You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
n8n releases a new minor version most weeks. The `latest` version is for production use. `next` is the most recent release. You should treat `next` as a beta: it may be unstable. To report issues, use the [forum](https://community.n8n.io/c/questions/12){:target=_blank .external-link}.
Copy file name to clipboardExpand all lines: docs/courses/level-one/chapter-4.md
+1-3
Original file line number
Diff line number
Diff line change
@@ -40,6 +40,4 @@ You will build this workflow in eight steps:
40
40
41
41
To build this workflow, you will need the credentials found in the email you received from n8n when you signed up for this course. If you haven't signed up already, you can do it [here](https://n8n-community.typeform.com/to/PDEMrevI?typeform-source=127.0.0.1){:target="_blank" .external-link}. If you haven't received a confirmation email after signing up, [contact us](mailto:[email protected]).
Copy file name to clipboardExpand all lines: docs/courses/level-one/index.md
+1-3
Original file line number
Diff line number
Diff line change
@@ -63,6 +63,4 @@ You can always **check your progress** throughout the course by entering your un
63
63
64
64
If you complete the milestones above, you will get [**a badge and an avatar**](https://community.n8n.io/badges/104/completed-n8n-course-level-1) in your forum profile. You can then share your profile and course verification ID to showcase your n8n skills to others.
65
65
66
-
<divstyle="text-align:center;">
67
-
<button style="font-weight: 600;padding: 20px 46px;border-radius: 30px;color: #fff;background-color: #ff6d5a;border-color: #ff6d5a;border: 1px solid #ff6d5a;font-size: 14px;"><a href="/courses/level-one/chapter-1/" style="color: #fff;">Let's get started!</a></button>
68
-
</div>
66
+
[Let's get started!](/courses/level-one/chapter-1.md){ .md-button }
Copy file name to clipboardExpand all lines: docs/courses/level-two/index.md
+1-3
Original file line number
Diff line number
Diff line change
@@ -51,6 +51,4 @@ You can always **check your progress** throughout the course by entering your un
51
51
52
52
If you successfully complete the milestones above, you will get [**a badge and an avatar**](https://community.n8n.io/badges/105/completed-n8n-course-level-2){:target="_blank" .external} in your forum profile. You can then share your profile and course verification ID to showcase your n8n skills to others.
53
53
54
-
<divstyle="text-align:center;">
55
-
<button style="font-weight: 600;padding: 20px 46px;border-radius: 30px;color: #fff;background-color: #ff6d5a;border-color: #ff6d5a;border: 1px solid #ff6d5a;font-size: 14px;"><a href="/courses/level-two/chapter-1/" style="color: #fff;">Let's get started!</a></button>
56
-
</div>
54
+
[Let's get started!](/courses/level-two/chapter-1.md){ .md-button }
Schema Preview exposes expected schema data from the previous node in the Node Editor without the user having to provide credentials or execute the node. This makes it possible to construct workflows without having to provide credentials in advance. The preview doesn't include mock data, but it does expose the expected fields, making it possible to select and incorporate them into the input of subsequent nodes.
11
+
12
+
## Using the preview
13
+
14
+
1. There must be a node with Schema Preview available in your workflow.
15
+
1. When clicking on the details of the next node in the sequence, the Schema Preview data will show up in the Node Editor where schema data would typically be exposed.
16
+
1. Use data from the Schema Preview just as you would other schemas - drag and drop fields as input into your node parameters and settings.
Copy file name to clipboardExpand all lines: docs/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.agent/index.md
+4-24
Original file line number
Diff line number
Diff line change
@@ -8,36 +8,16 @@ priority: critical
8
8
9
9
# AI Agent node
10
10
11
-
An [AI agent](/glossary.md#ai-agent) is an autonomous system that receives data, makes rational decisions, and acts within its environment to achieve specific goals. The AI agent's environment is everything the agent can access that isn't the agent itself, which might include customer queries, tools, or other context.
12
-
13
-
The AI Agent node gives you six LangChain agent options.
14
-
15
-
On this page, you'll find a summary of the available agents with links to more detailed pages on each, templates and examples, and links to more resources.
11
+
An [AI agent](/glossary.md#ai-agent) is an autonomous system that receives data, makes rational decisions, and acts within its environment to achieve specific goals. The AI agent's environment is everything the agent can access that isn't the agent itself. This agent uses external [tools](/glossary.md#ai-tool) and APIs to perform actions and retrieve information. It can understand the capabilities of different tools and determine which tool to use depending on the task.
16
12
17
13
/// note | Connect a tool
18
14
You must connect at least one tool [sub-node](/integrations/builtin/cluster-nodes/sub-nodes/index.md) to an AI Agent node.
19
15
///
20
16
21
-
## Available agents
22
-
23
-
n8n provides these agents:
24
-
25
-
*[**Tools Agent**](/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.agent/tools-agent.md) (default): This agent uses external [tools](/glossary.md#ai-tool) and APIs to perform actions and retrieve information. It can understand the capabilities of different tools and determine which tool to use depending on the task. This agent helps integrate LLMs with various external services and databases.
26
-
27
-
/// note | Begin here
28
-
n8n recommends using this agent for most use cases. It will handle most scenarios and provides the best experience when working with [tools](/advanced-ai/examples/understand-tools.md).
29
-
///
30
-
31
-
*[**Conversational Agent**](/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.agent/conversational-agent.md): This agent has human-like conversations. It can maintain context, understand user intent, and provide relevant answers. This agent is typically used for building chatbots, virtual assistants and customer support systems. If your preferred AI model doesn't support tool calling or you're handling simpler interactions, this agent is a good option.
32
-
*[**OpenAI Functions Agent**](/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.agent/openai-functions-agent.md): Use this agent with an [OpenAI functions model](https://platform.openai.com/docs/guides/gpt/function-calling){:target=_blank .external-link}. You must use the [OpenAI Chat Model](/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmchatopenai/index.md) with this agent.
33
-
*[**Plan and Execute Agent**](/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.agent/plan-execute-agent.md): This agent creates a high-level plan to solve the given task and then executes the plan step by step. It's most useful for tasks that require a structured approach and careful planning.
34
-
*[**ReAct Agent**](/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.agent/react-agent.md): This agent reasons about a given task, determines the necessary actions, and then executes them. It follows the cycle of reasoning and acting until it completes the task. The ReAct agent can break down complex tasks into smaller sub-tasks, prioritise them, and execute them one after the other.
35
-
36
-
/// note | No memory
37
-
The ReAct agent doesn't support memory sub-nodes. This means it can't recall previous prompts or simulate an ongoing conversation.
38
-
///
17
+
/// note | Agent type
18
+
Prior to version 1.82.0, the AI Agent had a setting for working as different agent types. This has now been removed and all AI Agent nodes work as a `Tools Agent` which was the recommended and most frequently used setting. If you're working with older versions of the AI Agent in workflows or templates, as long as they were set to 'Tools Agent', they should continue to behave as intended with the updated node.
19
+
///
39
20
40
-
*[**SQL Agent**](/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.agent/sql-agent.md): This agent uses a SQL database as a data source. It can understand natural language questions, convert them into SQL queries, execute the queries, and present the results in a user-friendly format. This agent is valuable for building natural language interfaces to databases.
41
21
42
22
## Templates and examples
43
23
<!-- see https://www.notion.so/n8n/Pull-in-templates-for-the-integrations-pages-37c716837b804d30a33b47475f6e3780 -->
Copy file name to clipboardExpand all lines: docs/integrations/builtin/core-nodes/n8n-nodes-base.splitinbatches.md
+4-3
Original file line number
Diff line number
Diff line change
@@ -8,20 +8,21 @@ priority: critical
8
8
9
9
# Loop Over Items
10
10
11
-
The Loop Over Items node helps you loop through data.
11
+
The Loop Over Items node helps you loop through data when needed.
12
12
13
13
The node saves the original incoming data, and with each iteration, returns a predefined amount of data through the **loop** output.
14
14
15
15
When the node execution completes, it combines all of the processed data and returns it through the **done** output.
16
16
17
17
## When to use the Loop Over Items node
18
18
19
-
By default, n8n nodes process input items one at a time. Depending on what you're trying to achieve, you often don't need the Loop Over Items node in your workflow. You can learn more about how n8n processes multiple items on the [looping in n8n](/flow-logic/looping.md) page.
19
+
By default, n8n nodes are designed to process a list of input items (with some exceptions, detailed below). Depending on what you're trying to achieve, you often don't need the Loop Over Items node in your workflow. You can learn more about how n8n processes multiple items on the [looping in n8n](/flow-logic/looping.md) page.
20
20
21
-
In particular, these two sections are of particular interest to the Loop Over Items node:
21
+
These links highlight some of the cases where the Loop Over Items node can be useful:
22
22
23
23
*[Loop until all items are processed](/flow-logic/looping.md#loop-until-all-items-are-processed): describes how the Loop Over Items node differs from normal item processing and when you might want to incorporate this node.
24
24
*[Node exceptions](/flow-logic/looping.md#node-exceptions): outlines specific cases and nodes where you may need to use the Loop Over Items node to manually build looping logic.
25
+
*[Avoiding rate limiting](/integrations/builtin/rate-limits.md): demonstrates how to batch API requests to avoid rate limits from other services.
0 commit comments