From 568e97d013888ccdd1e2a7211f34c2281e76b389 Mon Sep 17 00:00:00 2001
From: Parth Sharma <109902593+parthshr370@users.noreply.github.com>
Date: Fri, 7 Nov 2025 23:11:35 +0530
Subject: [PATCH] [docs] graph memory docs fix (#3728)
---
docs/open-source/features/graph-memory.mdx | 10 +++++++---
docs/platform/features/graph-memory.mdx | 9 ++++++---
2 files changed, 13 insertions(+), 6 deletions(-)
diff --git a/docs/open-source/features/graph-memory.mdx b/docs/open-source/features/graph-memory.mdx
index 2817700a1..f8c24bbc9 100644
--- a/docs/open-source/features/graph-memory.mdx
+++ b/docs/open-source/features/graph-memory.mdx
@@ -15,7 +15,7 @@ Graph Memory extends Mem0 by persisting nodes and edges alongside embeddings, so
## How Graph Memory Maps Context
-Mem0 extracts entities and relationships from every memory write, stores embeddings in your vector database, and mirrors relationships in a graph backend. On retrieval, vector search narrows candidates, then the graph supplies context and re-ranks results.
+Mem0 extracts entities and relationships from every memory write, stores embeddings in your vector database, and mirrors relationships in a graph backend. On retrieval, vector search narrows candidates while the graph returns related context alongside the results.
```mermaid
graph LR
@@ -37,8 +37,8 @@ Mem0’s extraction LLM identifies entities, relationships, and timestamps from
Embeddings land in your configured vector database while nodes and edges flow into a Bolt-compatible graph backend (Neo4j, Memgraph, Neptune, or Kuzu).
-
-`memory.search` first performs vector similarity, then follows connected nodes to boost (or filter) answers before optionally handing results to a reranker.
+
+`memory.search` performs vector similarity (optionally reranked by your configured reranker) and returns the results list. Graph Memory runs in parallel and adds related entities in the `relations` array—it does not reorder the vector hits automatically.
@@ -162,6 +162,10 @@ results.results.forEach((hit) => {
Expect to see **Alice met Bob at GraphConf 2025** in the output. In Neo4j Browser run `MATCH (p:Person)-[r]->(q:Person) RETURN p,r,q LIMIT 5;` to confirm the edge exists.
+
+Graph Memory enriches responses by adding related entities in the `relations` key. The ordering of `results` always comes from vector search (plus any reranker you configure); graph edges do not reorder those hits automatically.
+
+
## Operate Graph Memory Day-to-Day
diff --git a/docs/platform/features/graph-memory.mdx b/docs/platform/features/graph-memory.mdx
index a525a0a46..64579df9f 100644
--- a/docs/platform/features/graph-memory.mdx
+++ b/docs/platform/features/graph-memory.mdx
@@ -14,8 +14,8 @@ This feature allows your AI applications to understand connections between entit
The Graph Memory feature analyzes how each entity connects and relates to each other. When enabled:
1. Mem0 automatically builds a graph representation of entities
-2. Retrieval considers graph relationships between entities
-3. Results include entities that may be contextually important even if they're not direct semantic matches
+2. Vector search returns the top semantic matches (with any reranker you configure)
+3. Graph relations are returned alongside those results to provide additional context—they do not reorder the vector hits
## Using Graph Memory
@@ -179,6 +179,10 @@ console.log(results);
+
+`results` always reflects the vector search order (optionally reranked). Graph Memory augments that response by adding related entities in the `relations` array; it does not re-rank the vector results automatically.
+
+
### Retrieving All Memories with Graph Memory
When retrieving all memories, Graph Memory provides additional relationship context:
@@ -339,4 +343,3 @@ Graph Memory requires additional processing and may increase response times slig
If you have any questions, please feel free to reach out to us using one of the following methods:
-