diff --git a/docs/core_docs/docs/integrations/vectorstores/libsql.mdx b/docs/core_docs/docs/integrations/vectorstores/libsql.mdx
index 2d836b54ae04..19a44cc4ac3c 100644
--- a/docs/core_docs/docs/integrations/vectorstores/libsql.mdx
+++ b/docs/core_docs/docs/integrations/vectorstores/libsql.mdx
@@ -10,9 +10,9 @@ This guide provides a quick overview for getting started with libSQL vector stor
 
 ## Integration details
 
-| Class               | Package                | JS support | Package latest                                                    |
+| Class               | Package                | PY support | Package latest                                                    |
 | ------------------- | ---------------------- | ---------- | ----------------------------------------------------------------- |
-| `LibSQLVectorStore` | `@langchain/community` | ✅         | ![npm version](https://img.shields.io/npm/v/@langchain/community) |
+| `LibSQLVectorStore` | `@langchain/community` | ❌         | ![npm version](https://img.shields.io/npm/v/@langchain/community) |
 
 ## Setup
 
@@ -54,7 +54,7 @@ libsql://[database-name]-[your-username].turso.io
 
 Execute the following SQL command to create a new table or add the embedding column to an existing table.
 
-Make sure to mopdify the following parts of the SQL:
+Make sure to modify the following parts of the SQL:
 
 - `TABLE_NAME` is the name of the table you want to create.
 - `content` is used to store the `Document.pageContent` values.
@@ -70,7 +70,7 @@ CREATE TABLE IF NOT EXISTS TABLE_NAME (
 );
 ```
 
-Now create an index on the `EMBEDDING_COLUMN` column:
+Now create an index on the `EMBEDDING_COLUMN` column - the index name is important!:
 
 ```sql
 CREATE INDEX IF NOT EXISTS idx_TABLE_NAME_EMBEDDING_COLUMN ON TABLE_NAME(libsql_vector_idx(EMBEDDING_COLUMN));
@@ -103,9 +103,8 @@ const libsqlClient = createClient({
 
 const vectorStore = new LibSQLVectorStore(embeddings, {
   db: libsqlClient,
-  tableName: "TABLE_NAME",
-  embeddingColumn: "EMBEDDING_COLUMN",
-  dimensions: 1536,
+  table: "TABLE_NAME",
+  column: "EMBEDDING_COLUMN",
 });
 ```
 
@@ -154,7 +153,7 @@ const similaritySearchWithScoreResults =
 
 for (const [doc, score] of similaritySearchWithScoreResults) {
   console.log(
-    `${score.toFixed(3)} ${doc.pageContent} [${JSON.stringify(doc.metadata)}`
+    `${score.toFixed(3)} ${doc.pageContent} [${JSON.stringify(doc.metadata)}]`
   );
 }
 ```
diff --git a/libs/langchain-community/src/vectorstores/libsql.ts b/libs/langchain-community/src/vectorstores/libsql.ts
index 3740c62d99db..05c77da7489c 100644
--- a/libs/langchain-community/src/vectorstores/libsql.ts
+++ b/libs/langchain-community/src/vectorstores/libsql.ts
@@ -82,10 +82,10 @@ export class LibSQLVectorStore extends VectorStore {
 
     for (let i = 0; i < rows.length; i += batchSize) {
       const chunk = rows.slice(i, i + batchSize);
-      const insertQueries = chunk.map(
-        (row) =>
-          `INSERT INTO ${this.table} (content, metadata, ${this.column}) VALUES (${row.content}, ${row.metadata}, vector(${row.embedding})) RETURNING id`
-      );
+      const insertQueries = chunk.map((row) => ({
+        sql: `INSERT INTO ${this.table} (content, metadata, ${this.column}) VALUES (?, ?, ?) RETURNING id`,
+        args: [row.content, row.metadata, row.embedding],
+      }));
 
       const results = await this.db.batch(insertQueries);
 
@@ -124,17 +124,19 @@ export class LibSQLVectorStore extends VectorStore {
     const queryVector = `[${query.join(",")}]`;
 
     const sql = `
-      SELECT content, metadata, vector_distance_cos(${this.column}, vector(${queryVector})) AS distance
-      FROM vector_top_k('${this.table}_idx', vector(${queryVector}), ${k})
-      JOIN ${this.table} ON ${this.table}.rowid = id
+      SELECT ${this.table}.id, ${this.table}.content, ${this.table}.metadata, vector_distance_cos(${this.table}.${this.column}, vector('${queryVector}')) AS distance
+      FROM vector_top_k('idx_${this.table}_${this.column}', vector('${queryVector}'), ${k}) AS top_k
+      JOIN ${this.table} ON top_k.rowid = ${this.table}.id
     `;
 
     const results = await this.db.execute(sql);
 
+    // eslint-disable-next-line @typescript-eslint/no-explicit-any
     return results.rows.map((row: any) => {
       const metadata = JSON.parse(row.metadata);
 
       const doc = new Document({
+        id: row.id,
         metadata,
         pageContent: row.content,
       });
@@ -143,26 +145,6 @@ export class LibSQLVectorStore extends VectorStore {
     });
   }
 
-  /**
-   * Deletes vectors from the store.
-   * @param {Object} params - Delete parameters.
-   * @param {string[] | number[]} [params.ids] - The ids of the vectors to delete.
-   * @returns {Promise<void>}
-   */
-  async delete(params: { ids?: string[] | number[] }): Promise<void> {
-    if (!params.ids) {
-      await this.db.execute(`DELETE FROM ${this.table}`);
-      return;
-    }
-
-    const idsToDelete = params.ids.join(", ");
-
-    await this.db.execute({
-      sql: `DELETE FROM ${this.table} WHERE id IN (?)`,
-      args: [idsToDelete],
-    });
-  }
-
   /**
    * Creates a new LibSQLVectorStore instance from texts.
    * @param {string[]} texts - The texts to add to the store.
diff --git a/libs/langchain-community/src/vectorstores/tests/libsql.int.test.ts b/libs/langchain-community/src/vectorstores/tests/libsql.int.test.ts
new file mode 100644
index 000000000000..63fe6cbe2df7
--- /dev/null
+++ b/libs/langchain-community/src/vectorstores/tests/libsql.int.test.ts
@@ -0,0 +1,45 @@
+/* eslint-disable no-process-env */
+/* eslint-disable @typescript-eslint/no-non-null-assertion */
+import { expect, test } from "@jest/globals";
+import { OpenAIEmbeddings } from "@langchain/openai";
+import { Document } from "@langchain/core/documents";
+import { createClient } from "@libsql/client";
+
+import { LibSQLVectorStore } from "../libsql.js";
+
+test("can create and query", async () => {
+  const client = createClient({
+    url: process.env.LIBSQL_URL!,
+    authToken: process.env.LIBSQL_AUTH_TOKEN,
+  });
+  const vectorStore = new LibSQLVectorStore(
+    new OpenAIEmbeddings({
+      model: "text-embedding-3-small",
+      dimensions: 1536,
+    }),
+    {
+      db: client,
+      table: "documents",
+      column: "embeddings",
+    }
+  );
+  const ids = await vectorStore.addDocuments([
+    new Document({
+      pageContent: "added first page",
+    }),
+    new Document({
+      pageContent: "added second page",
+    }),
+    new Document({
+      pageContent: "added third page",
+    }),
+  ]);
+  const nextId = await vectorStore.addDocuments([
+    new Document({
+      pageContent: "added another first page",
+    }),
+  ]);
+  ids.push(nextId[0]);
+  const results = await vectorStore.similaritySearchWithScore("added first", 4);
+  expect(results.length).toBe(4);
+});