Add links to vector search

pages/ai-ecosystem/graph-rag.mdx

@@ -57,6 +57,8 @@ being updated on-the-fly.
 Here are the most useful features in Memgraph to build a GraphRAG:
 
 - [Deep-path traversals](/advanced-algorithms/deep-path-traversal)
+- [Vector search](/querying/vector-search) (experimental) - Usually used in the first step of finding and extracting
+  relevant information (pivot search)
 - [Leiden community
   detection](/advanced-algorithms/available-algorithms/leiden_community_detection):
   Proven to be a better and faster version of Louvain community detection,
@@ -70,8 +72,7 @@ Here are the most useful features in Memgraph to build a GraphRAG:
 - [Dynamic PageRank](/advanced-algorithms/available-algorithms/pagerank_online)
 - [Text search](/querying/text-search)
 - [Run-time schema tracking](/querying/schema#run-time-schema-tracking)
-- **Coming soon** - Vector search - Usually used in the first
-  step of finding and extracting relevant information (pivot search)
+
 
 Here is how those features fit into the GraphRAG architecture:
 

pages/data-modeling/knowledge-graph.mdx

@@ -265,10 +265,10 @@ and to iterate until you get it right.
 To return back to the example, let's say LLM needs to answer the question "Are
 we able to execute Data Preprocessing project?".
 
-In the background, the question gets embedded, vector search is performed and
-pivot node is found. In this case, the pivot node is `(:Project {name:"Data
-Preprocessing"})`. The next step is relevance expansion, which is performed with
-the following query:
+In the background, the question gets embedded, [vector
+search](/querying/vector-search) is performed and pivot node is found. In this
+case, the pivot node is `(:Project {name:"Data Preprocessing"})`. The next step
+is relevance expansion, which is performed with the following query:
 
 ```cypher
 MATCH path=(p:Project {name:"Data Preprocessing"})-[r *..2]-(n) RETURN path;