OpenWebUI/docs
1
0
Fork 0
mirror of https://github.com/open-webui/docs synced 2025-06-16 11:28:36 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Update Native vs Default Tools

Browse Source
This commit is contained in:
ayana 2025-06-10 10:52:40 -07:00
parent 47b6c26985
commit 71c659bcea
1 changed files with 9 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
docs/features/plugin/tools/index.mdx
View File

@ -1,6 +1,6 @@
---
sidebar_position: 2
title: "⚙️ Tools"
sidebar_position: 2
title: "⚙️ Tools"
---
# ⚙️ What are Tools?
@ -24,7 +24,6 @@ Explore ready-to-use tools here:
---
## 📦 How to Install Tools
There are two easy ways to install Tools in Open WebUI:
@ -38,7 +37,6 @@ There are two easy ways to install Tools in Open WebUI:
---
## 🔧 How to Use Tools in Open WebUI
Once you've installed Tools (we’ll show you how below), here’s how to enable and use them:
@ -52,6 +50,7 @@ While chatting, click the ➕ icon in the input area. You’ll see a list of ava
💡 Tip: Enabling a Tool gives the model permission to use it — but it may not use it unless it's useful for the task.
### ✏️ Option 2: Enable by Default (Recommended for Frequent Use)
1. Go to: Workspace ➡️ Models
2. Choose the model you’re using (like GPT-4 or LLaMa2) and click the ✏️ edit icon.
3. Scroll down to the “Tools” section.
@ -85,7 +84,7 @@ Let’s break it down:
This is the default setting in Open WebUI.
Here, your LLM doesn’t need to natively support function calling. Instead, we guide the model using smart tool selection prompt template to select and use a Tool.
Here, your LLM doesn’t need to natively support function calling. Instead, we guide the model using smart tool selection prompt template to select and use a Tool. Open WebUI then interprets the model's response and executes the tool on the model's behalf.
✅ Works with almost any model
✅ Great way to unlock Tools with basic or local models
@ -93,7 +92,7 @@ Here, your LLM doesn’t need to natively support function calling. Instead, we
### 🟢 Native Mode (Function Calling Built-In)
If your model does support “native” function calling (like GPT-4o or GPT-3.5-turbo-1106), you can use this powerful mode to let the LLM decide — in real time — when and how to call multiple Tools during a single chat message.
If your model does support “native” function calling (like GPT-4o or GPT-3.5-turbo-1106), you can use this powerful mode to let the LLM decide — in real time — when and how to call multiple Tools during a single chat message. Open WebUI will send the model full specifications of available tools, which the model can then decide in real time when to use.
✅ Fast, accurate, and can chain multiple Tools in one response
✅ The most natural and advanced experience
@ -116,10 +115,10 @@ That’s it! Your chat is now using true native Tool support (as long as the mod
💡 Summary:
| Mode | Who it’s for | Pros | Cons |
|----------|----------------------------------|-----------------------------------------|--------------------------------------|
| Default | Any model | Broad compatibility, safer, flexible | May be less accurate or slower |
| Native | GPT-4o, etc. | Fast, smart, excellent tool chaining | Needs proper function call support |
| Mode | Who it’s for | Pros | Cons |
| ------- | ------------ | ------------------------------------ | ---------------------------------- |
| Default | Any model | Broad compatibility, safer, flexible | May be less accurate or slower |
| Native | GPT-4o, etc. | Fast, smart, excellent tool chaining | Needs proper function call support |
Choose the one that works best for your setup — and remember, you can always switch on the fly via Chat Controls.