

### Description
This example demonstrates initiating a pipeline by defining its configuration directly within the code as a Python dictionary.

### Code Example
```python
config = {
    'name': 'My Pipeline',
    'project_id': 'my-project',
    'source': 'webhook_1',
    'components': [
        {'id': 'webhook_1', 'provider': 'webhook', 'config': {}},
        {'id': 'ai_chat_1', 'provider': 'ai_chat', 'config': {'model': 'gpt-4'},
         'input': [{'from': 'webhook_1', 'lane': 'output'}]},
        {'id': 'response_1', 'provider': 'response', 'config': {},
         'input': [{'from': 'ai_chat_1', 'lane': 'answer'}]},
    ],
}
result = await client.use(pipeline=config)
```
```

--------------------------------

### Starting a Pipeline with `use`

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/api/use-method/use-method.md

This example demonstrates how to start a pipeline using the `use` method, providing a filepath to the pipeline configuration. It shows how to obtain a task token from the result for subsequent operations.

```APIDOC
## `use` Method

### Description
Starts a processing pipeline based on a provided configuration. It returns a unique token that can be used to track the pipeline's execution and interact with it.

### Method Signature
`await client.use(filepath: str)`

### Parameters
#### Path Parameters
- **filepath** (str) - Required - The path to the JSON file containing the pipeline configuration.

### Request Example
```python
from rocketride import RocketRideClient

async with RocketRideClient(auth='your-api-key') as client:
    result = await client.use(filepath='pipeline.json')
    token = result['token']
    print(f'Pipeline started with token: {token}')
```

### Response
#### Success Response (200)
Returns a JSON object containing a task token.
- **token** (str) - The unique identifier for the started pipeline task.

#### Response Example
```json
{
  "status": "OK",
  "data": {
    "token": "abc123-task-token"
  }
}
```

### Error Handling
- `ValueError` / `Error`: Neither `filepath` nor `pipeline` was provided.
- `FileNotFoundError`: The pipeline configuration file was not found at the specified path.
- `json.JSONDecodeError`: The pipeline configuration file contains invalid JSON.
- `RuntimeError` / `Error`: Failed to start the pipeline execution. Check the error message for details.
- Authentication error: Invalid or missing API key.
```

--------------------------------

### Start a Pipeline from a File (Python)

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/api/use-method/use-method.md

Example of starting a RocketRide pipeline using a JSON configuration file in Python.

```APIDOC
## Start a Pipeline from a File (Python)

### Description
This example demonstrates how to initiate a pipeline by providing the path to its configuration file.

### Code Example
```python
from rocketride import RocketRideClient

async with RocketRideClient(uri='https://cloud.rocketride.ai', auth='your-api-key') as client:
    result = await client.use(filepath='text_analyzer.json')
    token = result['token']
    print(f'Pipeline started with token: {token}')
```
```

--------------------------------

### Start with Custom Parameters (Python)

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/api/use-method/use-method.md

Example of starting a pipeline with custom parameters like threads, arguments, source override, and TTL in Python.

```APIDOC
## Start with Custom Parameters (Python)

### Description
This example shows how to configure a pipeline with specific settings beyond the basic file path.

### Code Example
```python
result = await client.use(
    filepath='data_processor.json',
    threads=8,
    args=['--verbose'],
    source='custom_input',
    ttl=300,
)
token = result['token']
```
```

--------------------------------

### Start, Send Data, and Check Status with use()

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/api/use-method/use-method.md

This example demonstrates a full workflow: starting a pipeline with `use()`, sending data for processing with `send()`, and checking the task status with `get_task_status()` before terminating.

```python
from rocketride import RocketRideClient

async with RocketRideClient(auth='your-api-key') as client:
    # Start pipeline
    result = await client.use(filepath='pipeline.json')
    token = result['token']

    # Send data for processing
    response = await client.send(token, 'Analyze this text for sentiment')

    # Check status
    status = await client.get_task_status(token)
    print(f'State: {status["state"]}')

    # Terminate when done
    await client.terminate(token)
```

--------------------------------

### Start a Pipeline from a File (TypeScript)

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/api/use-method/use-method.md

Example of starting a RocketRide pipeline using a JSON configuration file in TypeScript.

```APIDOC
## Start a Pipeline from a File (TypeScript)

### Description
This example demonstrates how to initiate a pipeline by providing the path to its configuration file.

### Code Example
```typescript
import { RocketRideClient } from 'rocketride';

const client = new RocketRideClient({
    auth: 'your-api-key',
    uri: 'https://cloud.rocketride.ai',
});
await client.connect();

const result = await client.use({ filepath: './text_analyzer.json' });
console.log(`Pipeline started with token: ${result.token}`);

await client.disconnect();
```
```

--------------------------------

### Start with Custom Parameters (TypeScript)

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/api/use-method/use-method.md

Example of starting a pipeline with custom parameters like threads, arguments, source override, and TTL in TypeScript.

```APIDOC
## Start with Custom Parameters (TypeScript)

### Description
This example shows how to configure a pipeline with specific settings beyond the basic file path.

### Code Example
```typescript
const result = await client.use({
    filepath: './data_processor.json',
    threads: 8,
    args: ['--verbose'],
    source: 'custom_input',
    ttl: 300,
});
```
```

--------------------------------

### Add Examples to a Question

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/sdk/python-sdk.md

The `addExample` method allows you to provide input/output pairs to guide the AI's response format and content. The `result` can be a dictionary, list, or string.

```python
question.addExample(given='What is the capital of France?', result='Paris')
```

--------------------------------

### Handle Pipeline Start Errors

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/api/use-method/use-method.md

This example shows how to catch common exceptions like `FileNotFoundError` for missing pipeline files or `RuntimeError` for pipeline execution failures.

```python
from rocketride import RocketRideClient, RocketRideException

try:
    result = await client.use(filepath='pipeline.json')
except FileNotFoundError:
    print('Pipeline file not found')
except RuntimeError as e:
    print(f'Pipeline failed to start: {e}')
```

--------------------------------

### Start Pipeline with Custom Parameters (Python)

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/api/use-method/use-method.md

Starts a pipeline with a configuration file, overriding default settings with custom threads, arguments, source, and TTL.

```python
result = await client.use(
    filepath='data_processor.json',
    threads=8,
    args=['--verbose'],
    source='custom_input',
    ttl=300,
)
token = result['token']
```

--------------------------------

### Start Pipeline from File (Python)

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/api/use-method/use-method.md

Initiates a pipeline using a JSON configuration file. The returned token is essential for further interactions with the pipeline.

```python
from rocketride import RocketRideClient

async with RocketRideClient(uri='https://cloud.rocketride.ai', auth='your-api-key') as client:
    result = await client.use(filepath='text_analyzer.json')
    token = result['token']
    print(f'Pipeline started with token: {token}')
```

--------------------------------

### Install RocketRide Node.js SDK

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/sdk/node-sdk.md

Install the RocketRide SDK using npm, Yarn, or PNPM.

```bash
# NPM
npm install rocketride
# Yarn
yarn add rocketride
# PNPM
pnpm add rocketride
```

--------------------------------

### Add Example to Question

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/sdk/node-sdk.md

Supplies an example input and its corresponding desired output to help the AI understand the expected response format.

```typescript
question.addExample('Input text', 'Expected output');
```

--------------------------------

### RocketRideClient Usage Examples

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/sdk/python-sdk.md

Examples demonstrating how to use the RocketRideClient for various tasks.

```APIDOC
## RocketRideClient Usage Examples

### Description
Examples demonstrating how to use the RocketRideClient for various tasks.

### 1. Minimal: connect, run pipeline from file, send one string, disconnect

```python
import asyncio
from rocketride import RocketRideClient

async def main():
    client = RocketRideClient(uri="https://cloud.rocketride.ai", auth="my-key")
    await client.connect()
    result = await client.use(filepath="pipeline.json")
    token = result["token"]
    out = await client.send(token, "Hello, pipeline!", objinfo={"name": "input.txt"}, mimetype="text/plain")
    print(out)
    await client.terminate(token)
    await client.disconnect()

asyncio.run(main())
```

### 2. One-off script with context manager (recommended)

```python
import asyncio
from rocketride import RocketRideClient

async def main():
    async with RocketRideClient(uri="wss://cloud.rocketride.ai", auth="my-key") as client:
        result = await client.use(pipeline={"pipeline": my_pipeline_config})
        token = result["token"]
        await client.send(token, '{"data": 1}')
        status = await client.get_task_status(token)
        print(status)
        await client.terminate(token)

asyncio.run(main())
```
```

--------------------------------

### Start Pipeline from File (TypeScript)

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/api/use-method/use-method.md

Initiates a pipeline using a JSON configuration file. The returned token is essential for further interactions with the pipeline.

```typescript
import { RocketRideClient } from 'rocketride';

const client = new RocketRideClient({
    auth: 'your-api-key',
    uri: 'https://cloud.rocketride.ai',
});
await client.connect();

const result = await client.use({ filepath: './text_analyzer.json' });
console.log(`Pipeline started with token: ${result.token}`);

await client.disconnect();
```

--------------------------------

### Start a Pipeline

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/sdk/node-sdk.md

Starts a pipeline execution. You can provide the pipeline configuration directly or via a file path. The client will substitute environment variables for placeholders like `${ROCKETRIDE_*}`. The returned token is essential for subsequent operations.

```APIDOC
## use

### Description
Starts a pipeline. You must pass either `pipeline` (object) or `filepath` (path to a JSON file; Node only). The client substitutes `${ROCKETRIDE_*}` in the config from its `env` (or `.env`). Returns at least `token`; use that token for `send()`, `sendFiles()`, `pipe()`, `chat()`, `getTaskStatus()`, and `terminate()`.

### Method
`use(options?: { token?: string; filepath?: string; pipeline?: PipelineConfig; source?: string; threads?: number; useExisting?: boolean; args?: string[]; ttl?: number }): Promise<Record<string, any> & { token: string }> `

### Parameters
#### Options
- **token** (string) - Optional - An existing token to reuse.
- **filepath** (string) - Optional - Path to a JSON file containing the pipeline configuration (Node.js only).
- **pipeline** (PipelineConfig) - Optional - An object representing the pipeline configuration.
- **source** (string) - Optional - Source code for the pipeline.
- **threads** (number) - Optional - Number of threads to use for execution.
- **useExisting** (boolean) - Optional - Whether to use an existing pipeline if available.
- **args** (string[]) - Optional - Arguments to pass to the pipeline.
- **ttl** (number) - Optional - Time-to-live for the pipeline task in seconds.

### Returns
- **Promise<Record<string, any> & { token: string }>** - A promise that resolves to an object containing the pipeline token and other results.
```

--------------------------------

### Start Pipeline with Custom Parameters (TypeScript)

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/api/use-method/use-method.md

Starts a pipeline with a configuration file, overriding default settings with custom threads, arguments, source, and TTL.

```typescript
const result = await client.use({
    filepath: './data_processor.json',
    threads: 8,
    args: ['--verbose'],
    source: 'custom_input',
    ttl: 300,
});
```

--------------------------------

### Quick Start: Initialize and Run a Pipeline

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/sdk/node-sdk.md

Initialize the RocketRide client, connect to the cloud, use a pipeline, send data, and disconnect. Ensure your ROCKETRIDE_APIKEY environment variable is set.

```typescript
import { RocketRideClient } from 'rocketride';

const client = new RocketRideClient({
	auth: process.env.ROCKETRIDE_APIKEY!,
	uri: 'https://cloud.rocketride.ai',
});
await client.connect();
const { token } = await client.use({ filepath: './pipeline.pipe' });
const result = await client.send(token, 'Hello, pipeline!', { name: 'input.txt' }, 'text/plain');
console.log(result);
await client.terminate(token);
await client.disconnect();
```

--------------------------------

### Example Task Status Response

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/api/get-task-status-method/get-task-status-method.md

This is an example of the full `TASK_STATUS` object returned by the method. It includes details about the task's state, progress, and metrics.

```json
{
  "name": "text_analyzer",
  "project_id": "my-project",
  "state": 3,
  "completed": false,
  "startTime": 1700000000.0,
  "endTime": 0.0,
  "totalCount": 100,
  "completedCount": 45,
  "failedCount": 2,
  "rateCount": 5,
  "errors": [],
  "warnings": [],
  "metrics": {
    "cpu_percent": 25.3,
    "cpu_memory_mb": 512.0,
    "gpu_memory_mb": 1024.0
  },
  "tokens": {
    "cpu_utilization": 1.5,
    "cpu_memory": 0.8,
    "gpu_memory": 2.1,
    "total": 4.4
  },
  "pipeflow": {
    "totalPipes": 2,
    "byPipe": {
      "0": ["source", "transform", "filter"],
      "1": ["source", "transform"]
    }
  }
}
```

--------------------------------

### Instantiate Client with Persistence and Callbacks

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/sdk/python-sdk.md

Example of creating a RocketRideClient instance with automatic reconnection enabled (`persist=True`) and custom error handling for connection failures. This setup is useful for long-running applications or UIs that need to maintain a connection.

```python
client = RocketRideClient(
    uri="https://cloud.rocketride.ai",
    auth="my-key",
    persist=True,
    max_retry_time=300000,
    on_connect_error=lambda msg: print("Connect error:", msg),
    on_event=handle_event,
)
```

--------------------------------

### Validate Before Starting Pipeline (Python)

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/api/validate-method/validate-method.md

Illustrates a common pattern of validating a pipeline configuration before initiating its execution using the `use` method. This ensures that only valid pipelines are started.

```python
# Validate first, then start if valid
result = await client.validate(pipeline)

# Check the result for errors before proceeding
# (exact structure depends on pipeline configuration)
task = await client.use(pipeline=pipeline)
```

--------------------------------

### Basic Status Check (Python)

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/api/get-task-status-method/get-task-status-method.md

Example of initiating a pipeline with `use()` and then checking its status using `get_task_status()`. Ensure you have the RocketRideClient imported and authenticated.

```python
from rocketride import RocketRideClient

async with RocketRideClient(auth='your-api-key') as client:
    result = await client.use(filepath='pipeline.json')
    token = result['token']

    status = await client.get_task_status(token)
    print(f'State: {status["state"]}')
    print(f'Progress: {status["completedCount"]}/{status["totalCount"]}')
```

--------------------------------

### Install RocketRide Python SDK

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/sdk/python-sdk.md

Install the RocketRide Python SDK using pip. This command should be run in your terminal or command prompt.

```bash
pip install rocketride
```

--------------------------------

### Start Pipeline from Configuration Object (Python)

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/api/use-method/use-method.md

Initiates a pipeline directly from a Python dictionary representing the pipeline configuration. This is useful for dynamically defined pipelines.

```python
config = {
    'name': 'My Pipeline',
    'project_id': 'my-project',
    'source': 'webhook_1',
    'components': [
        {'id': 'webhook_1', 'provider': 'webhook', 'config': {}},
        {'id': 'ai_chat_1', 'provider': 'ai_chat', 'config': {'model': 'gpt-4'},
         'input': [{'from': 'webhook_1', 'lane': 'output'}]},
        {'id': 'response_1', 'provider': 'response', 'config': {},
         'input': [{'from': 'ai_chat_1', 'lane': 'answer'}]},
    ],
}
result = await client.use(pipeline=config)
```

--------------------------------

### Run rocketride-mcp from command line

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/mcp_server/rocketride-mcp-server/rocketride-mcp-server.md

Execute the rocketride-mcp server using its installed entry point or by running it as a Python module.

```bash
# Using the installed entry point
rocketride-mcp

# Or using Python module
python -m rocketride_mcp
```

--------------------------------

### Basic Status Check (TypeScript)

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/api/get-task-status-method/get-task-status-method.md

Example of initiating a pipeline with `use()` and then checking its status using `getTaskStatus()`. Ensure you have the RocketRideClient imported and connected.

```typescript
import { RocketRideClient } from 'rocketride';

const client = new RocketRideClient({ auth: 'your-api-key' });
await client.connect();

const result = await client.use({ filepath: './pipeline.json' });
const status = await client.getTaskStatus(result.token);
console.log(`State: ${status.state}`);
console.log(`Progress: ${status.completedCount}/${status.totalCount}`);

await client.disconnect();
```

--------------------------------

### Install and Run RocketRide MCP SSE Mode

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/mcp_server/rocketride-mcp-server/rocketride-mcp-server.md

Install the necessary package and run the RocketRide MCP server in SSE mode for remote or Docker deployments. Supports Bearer token authentication via `MCP_API_KEY`.

```bash
pip install rocketride-mcp[sse]
rocketride-mcp-sse --host 0.0.0.0 --port 8080

```

--------------------------------

### Validate Pipeline Configuration

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/sdk/node-sdk.md

Validates a pipeline configuration without initiating its execution. This is useful for checking the correctness of your pipeline setup and identifying potential errors or warnings before starting.

```APIDOC
## validate

### Description
Validates a pipeline configuration without starting it. Returns validation results (e.g. errors, warnings). Use to check pipeline correctness before `use()`.

### Method
`validate(options: { pipeline: PipelineConfig | Record<string, unknown>; source?: string }): Promise<Record<string, unknown>>`

### Parameters
#### Options
- **pipeline** (PipelineConfig | Record<string, unknown>) - Required - The pipeline configuration object or a record representing it.
- **source** (string) - Optional - Source code for the pipeline.

### Returns
- **Promise<Record<string, unknown>>** - A promise that resolves to an object containing validation results.
```

--------------------------------

### Question Object

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/sdk/python-sdk.md

The `Question` object, from `rocketride.schema`, is used to construct detailed prompts for the AI. You can add instructions, examples, context, history, and documents to guide the AI's response.

```APIDOC
## Question

From `rocketride.schema`. Build a question for `client.chat(token=..., question=question)`. Add instructions, examples, context, history, and documents to steer the AI.

### Constructor
```python
Question(
    type: QuestionType = QuestionType.QUESTION,
    filter: DocFilter = None,
    expectJson: bool = False,
    role: str = '',
)
```
`QuestionType`: `QUESTION`, `SEMANTIC`, `KEYWORD`, `GET`, `PROMPT`. Default type is `QUESTION`. Default filter and `expectJson=False`, `role=''` if omitted.

### Methods
- **addInstruction** (`addInstruction(self, title: str, instruction: str)`): Adds an instruction (e.g. "Use bullet points").
- **addExample** (`addExample(self, given: str, result: dict | list | str)`): Adds an example input/output; `result` can be dict/list (JSON-serialized).
- **addContext** (`addContext(self, context: str | dict | List[str] | List[dict])`): Adds context.
- **addHistory** (`addHistory(self, item: QuestionHistory)`): Adds a history item for multi-turn chat.
- **addQuestion** (`addQuestion(self, question: str)`): Appends the question text.
- **addDocuments** (`addDocuments(self, documents: Doc | List[Doc])`): Adds documents for the AI to reference.
- **getPrompt** (`getPrompt(self, has_previous_json_failed: bool = False) -> str`): Returns the full prompt (internal).
```

--------------------------------

### Chat with Instructions and Parse JSON Answer

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/sdk/python-sdk.md

Engages in a chat interaction, providing instructions and examples to guide the AI's response, and then parses the JSON output. Use when expecting structured data from the chat model.

```python
import asyncio
from rocketride import RocketRideClient
from rocketride.schema import Question, Answer

async def main():
    async with RocketRideClient(uri="https://cloud.rocketride.ai", auth="my-key") as client:
        result = await client.use(filepath="chat_pipeline.json")
        token = result["token"]
        question = Question(expectJson=True)
        question.addInstruction("Format", "Return a JSON object with keys: summary, keywords.")
        question.addExample("Summarize X", {"summary": "...", "keywords": ["a", "b"]})
        question.addQuestion("Summarize the main points and list keywords.")
        response = await client.chat(token=token, question=question)
        answer_text = response.get("data", {}).get("answer") or (response.get("answers") or [None])[0]
        structured = Answer().parseJson(answer_text) if answer_text else None
        print(structured)
        await client.terminate(token)

asyncio.run(main())
```

--------------------------------

### Serve Production Build Locally

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/README.md

Test the production build locally before deploying. The 'build' folder is served at http://localhost:3000/.

```bash
npm run serve
```

--------------------------------

### Install rocketride-mcp

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/mcp_server/rocketride-mcp-server/rocketride-mcp-server.md

Install the rocketride-mcp package using pip. Requires Python 3.10+ and rocketride-client-python >= 1.1.0.

```bash
pip install rocketride-mcp
```

--------------------------------

### Using Prompts Programmatically

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/mcp_server/rocketride-mcp-server/rocketride-mcp-server.md

Shows how to list available prompts and retrieve rendered prompts using the session object.

```APIDOC
## Using Prompts Programmatically

Interact with prompts programmatically using the session object.

### List Available Prompts
```python
prompts = await session.list_prompts()
```

### Get a Rendered Prompt
```python
result = await session.get_prompt("analyze-document", arguments={
    "pipeline": "my-pipeline",
    "query": "Summarize the key findings"
})
# result.messages[0].content.text contains the rendered message
```
```

--------------------------------

### Instantiate RocketRideClient

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/sdk/node-sdk.md

Create a client instance with optional authentication and URI. The client does not connect until `connect()` is called.

```typescript
const client = new RocketRideClient({ auth: 'my-key', uri: 'https://cloud.rocketride.ai' });
await client.connect();
```

--------------------------------

### Get Task Status

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/api/get-task-status-method/get-task-status-method.md

Retrieves the current status of a task. This method communicates via the RocketRide DAP protocol over WebSocket. The equivalent HTTP endpoint is GET /task?token={token}.

```APIDOC
## GET /task

### Description
Retrieves the current status of a task.

### Method
GET

### Endpoint
/task

### Query Parameters
- **token** (string) - Required - The token identifying the task.

### Response
#### Success Response (200)
- **TASK_STATUS** (object) - The full task status object.

### Response Example
```json
{
  "name": "text_analyzer",
  "project_id": "my-project",
  "state": 3,
  "completed": false,
  "startTime": 1700000000.0,
  "endTime": 0.0,
  "totalCount": 100,
  "completedCount": 45,
  "failedCount": 2,
  "rateCount": 5,
  "errors": [],
  "warnings": [],
  "metrics": {
    "cpu_percent": 25.3,
    "cpu_memory_mb": 512.0,
    "gpu_memory_mb": 1024.0
  },
  "tokens": {
    "cpu_utilization": 1.5,
    "cpu_memory": 0.8,
    "gpu_memory": 2.1,
    "total": 4.4
  },
  "pipeflow": {
    "totalPipes": 2,
    "byPipe": {
      "0": ["source", "transform", "filter"],
      "1": ["source", "transform"]
    }
  }
}
```

### Error Handling
- **RuntimeError** / **Error**: Status retrieval failed (e.g., invalid token, server error).
- **Authentication error**: Invalid or missing API key.
```

--------------------------------

### Map URL

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/tools/firecrawl/firecrawl.md

Discovers all URLs within a given website, starting from a root URL.

```APIDOC
## firecrawl.map_url

### Description
Discovers all URLs within a website.

### Parameters
#### Path Parameters
- None

#### Query Parameters
- None

#### Request Body
- **url** (string) - Required - Root URL to map

### Request Example
```json
{
  "url": "https://example.com"
}
```

### Response
#### Success Response (200)
- **links** (array) - An array of discovered links across the site.
```

--------------------------------

### Build Production Site

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/README.md

Generate static HTML, JavaScript, and CSS files for production deployment. The output is placed in the 'build' folder.

```bash
npm run build
```

--------------------------------

### Initialize Question with Options

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/sdk/node-sdk.md

Constructs a new Question object, optionally specifying the question type, document filter, JSON expectation, and AI role.

```typescript
const question = new Question({
  type: QuestionType.PROMPT,
  expectJson: true,
  role: 'developer'
});
```

--------------------------------

### Create DataPipe (Python)

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/api/send-method/send-method.md

Initializes a streaming data pipe for sending large datasets in chunks. Recommended to use with a context manager.

```python
async with await client.pipe(token, mime_type='text/csv') as pipe:
    for chunk in csv_chunks:
        await pipe.write(chunk.encode())
    result = await pipe.close()
```

--------------------------------

### RocketRide Client with Context Manager

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/sdk/python-sdk.md

Use the RocketRide client within an asynchronous context manager for recommended usage. This example shows running a pipeline defined inline, sending JSON data, and checking task status.

```python
import asyncio
from rocketride import RocketRideClient

async def main():
    async with RocketRideClient(uri="wss://cloud.rocketride.ai", auth="my-key") as client:
        result = await client.use(pipeline={"pipeline": my_pipeline_config})
        token = result["token"]
        await client.send(token, '{"data": 1}')
        status = await client.get_task_status(token)
        print(status)
        await client.terminate(token)

asyncio.run(main())
```

--------------------------------

### Add Instructions to a Question

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/sdk/python-sdk.md

Use the `addInstruction` method to provide specific guidance to the AI, such as formatting requirements for the answer.

```python
question.addInstruction(title='Formatting', instruction='Use bullet points')
```

--------------------------------

### Close DataPipe and Get Result

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/sdk/node-sdk.md

Finalizes the streaming upload and retrieves the processing result from the server. This operation is idempotent if the pipe is already closed.

```typescript
const result = await pipe.close();
```

--------------------------------

### Send Multiple Files with Metadata (Python)

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/api/send-method/send-method.md

Uploads a list of files with optional metadata and MIME types. Ensure the client is initialized with authentication.

```python
from rocketride import RocketRideClient

async with RocketRideClient(auth='your-api-key') as client:
    result = await client.use(filepath='document_processor.json')
    token = result['token']

    # Simple file list
    files = ['document1.pdf', 'data.csv', 'report.docx']
    results = await client.send_files(files, token)

    for r in results:
        if r['action'] == 'complete':
            print(f"Uploaded {r['filepath']} in {r['upload_time']:.2f}s")
        else:
            print(f"Failed {r['filepath']}: {r['error']}")

    # With metadata and MIME types
    files = [
        ('report.pdf', {'department': 'finance'}),
        ('data.csv', {'type': 'quarterly'}, 'text/csv'),
    ]
    results = await client.send_files(files, token)
```

--------------------------------

### Get Task Status Method Signature (TypeScript)

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/api/get-task-status-method/get-task-status-method.md

Asynchronous method signature for retrieving task status in TypeScript. Requires an authentication token.

```typescript
const status = await client.getTaskStatus(token);
```

--------------------------------

### Get Task Status Method Signature (Python)

Source: https://github.com/rocketride-org/rocketride-docs/blob/main/docs/api/get-task-status-method/get-task-status-method.md

Asynchronous method signature for retrieving task status in Python. Requires an authentication token.

```python
status = await client.get_task_status(token)
```