Tool collections - Slide Framework

Overview

This page provides detailed documentation for each tool collection in Lye, including parameters, return values, and usage examples.

WEB_TOOLS

Tools for web browsing, searching, and content extraction.

web-fetch_page

Fetches content from a web page in text or HTML format.

url

string

required

The URL to fetch

format

string

default:"text"

Output format - “text” for readable content, “html” for raw HTML

headers

object

Custom headers to send with request

# Example usage
thread.add_message(Message(
    role="user",
    content="Get the content from https://example.com"
))

web-search

Search the web using Google.

query

string

required

The search query

num_results

integer

default:"5"

Number of results to return (max 10)

# Example usage
thread.add_message(Message(
    role="user",
    content="Search for recent AI developments"
))

web-download_file

Download files from URLs.

url

string

required

URL of the file to download

headers

object

Custom headers for the request

Returns downloaded file as attachment.

FILES_TOOLS

Tools for file system operations.

files-read_file

Read contents of a file.

path

string

required

Path to the file to read

encoding

string

default:"utf-8"

File encoding

files-write_file

Write content to a file.

path

string

required

Path where to write the file

content

string

required

Content to write

encoding

string

default:"utf-8"

File encoding

create_dirs

boolean

default:"false"

Create parent directories if they don’t exist

files-list_directory

List contents of a directory.

path

string

default:"."

Directory path to list

recursive

boolean

default:"false"

List subdirectories recursively

include_hidden

boolean

default:"false"

Include hidden files (starting with .)

files-move_file

Move or rename a file.

source

string

required

Source file path

destination

string

required

Destination file path

files-copy_file

Copy a file.

source

string

required

Source file path

destination

string

required

Destination file path

files-delete_file

Delete a file.

path

string

required

Path to file to delete

files-create_directory

Create a directory.

path

string

required

Directory path to create

parents

boolean

default:"true"

Create parent directories if needed

files-search_files

Search for files matching a pattern.

pattern

string

required

Search pattern (supports wildcards)

IMAGE_TOOLS

Tools for image generation and analysis.

image-generate_image

Generate images using DALL-E 3.

prompt

string

required

Description of the image to generate

model

string

default:"dall-e-3"

Model to use: “dall-e-3” or “dall-e-2”

size

string

default:"1024x1024"

Image size: “1024x1024”, “1792x1024”, or “1024x1792” (DALL-E 3)

quality

string

default:"standard"

Image quality: “standard” or “hd” (DALL-E 3 only)

style

string

default:"vivid"

Style: “vivid” or “natural” (DALL-E 3 only)

Returns generated image as attachment.

image-analyze_image

Analyze images using GPT-4 Vision.

image_path

string

required

Path to image file or URL

prompt

string

default:"What do you see?"

Question about the image

detail

string

default:"auto"

Analysis detail: “low”, “high”, or “auto”

image-create_qr_code

Generate QR codes.

data

string

required

Data to encode in QR code

size

integer

default:"300"

QR code size in pixels

border

integer

default:"4"

Border size in modules

Returns QR code image as attachment.

image-resize_image

Resize images.

image_path

string

required

Path to image file

width

integer

Target width (maintains aspect if height not specified)

height

integer

Target height (maintains aspect if width not specified)

mode

string

default:"contain"

Resize mode: “contain”, “cover”, “fill”, or “exact”

image-convert_image

Convert between image formats.

image_path

string

required

Path to source image

output_format

string

required

Target format: “JPEG”, “PNG”, “WEBP”, “BMP”, “GIF”

quality

integer

default:"95"

Output quality (1-100, for lossy formats)

AUDIO_TOOLS

Tools for audio processing.

audio-transcribe

Transcribe audio using OpenAI Whisper.

audio_path

string

required

Path to audio file

model

string

default:"whisper-1"

Whisper model to use

language

string

Language code (e.g., “en”, “es”)

temperature

number

default:"0"

Sampling temperature (0-1)

COMMAND_LINE_TOOLS

System command execution.

run_terminal_command

Execute shell commands.

command

string

required

Command to execute

working_directory

string

default:"."

Directory to run command in

timeout

integer

default:"30"

Command timeout in seconds

shell

boolean

default:"true"

Run command in shell

SLACK_TOOLS

Slack integration tools.

slack-send_message

Send messages to Slack.

channel

string

required

Channel ID or name (e.g., “C1234567890” or “#general”)

text

string

required

Message text

thread_ts

string

Thread timestamp to reply to

blocks

array

Rich message blocks

slack-get_messages

Retrieve messages from a channel.

channel

string

required

Channel ID

limit

integer

default:"100"

Number of messages to retrieve

oldest

string

Oldest message timestamp

latest

string

Latest message timestamp

slack-list_channels

List available Slack channels.

types

string

default:"public_channel"

Channel types: “public_channel”, “private_channel”, “mpim”, “im”

exclude_archived

boolean

default:"true"

Exclude archived channels

slack-react_to_message

Add emoji reaction to a message.

channel

string

required

Channel ID

timestamp

string

required

Message timestamp

emoji

string

required

Emoji name (without colons)

NOTION_TOOLS

Notion workspace integration.

notion-create_page

Create a new Notion page.

parent_id

string

required

Parent page or database ID

title

string

required

Page title

content

string | array

required

Page content (text or blocks)

properties

object

Page properties for database items

notion-update_page

Update existing Notion page.

page_id

string

required

Page ID to update

content

string | array

New content

properties

object

Properties to update

notion-search

Search Notion workspace.

query

string

required

Search query

filter

object

Filter by object type: “page” or “database”

sort

object

Sort results by “last_edited_time”

BROWSER_TOOLS

Browser automation with Playwright.

browser-navigate

Navigate to a URL.

url

string

required

URL to navigate to

wait_until

string

default:"networkidle"

Wait condition: “load”, “domcontentloaded”, “networkidle”

browser-click

Click an element.

selector

string

required

CSS selector or text

timeout

integer

default:"30000"

Timeout in milliseconds

browser-type

Type text into an input.

selector

string

required

Input selector

text

string

required

Text to type

delay

integer

default:"0"

Delay between keystrokes (ms)

browser-screenshot

Take a screenshot.

path

string

Save screenshot to path

full_page

boolean

default:"false"

Capture full page

selector

string

Capture specific element

WANDB_TOOLS

Weights & Biases integration.

wandb-create_workspace

Create a W&B workspace.

name

string

required

Workspace name

project

string

required

W&B project name

config

object

Workspace configuration

wandb-log_metrics

Log metrics to W&B.

metrics

object

required

Metrics to log

step

integer

Step number

commit

boolean

default:"true"

Commit immediately

Usage Examples

Web research agent

from tyler import Agent, Thread, Message
from lye import WEB_TOOLS, FILES_TOOLS

agent = Agent(
    name="researcher",
    tools=[*WEB_TOOLS, *FILES_TOOLS]
)

thread = Thread()
thread.add_message(Message(
    role="user",
    content="Research the latest developments in quantum computing and save a summary to research.md"
))

result = await agent.run(thread)

Creative assistant

from lye import IMAGE_TOOLS, AUDIO_TOOLS

agent = Agent(
    name="creative",
    tools=[*IMAGE_TOOLS, *AUDIO_TOOLS]
)

thread.add_message(Message(
    role="user",
    content="Generate an image of a futuristic city and transcribe this audio note",
    attachments=[audio_file]
))

DevOps Agent

from lye import COMMAND_LINE_TOOLS, FILES_TOOLS, SLACK_TOOLS

agent = Agent(
    name="devops",
    tools=[*COMMAND_LINE_TOOLS, *FILES_TOOLS, *SLACK_TOOLS]
)

thread.add_message(Message(
    role="user",
    content="Check system status, create a report, and notify the team on Slack"
))

Documentation Index

​Overview

​WEB_TOOLS

​web-fetch_page

​web-search

​web-download_file

​FILES_TOOLS

​files-read_file

​files-write_file

​files-list_directory

​files-move_file

​files-copy_file

​files-delete_file

​files-create_directory

​files-search_files

​IMAGE_TOOLS

​image-generate_image

​image-analyze_image

​image-create_qr_code

​image-resize_image

​image-convert_image

​AUDIO_TOOLS

​audio-transcribe

​COMMAND_LINE_TOOLS

​run_terminal_command

​SLACK_TOOLS

​slack-send_message

​slack-get_messages

​slack-list_channels

​slack-react_to_message

​NOTION_TOOLS

​notion-create_page

​notion-update_page

​notion-search

​BROWSER_TOOLS

​browser-navigate

​browser-click

​browser-type

​browser-screenshot

​WANDB_TOOLS

​wandb-create_workspace

​wandb-log_metrics

​Usage Examples

​Web research agent

​Creative assistant

​DevOps Agent

Overview

WEB_TOOLS

web-fetch_page

web-search

web-download_file

FILES_TOOLS

files-read_file

files-write_file

files-list_directory

files-move_file

files-copy_file

files-delete_file

files-create_directory

files-search_files

IMAGE_TOOLS

image-generate_image

image-analyze_image

image-create_qr_code

image-resize_image

image-convert_image

AUDIO_TOOLS

audio-transcribe

COMMAND_LINE_TOOLS

run_terminal_command

SLACK_TOOLS

slack-send_message

slack-get_messages

slack-list_channels

slack-react_to_message

NOTION_TOOLS

notion-create_page

notion-update_page

notion-search

BROWSER_TOOLS

browser-navigate

browser-click

browser-type

browser-screenshot

WANDB_TOOLS

wandb-create_workspace

wandb-log_metrics

Usage Examples

Web research agent

Creative assistant

DevOps Agent