Added descriptions of Message and Keyword agent components (#4512)

### What problem does this PR solve?

### Type of change


- [x] Documentation Update
This commit is contained in:
writinwaters
2025-01-16 19:47:15 +08:00
committed by GitHub
parent 4946e43941
commit c0799c53b3
5 changed files with 117 additions and 6 deletions

View File

@ -7,7 +7,9 @@ slug: /categorize_component
The component that classifies user inputs and applies strategies accordingly.
> The **Categorize** component is usually the downstream of the **Interact** component.
---
The **Categorize** component is usually the downstream of the **Interact** component.
## Scenarios
@ -91,12 +93,12 @@ Additional examples that may help the LLM determine which inputs belong in this
Examples are more helpful than the description if you want the LLM to classify particular cases into this category.
:::
#### To
#### Next step
Specifies the downstream component of this category.
- *Once you specify the ID of the downstream component, a link is established between this category and the corresponding component.*
- *If you manually link this category to a downstream component on the canvas, the ID of that component is auto-populated.*
- Once you specify the ID of the downstream component, a link is established between this category and the corresponding component.
- If you manually link this category to a downstream component on the canvas, the ID of that component is auto-populated.
## Examples