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

# Python

> Reference documentation for the `hunch` Python module available in the Code Runner

# Functions

## `hunch.output`

Appends the given values to the output file. This function has a similar
signature to the built-in `print`.

**Parameters:**

* `*values` *object* : The values to be written to the output.
* `sep` *Optional\[str]* : The separator between values. Defaults to a space.
* `end` *Optional\[str]* : The string appended after the last value. Defaults to a newline.

**Example:**

```python theme={null}
import hunch

# Appends "Hello World\n\n" to the output file
hunch.output("Hello", "World", sep=" ", end="\n\n")
```

***

## `hunch.input`

Loads and returns the input JSON.

**Returns:**

* *[Input](#class-hunch-input)* : The validated input data

**Example:**

```python theme={null}
import hunch

# Fetch the input data
input_data = hunch.input()
```

***

## `hunch.compiled_prompt`

Gets the entire compiled prompt.

**Parameters:**

* `instructions` *bool* : Whether to include the instructions of the code runner block. Defaults to false.
* `titles` *bool* : Whether to include the titles of the blocks. Defaults to true.

**Returns:**

* *str* : The compiled prompt

**Example:**

```python theme={null}
import hunch

prompt = hunch.compiled_prompt(instructions=True, titles=False)
```

***

## `hunch.extract_url`

Extracts the first URL from the upstream blocks.

**Returns:**

* *str* : The first URL found.

**Raises:**

* *[Error](#class-hunch-error)* : If no URL is found

**Example:**

```python theme={null}
import hunch

url = hunch.extract_url()
```

***

## `hunch.extract_urls`

Extracts all URLs from the upstream blocks.

**Returns:**

* *list\[str]* : A list of all URLs found

**Example:**

```python theme={null}
import hunch

urls = hunch.extract_urls()
```

***

## `hunch.block`

Fetches an upstream block from the input.

**Parameters:**

* `title` *Optional\[str]* : The title of the block to fetch
* `ititle` *Optional\[str]* : The case-insensitive title of the block to fetch

**Returns:**

* *[Block](#class-hunch-block)* : The  block.

**Raises:**

* *[Error](#class-hunch-error)* : If the specified block is not found or if invalid arguments are provided.

**Example:**

```python theme={null}
import hunch

# Get by exact title
b = hunch.block(title="Introduction")

# Get by case-insensitive title
b = hunch.block(ititle="introduction")
```

***

# Classes

## class `hunch.Input`

**Attributes**

* `instructions` *Optional\[str]* : The instructions on the code runner block
* `files` *Optional\[list\[[File](#class-hunch-file)]]* : The files contained in the instructions
* `blocks` *list\[[Block](#class-hunch-block)]* : The blocks upstream of the code runner

***

## class `hunch.Block`

**Attributes**

* `title` *str* : The title of the block.
* `output` *str* : The output of the block or the content if the block is a content block
* `files` *Optional\[list\[[File](#class-hunch-file)]]* : The files contained in the block output

**Methods**

* `extract_url(self) -> str` : Extracts the first URL from the block output
* `extract_urls(self) -> list[str]` : Extracts all URLs from the block output

***

## class `hunch.File`

Represents a file contained in a block.

**Attributes**

* `media_type` *Optional\[str]* : The media type of the file (e.g. "application/pdf", "image/jpeg")
* `url` *str* : The URL to download the file
* `path` *Optional\[Path]*: The path to the file, if it has been downloaded

**Methods**

* `download(self, path: str | Path) -> None`: Downloads the file to the given path and updates the `path` attribute

***

## class `hunch.Error`

Raised when a hunch module specific error occurs.

**Example:**

```python theme={null}
import hunch

try:
    url = hunch.extract_url()
except hunch.Error:
    # no url found ...
```

***