From 545276318d8dd8a4fd890c09ffa525bd43f2a630 Mon Sep 17 00:00:00 2001
From: Gatefixer <313497061+lancedb-gatefixer[bot]@users.noreply.github.com>
Date: Wed, 5 Aug 2026 19:52:12 +0000
Subject: [PATCH] docs(nodejs): explain opening existing LangChain tables

---
 nodejs/README.md | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/nodejs/README.md b/nodejs/README.md
index 2ca1be7b0..6c368cba8 100644
--- a/nodejs/README.md
+++ b/nodejs/README.md
@@ -30,6 +30,27 @@ const results = await table.vectorSearch([0.1, 0.3]).limit(20).toArray();
 console.log(results);
 ```
 
+### Use an Existing Table with LangChain
+
+When wrapping an existing table with `@langchain/community`, open the table
+with LanceDB and pass the resulting table handle to LangChain. The LangChain
+`uri` and `tableName` options are used when creating a table; they do not open
+an existing table for search.
+
+```javascript
+import { LanceDB as LangChainLanceDB } from "@langchain/community/vectorstores/lancedb";
+import * as lancedb from "@lancedb/lancedb";
+
+const db = await lancedb.connect("data/sample-lancedb");
+const table = await db.openTable("my_table");
+const vectorStore = new LangChainLanceDB(embeddings, { table });
+
+const results = await vectorStore.similaritySearchVectorWithScore(
+  queryVector,
+  5,
+);
+```
+
 The [quickstart](https://docs.lancedb.com/quickstart/) contains more complete examples.
 
 ## Development