Add memory management section to simple vector store (#3002)

Co-authored-by: Justin Ellingwood <justin@n8n.io>

Author: OlegIvaniv

docs/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstoreinmemory.md

@@ -20,6 +20,11 @@ The simple vector storage described here is different to the AI memory nodes suc
 This node creates a [vector database](/glossary.md#ai-vector-store) in the app memory.
 ///
 
+
+/// warning | For development use only
+This node stores data in memory only and isn't recommended for production use. All data is lost when n8n restarts and may also be purged in low-memory conditions.
+///
+
 ## Node usage patterns
 
 You can use the Simple Vector Store node in the following patterns.
@@ -48,6 +53,25 @@ Another pattern uses the [Vector Store Question Answer Tool](/integrations/built
 
 The [connections flow](https://n8n.io/workflows/2465-building-your-first-whatsapp-chatbot/) in this case would look like this: AI agent (tools connector) -> Vector Store Question Answer Tool (Vector Store connector) -> Simple Vector store.
 
+## Memory Management
+
+The Simple Vector Store implements memory management to prevent excessive memory usage:
+
+- Automatically cleans up old vector stores when memory pressure increases
+- Removes inactive stores that haven't been accessed for a configurable amount of time
+- Each workflow gets its own isolated storage space identified by the workflow ID and memory key
+
+### Configuration Options
+
+You can control memory usage with these environment variables:
+
+ | Variable                      | Type   | Default | Description                                                                         |
+ |-------------------------------|--------|---------|-------------------------------------------------------------------------------------|
+ | `N8N_VECTOR_STORE_MAX_MEMORY` | Number | -1      | Maximum memory in MB allowed for all vector stores combined (-1 to disable limits). |
+ | `N8N_VECTOR_STORE_TTL_HOURS`  | Number | -1      | Hours of inactivity after which a store gets removed (-1 to disable TTL).           |
+
+On n8n Cloud, these values are preset to 100MB (about 8,000 documents, depending on document size and metadata) and 7 days respectively. For self-hosted instances, both values default to -1(no memory limits or time-based cleanup).
+
 ## Node parameters
 
 --8<-- "_snippets/integrations/builtin/cluster-nodes/vector-store-mode.md"