update Window Buffer Memory to Simple Memory (#2930)

This commit is contained in:
Nick Veitch
2025-03-04 10:41:47 +00:00
committed by GitHub
parent b515133074
commit b568d9289a
14 changed files with 33 additions and 33 deletions

View File

@@ -54,7 +54,7 @@
{
"parameters": {},
"id": "d702f647-1fa7-4b4f-91b1-e0152326ea11",
"name": "Window Buffer Memory",
"name": "Simple Memory",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"typeVersion": 1.2,
"position": [
@@ -291,7 +291,7 @@
]
]
},
"Window Buffer Memory": {
"Simple Memory": {
"ai_memory": [
[
{

View File

@@ -4,7 +4,7 @@
{
"parameters": {},
"id": "a60c8572-56c1-4bf3-8352-a6419a475887",
"name": "Window Buffer Memory",
"name": "Simple Memory",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"typeVersion": 1.1,
"position": [
@@ -280,7 +280,7 @@
],
"pinData": {},
"connections": {
"Window Buffer Memory": {
"Simple Memory": {
"ai_memory": [
[
{

View File

@@ -201,7 +201,7 @@
{
"parameters": {},
"id": "c3d20569-1374-4f8d-8779-23b98952d124",
"name": "Window Buffer Memory",
"name": "Simple Memory",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
800,
@@ -559,7 +559,7 @@
]
]
},
"Window Buffer Memory": {
"Simple Memory": {
"ai_memory": [
[
{

View File

@@ -59,7 +59,7 @@
{
"parameters": {},
"id": "29678c05-9a48-41ec-9c5c-af36ee0d7fc6",
"name": "Window Buffer Memory",
"name": "Simple Memory",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
860,
@@ -343,7 +343,7 @@
]
]
},
"Window Buffer Memory": {
"Simple Memory": {
"ai_memory": [
[
{

View File

@@ -61,7 +61,7 @@
180
],
"id": "afbab05c-1e87-4f7a-9d66-c86f9db1ec64",
"name": "Window Buffer Memory"
"name": "Simple Memory"
}
],
"pinData": {},
@@ -88,7 +88,7 @@
]
]
},
"Window Buffer Memory": {
"Simple Memory": {
"ai_memory": [
[
{

View File

@@ -13,7 +13,7 @@ Memory is a key part of AI chat services. The [memory](/glossary.md#ai-memory) k
To add memory to your AI workflow you can use either:
* [Window Buffer Memory](/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memorybufferwindow/index.md): stores a customizable length of chat history for the current session. This is the easiest to get started with.
* [Simple Memory](/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memorybufferwindow/index.md): stores a customizable length of chat history for the current session. This is the easiest to get started with.
* One of the memory services that n8n provides nodes for. These include:
* [Motorhead](/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memorymotorhead.md)
* [Redis Chat Memory](/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memoryredischat.md)

View File

@@ -152,7 +152,7 @@ The chat model is now giving us useful output, but there is something wrong with
1. In order to remember what has happened in the conversation, the AI Agent needs to preserve context. We can do this by adding memory to the **AI Agent** node. On the canvas click on the <span class="inline-image">![Add node icon](/_images/try-it-out/add-node-small.png){.off-glb}</span> on the bottom of the **AI Agent** node labeled "Memory".
1. From the panel which appears, select "Window Buffer Memory". This will use the memory from the instance running n8n, and is usually sufficient for simple usage. The default value of 5 interactions should be sufficient here, but remember where this option is if you may want to change it later.
1. From the panel which appears, select "Simple Memory". This will use the memory from the instance running n8n, and is usually sufficient for simple usage. The default value of 5 interactions should be sufficient here, but remember where this option is if you may want to change it later.
1. Repeat the exercise of having a conversation above, and see that the AI Agent now remembers your name.

View File

@@ -111,7 +111,7 @@ Available nodes:
* [Motorhead](/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memorymotorhead.md)
* [Redis Chat Memory](/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memoryredischat.md)
* [Postgres Chat Memory](/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memorypostgreschat.md)
* [Window Buffer Memory](/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memorybufferwindow/index.md)
* [Simple Memory](/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memorybufferwindow/index.md)
* [Xata](/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memoryxata.md)
* [Zep](/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memoryzep.md)

View File

@@ -29,13 +29,13 @@ You might see this in one of two scenarios:
2. When you've set the **Prompt** to **Connected Chat Trigger Node** and the incoming data has null values.
* To resolve, remove any null values from the `chatInput` field of the input node.
## Error in sub-node Window Buffer Memory
## Error in sub-node Simple Memory
This error displays when n8n runs into an issue with the [Window Buffer Memory](/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memorybufferwindow/index.md) sub-node.
This error displays when n8n runs into an issue with the [Simple Memory](/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memorybufferwindow/index.md) sub-node.
It most often occurs when your workflow or the workflow template you copied uses an older version of the Window Buffer Memory node.
It most often occurs when your workflow or the workflow template you copied uses an older version of the Simple memory node (previously known as "Window Buffer Memory").
Try removing the Window Buffer Memory node from your workflow and re-adding it, which will guarantee you're using the latest version of the node.
Try removing the Simple Memory node from your workflow and re-adding it, which will guarantee you're using the latest version of the node.
## A Chat Model sub-node must be connected error

View File

@@ -15,7 +15,7 @@ On this page, you'll find the node parameters for the In Memory Vector Store nod
--8<-- "_snippets/integrations/builtin/cluster-nodes/sub-node-expression-resolution.md"
/// note | This node is different to AI memory nodes
The in-memory storage described here is different to the AI memory nodes such as [Window Buffer Memory](/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memorybufferwindow/index.md).
The in-memory storage described here is different to the AI memory nodes such as [Simple Memory](/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memorybufferwindow/index.md).
This node creates a [vector database](/glossary.md#ai-vector-store) in the app memory.
///

View File

@@ -1,18 +1,18 @@
---
#https://www.notion.so/n8n/Frontmatter-432c2b8dff1f43d4b1c8d20075510fe4
title: Window Buffer Memory node common issues
description: Documentation for common issues and questions in the Window Buffer Memory node in n8n, a workflow automation platform. Includes details of the issue and suggested solutions.
title: Simple Memory node common issues
description: Documentation for common issues and questions in the Simple Memory node in n8n, a workflow automation platform. Includes details of the issue and suggested solutions.
contentType: [integration, reference]
priority: high
---
# Window Buffer Memory node common issues
# Simple Memory node common issues
Here are some common errors and issues with the [Window Buffer Memory node](/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memorybufferwindow/index.md) and steps to resolve or troubleshoot them.
Here are some common errors and issues with the [Simple Memory node](/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memorybufferwindow/index.md) and steps to resolve or troubleshoot them.
## Single memory instance
If you add more than one Window Buffer Memory node to your workflow, all nodes access the same memory instance by default. Be careful when doing destructive actions that override existing memory contents, such as the override all messages operation in the [Chat Memory Manager](/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memorymanager.md) node. If you want more than one memory instance in your workflow, set different session IDs in different memory nodes.
If you add more than one Simple Memory node to your workflow, all nodes access the same memory instance by default. Be careful when doing destructive actions that override existing memory contents, such as the override all messages operation in the [Chat Memory Manager](/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memorymanager.md) node. If you want more than one memory instance in your workflow, set different session IDs in different memory nodes.
## Managing the Session ID

View File

@@ -1,19 +1,19 @@
---
#https://www.notion.so/n8n/Frontmatter-432c2b8dff1f43d4b1c8d20075510fe4
title: Window Buffer Memory node documentation
description: Learn how to use the Window Buffer Memory node in n8n. Follow technical documentation to integrate Window Buffer Memory node into your workflows.
title: Simple Memory node documentation
description: Learn how to use the Simple Memory node in n8n. Follow technical documentation to integrate Simple Memory node into your workflows.
contentType: [integration, reference]
priority: high
---
# Window Buffer Memory node
# Simple Memory node
Use the Window Buffer Memory node to [persist](/glossary.md#ai-memory) chat history in your workflow.
Use the Simple Memory node to [persist](/glossary.md#ai-memory) chat history in your workflow.
On this page, you'll find a list of operations the Window Buffer Memory node supports, and links to more resources.
On this page, you'll find a list of operations the Simple Memory node supports, and links to more resources.
/// warning | Don't use this node if running n8n in queue mode
If your n8n instance uses [queue mode](/hosting/scaling/queue-mode.md), this node doesn't work in an active production workflow. This is because n8n can't guarantee that every call to Window Buffer Memory will go to the same worker.
If your n8n instance uses [queue mode](/hosting/scaling/queue-mode.md), this node doesn't work in an active production workflow. This is because n8n can't guarantee that every call to Simple Memory will go to the same worker.
///
--8<-- "_snippets/integrations/builtin/cluster-nodes/sub-node-expression-resolution.md"

View File

@@ -34,9 +34,9 @@ When you configure a Chat Trigger node, you might experience problems fetching p
In Chat Triggers, the **Load Previous Session** option retrieves previous chat messages for a session using the `sessionID`. When you set the **Load Previous Session** option to **From memory**, it's almost always best to [connect the same memory node](/integrations/builtin/core-nodes/n8n-nodes-langchain.chattrigger/index.md#load-previous-session) to both the Chat Trigger and the Agent in your workflow:
1. In your **Chat Trigger** node, set the **Load Previous Session** option to **From Memory**. This is only visible if you've made the chat publicly available.
2. Attach a **Window Buffer Memory** node to the **Memory** connector.
3. Attach the same **Window Buffer Memory** node to **Memory** connector of your **Agent**.
4. In the **Window Buffer Memory** node, set **Session ID** to **Connected Chat Trigger Node**.
2. Attach a **Simple Memory** node to the **Memory** connector.
3. Attach the same **Simple Memory** node to **Memory** connector of your **Agent**.
4. In the **Simple Memory** node, set **Session ID** to **Connected Chat Trigger Node**.
One instance where you may want to attach separate memory nodes to your Chat Trigger and the Agent is if you want to set the **Session ID** in your memory node to **Define below**.

View File

@@ -931,7 +931,7 @@ nav:
- Common issues: integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmollama/common-issues.md
- Hugging Face Inference Model: integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmopenhuggingfaceinference.md
- Chat Memory Manager: integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memorymanager.md
- Window Buffer Memory:
- Simple Memory:
- integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memorybufferwindow/index.md
- Common issues: integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memorybufferwindow/common-issues.md
- Motorhead: integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memorymotorhead.md