From e704c23b94bd8d13278799d954778a035089f7aa Mon Sep 17 00:00:00 2001
From: Naman <namanaaditya0611@gmail.com>
Date: Tue, 11 Nov 2025 10:58:57 +0530
Subject: chore: improved docs for document/by-id endpoint, added a couple of
 warnings based on mintlify questions (#550)

Co-authored-by: Naman Bansal <namanbansal@Namans-Macbook-Air.local>
---
 apps/docs/memory-api/track-progress.mdx       |  2 ++
 apps/docs/search/overview.mdx                 | 42 +++++++++++++++++++++++++++
 apps/docs/update-delete-memories/overview.mdx |  6 ++++
 3 files changed, 50 insertions(+)

(limited to 'apps')

diff --git a/apps/docs/memory-api/track-progress.mdx b/apps/docs/memory-api/track-progress.mdx
index 97a7f5bc..1d02cc0d 100644
--- a/apps/docs/memory-api/track-progress.mdx
+++ b/apps/docs/memory-api/track-progress.mdx
@@ -154,6 +154,8 @@ curl -X GET "https://api.supermemory.ai/v3/documents/doc_abc123" \
 }
 ```
 
+For more comprehensive information on the get documents by ID endpoint, refer to the [API reference.](/api-reference/manage-documents/get-document)
+
 ## Status Values
 
 | Status | Description | Typical Duration |
diff --git a/apps/docs/search/overview.mdx b/apps/docs/search/overview.mdx
index d95b611d..b6356202 100644
--- a/apps/docs/search/overview.mdx
+++ b/apps/docs/search/overview.mdx
@@ -285,6 +285,48 @@ Companies like Composio [Rube.app](https://rube.app) use memories search for let
 
 The `/v4/search` endpoint searches through and returns memories.
 
+## Direct Document Retrieval
+
+If you don't need semantic search and just want to retrieve a specific document you've uploaded by its ID, use the GET document endpoint:
+
+`GET /v3/documents/{id}`
+
+This is useful when:
+- You know the exact document ID
+- You want to retrieve the full document content and metadata
+- You need to check processing status or document details
+
+<CodeGroup>
+
+```typescript TypeScript
+// Get a specific document by ID
+const document = await client.memories.get("doc_abc123");
+
+console.log(document.content);    // Full document content
+console.log(document.status);     // Processing status
+console.log(document.metadata);   // Document metadata
+console.log(document.summary);    // AI-generated summary
+```
+
+```python Python
+# Get a specific document by ID
+document = client.memories.get("doc_abc123")
+
+print(document.content)    # Full document content
+print(document.status)     # Processing status
+```
+
+```bash cURL
+curl -X GET "https://api.supermemory.ai/v3/documents/{YOUR-DOCUMENT-ID}" \
+  -H "Authorization: Bearer $SUPERMEMORY_API_KEY"
+```
+
+</CodeGroup>
+
+<Note>
+This endpoint returns the complete document with all fields including content, metadata, containerTags, summary, and processing status. For more details, see the [API reference](/api-reference/manage-documents/get-document).
+</Note>
+
 ## Search Flow Architecture
 
 ### Document Search (`/v3/search`) Flow
diff --git a/apps/docs/update-delete-memories/overview.mdx b/apps/docs/update-delete-memories/overview.mdx
index f708a561..926e2971 100644
--- a/apps/docs/update-delete-memories/overview.mdx
+++ b/apps/docs/update-delete-memories/overview.mdx
@@ -151,6 +151,12 @@ curl -X POST "https://api.supermemory.ai/v3/documents" \
 The `customId` enables idempotency across all endpoints. The `memoryId` doesn't support idempotency, only the `customId` does.
 </Note>
 
+<Warning> 
+
+The `customId` can have a maximum length of 100 characters.
+
+</Warning>
+
 ## Single Delete
 
 Delete individual memories by their ID. This is a permanent hard delete with no recovery mechanism.
-- 
cgit v1.2.3