The find_tools function in the Knit LangChain SDK allows you to discover tools that are available for integration with a specific app or the unified tools for a category.

The function will return a list of tools. You can then select and use these tools in your AI agents.

Discover Tools for an App

Parameters Overview

• app_id: Specify the app ID to find tools related to a specific app. You can find the list of apps here: https://developers.getknit.dev/reference/supported-apps

• entities: (Optional) Provide a list of entities if you're looking for tools handling specific data or functionalities.

• operation: (Optional) Define the type of operation (like "read" or "write") that the tool should support.

• include_unified_tools: Set this to True if you want to include Knit's Unified Tools for this app's category

• usecase: Search tools by your use case in plain English

Example Usage

Here's a quick example to demonstrate how you can use the find_tools function:

from knit_langchain import KnitLangChain

# Initialize the Knit SDK with your API key
knit = KnitLangChain(api_key="YOUR_KNIT_API_KEY")

# Find tools related to a specific app and operation
tools = knit.find_tools(app_id="charliehr", operation="read", usecase="I want to fetch the list of employees")

# Display tool information
for tool in tools:
    print(f"Tool ID: {tool.tool_id}")
    print(f"Title: {tool.title}")
    print(f"Description: {tool.description}")

Discover Unified Tools for a Category

Parameters Overview

• category_id: Use this to search Knit's Unified APIs tools by category. You can find the list of categories here: https://developers.getknit.dev/reference/supported-apps

• entities: (Optional) Provide a list of entities if you're looking for tools handling specific data or functionalities.

• operation: (Optional) Define the type of operation (like "read" or "write") that the tool should support.

• include_unified_tools: Must be set to True

• usecase: Search tools by your use case in plain English

Example Usage

Here's a quick example to demonstrate how you can use the find_tools function:

from knit_langchain import KnitLangChain

# Initialize the Knit SDK with your API key
knit = KnitLangChain(api_key="YOUR_KNIT_API_KEY")

# Find tools related to a specific app and operation
tools = knit.find_tools(category_id="ticketing", include_unified_tools=True, usecase="I want to add a comment to ticket")

# Display tool information
for tool in tools:
    print(f"Tool ID: {tool.tool_id}")
    print(f"Title: {tool.title}")
    print(f"Description: {tool.description}")

What It Returns

• The function returns a list of tool summaries, which are objects containing key information about each tool. Each tool summary includes:
  • tool_id: The unique identifier for the tool.
  • title: The name of the tool.
  • description: A brief description of the tool's functionality.
  • entities: The entities associated with the tool (if any).
  • operation: The operation the tool supports (if specified).
  • is_unified_tool: Indicates whether the tool is a Knit's Unified APIs tool.