feat:Implement vastabase vectorDB support

README.md

@@ -136,6 +136,7 @@ AnythingLLM divides your documents into objects called `workspaces`. A Workspace
 
 - [LanceDB](https://github.com/lancedb/lancedb) (default)
 - [PGVector](https://github.com/pgvector/pgvector)
+- [Vastbase](https://www.vastbase.com)
 - [Astra DB](https://www.datastax.com/products/datastax-astra)
 - [Pinecone](https://pinecone.io)
 - [Chroma & ChromaCloud](https://trychroma.com)

docker/.env.example

@@ -218,6 +218,11 @@ GID='1000'
 # PGVECTOR_CONNECTION_STRING="postgresql://dbuser:dbuserpass@localhost:5432/yourdb"
 # PGVECTOR_TABLE_NAME="anythingllm_vectors" # optional, but can be defined
 
+# Enable all below if you are using vector database: Vastbase.
+# VECTOR_DB="vastbase"
+# VASTBASE_CONNECTION_STRING="postgresql://dbuser:dbuserpass@localhost:5432/yourdb"
+# VASTBASE_TABLE_NAME="anythingllm_vectors" # optional, but can be defined
+
 # Enable all below if you are using vector database: Chroma.
 # VECTOR_DB="chroma"
 # CHROMA_ENDPOINT='http://host.docker.internal:8000'

frontend/src/components/VectorDBSelection/VastbaseOptions/index.jsx

@@ -0,0 +1,103 @@
+import { Info } from "@phosphor-icons/react";
+import { Tooltip } from "react-tooltip";
+
+export default function VastbaseOptions({ settings }) {
+  return (
+    <div className="w-full flex flex-col gap-y-7">
+      <div className="w-full flex items-center gap-[36px] mt-1.5">
+        <div className="flex flex-col w-96">
+          <div className="flex items-center gap-x-1 mb-3">
+            <label className="text-white text-sm font-semibold block">
+              Postgres Connection String
+            </label>
+            <Info
+              size={16}
+              className="text-theme-text-secondary cursor-pointer"
+              data-tooltip-id="vastbase-connection-string-tooltip"
+              data-tooltip-place="right"
+            />
+            <Tooltip
+              delayHide={300}
+              id="vastbase-connection-string-tooltip"
+              className="max-w-md z-99"
+              clickable={true}
+            >
+              <p className="text-md whitespace-pre-line break-words">
+                This is the connection string for the Postgres database in the
+                format of <br />
+                <code>postgresql://username:password@host:port/database</code>
+                <br />
+                <br />
+                The user for the database must have the following permissions:
+                <ul className="list-disc list-inside">
+                  <li>Read access to the database</li>
+                  <li>Read access to the database schema</li>
+                  <li>Create access to the database</li>
+                </ul>
+                <br />
+                <b>
+                  You must have the vastbase extension installed on the
+                  database.
+                </b>
+              </p>
+            </Tooltip>
+          </div>
+          <input
+            type="text"
+            name="VastbaseConnectionString"
+            className="border-none bg-theme-settings-input-bg text-white placeholder:text-theme-settings-input-placeholder text-sm rounded-lg focus:outline-primary-button active:outline-primary-button outline-none block w-full p-2.5"
+            placeholder="postgresql://username:password@host:port/database"
+            defaultValue={
+              settings?.VastbaseConnectionString ? "*".repeat(20) : ""
+            }
+            required={true}
+            autoComplete="off"
+            spellCheck={false}
+          />
+        </div>
+
+        <div className="flex flex-col w-60">
+          <div className="flex items-center gap-x-1 mb-3">
+            <label className="text-white text-sm font-semibold block">
+              Vector Table Name
+            </label>
+            <Info
+              size={16}
+              className="text-theme-text-secondary cursor-pointer"
+              data-tooltip-id="vastbase-table-name-tooltip"
+              data-tooltip-place="right"
+            />
+            <Tooltip
+              delayHide={300}
+              id="vastbase-table-name-tooltip"
+              className="max-w-md z-99"
+              clickable={true}
+            >
+              <p className="text-md whitespace-pre-line break-words">
+                This is the name of the table in the Postgres database that will
+                store the vectors.
+                <br />
+                <br />
+                By default, the table name is <code>anythingllm_vectors</code>.
+                <br />
+                <br />
+                <b>
+                  This table must not already exist on the database - it will be
+                  created automatically.
+                </b>
+              </p>
+            </Tooltip>
+          </div>
+          <input
+            type="text"
+            name="VastbaseTableName"
+            autoComplete="off"
+            defaultValue={settings?.VastbaseTableName}
+            className="border-none bg-theme-settings-input-bg text-white placeholder:text-theme-settings-input-placeholder text-sm rounded-lg focus:outline-primary-button active:outline-primary-button outline-none block w-full p-2.5"
+            placeholder="vector_table"
+          />
+        </div>
+      </div>
+    </div>
+  );
+}

frontend/src/pages/GeneralSettings/VectorDatabase/index.jsx

@@ -21,6 +21,7 @@ import MilvusLogo from "@/media/vectordbs/milvus.png";
 import ZillizLogo from "@/media/vectordbs/zilliz.png";
 import AstraDBLogo from "@/media/vectordbs/astraDB.png";
 import PGVectorLogo from "@/media/vectordbs/pgvector.png";
+import VastbaseLogo from "@/media/vectordbs/vastbase.png";
 
 import LanceDBOptions from "@/components/VectorDBSelection/LanceDBOptions";
 import ChromaDBOptions from "@/components/VectorDBSelection/ChromaDBOptions";
@@ -32,6 +33,7 @@ import MilvusDBOptions from "@/components/VectorDBSelection/MilvusDBOptions";
 import ZillizCloudOptions from "@/components/VectorDBSelection/ZillizCloudOptions";
 import AstraDBOptions from "@/components/VectorDBSelection/AstraDBOptions";
 import PGVectorOptions from "@/components/VectorDBSelection/PGVectorOptions";
+import VastbaseOptions from "@/components/VectorDBSelection/VastbaseOptions";
 
 export default function GeneralVectorDatabase() {
   const [saving, setSaving] = useState(false);
@@ -126,6 +128,13 @@ export default function GeneralVectorDatabase() {
       options: <PGVectorOptions settings={settings} />,
       description: "Vector search powered by PostgreSQL.",
     },
+    {
+      name: "Vastbase",
+      value: "vastbase",
+      logo: VastbaseLogo,
+      options: <VastbaseOptions settings={settings} />,
+      description: "Vector search powered by Vastbase.",
+    },
     {
       name: "Chroma",
       value: "chroma",

frontend/src/pages/OnboardingFlow/Steps/DataHandling/index.jsx

@@ -37,6 +37,7 @@ import MilvusLogo from "@/media/vectordbs/milvus.png";
 import VoyageAiLogo from "@/media/embeddingprovider/voyageai.png";
 import PPIOLogo from "@/media/llmprovider/ppio.png";
 import PGVectorLogo from "@/media/vectordbs/pgvector.png";
+import VastbaseLogo from "@/media/vectordbs/vastbase.png";
 import DPAISLogo from "@/media/llmprovider/dpais.png";
 import MoonshotAiLogo from "@/media/llmprovider/moonshotai.png";
 import CometApiLogo from "@/media/llmprovider/cometapi.png";
@@ -280,6 +281,14 @@ export const VECTOR_DB_PRIVACY = {
     ],
     logo: PGVectorLogo,
   },
+  vastbase: {
+    name: "Vastbase",
+    description: [
+      "Your vectors and document text are stored on your Vastbase instance",
+      "Access to your instance is managed by you",
+    ],
+    logo: VastbaseLogo,
+  },
   chroma: {
     name: "Chroma",
     description: [

locales/README.fa-IR.md

@@ -138,6 +138,7 @@ AnythingLLM اسناد شما را به اشیایی به نام `workspaces` ت
 
 - [LanceDB](https://github.com/lancedb/lancedb) (پیش‌فرض)
 - [PGVector](https://github.com/pgvector/pgvector)
+- [Vastbase](https://www.vastdata.com.cn)
 - [Astra DB](https://www.datastax.com/products/datastax-astra)
 - [Pinecone](https://pinecone.io)
 - [Chroma](https://trychroma.com)

locales/README.ja-JP.md

@@ -122,6 +122,7 @@ AnythingLLMは、ドキュメントを`ワークスペース`と呼ばれるオ
 
 - [LanceDB](https://github.com/lancedb/lancedb)（デフォルト）
 - [PGVector](https://github.com/pgvector/pgvector)
+- [Vastbase](https://www.vastdata.com.cn)
 - [Astra DB](https://www.datastax.com/products/datastax-astra)
 - [Pinecone](https://pinecone.io)
 - [Chroma](https://trychroma.com)

locales/README.tr-TR.md

@@ -133,6 +133,7 @@ AnythingLLM, belgelerinizi **"çalışma alanları" (workspaces)** adı verilen
 
 - [LanceDB](https://github.com/lancedb/lancedb) (default)
 - [PGVector](https://github.com/pgvector/pgvector)
+- [Vastbase](https://www.vastdata.com.cn)
 - [Astra DB](https://www.datastax.com/products/datastax-astra)
 - [Pinecone](https://pinecone.io)
 - [Chroma](https://trychroma.com)

locales/README.zh-CN.md

@@ -133,6 +133,7 @@ AnythingLLM将您的文档划分为称为`workspaces` (工作区)的对象。工
 
 - [LanceDB](https://github.com/lancedb/lancedb) （默认）
 - [PGVector](https://github.com/pgvector/pgvector)
+- [Vastbase](https://www.vastdata.com.cn)
 - [Astra DB](https://www.datastax.com/products/datastax-astra)
 - [Pinecone](https://pinecone.io)
 - [Chroma](https://trychroma.com)

server/.env.example

@@ -239,6 +239,11 @@ VECTOR_DB="lancedb"
 # PGVECTOR_CONNECTION_STRING="postgresql://dbuser:dbuserpass@localhost:5432/yourdb"
 # PGVECTOR_TABLE_NAME="anythingllm_vectors" # optional, but can be defined
 
+# Enable all below if you are using vector database: Vastbase.
+# VECTOR_DB="vastbase"
+# VASTBASE_CONNECTION_STRING="postgresql://dbuser:dbuserpass@localhost:5432/yourdb"
+# VASTBASE_TABLE_NAME="anythingllm_vectors" # optional, but can be defined
+
 # Enable all below if you are using vector database: Weaviate.
 # VECTOR_DB="weaviate"
 # WEAVIATE_ENDPOINT="http://localhost:8080"

server/__tests__/utils/vectorDbProviders/vastbase/index.test.js

@@ -0,0 +1,76 @@
+const { Vastbase } = require("../../../../utils/vectorDbProviders/vastbase");
+
+describe("Vastbase.sanitizeForJsonb", () => {
+  it("returns null/undefined as-is", () => {
+    expect(Vastbase.sanitizeForJsonb(null)).toBeNull();
+    expect(Vastbase.sanitizeForJsonb(undefined)).toBeUndefined();
+  });
+
+  it("keeps safe whitespace (tab, LF, CR) and removes disallowed C0 controls", () => {
+    const input = "a\u0000\u0001\u0002\tline\ncarriage\rreturn\u001Fend";
+    const result = Vastbase.sanitizeForJsonb(input);
+    // Expect all < 0x20 except 9,10,13 removed; keep letters and allowed whitespace
+    expect(result).toBe("a\tline\ncarriage\rreturnend");
+  });
+
+  it("removes only disallowed control chars; keeps normal printable chars", () => {
+    const input = "Hello\u0000, World! \u0007\u0008\u000B\u000C\u001F";
+    const result = Vastbase.sanitizeForJsonb(input);
+    expect(result).toBe("Hello, World! ");
+  });
+
+  it("deeply sanitizes objects", () => {
+    const input = {
+      plain: "ok",
+      bad: "has\u0000nul",
+      nested: {
+        arr: ["fine", "bad\u0001", { deep: "\u0002oops" }],
+      },
+    };
+    const result = Vastbase.sanitizeForJsonb(input);
+    expect(result).toEqual({
+      plain: "ok",
+      bad: "hasnul",
+      nested: { arr: ["fine", "bad", { deep: "oops" }] },
+    });
+  });
+
+  it("deeply sanitizes arrays", () => {
+    const input = ["\u0000", 1, true, { s: "bad\u0003" }, ["ok", "\u0004bad"]];
+    const result = Vastbase.sanitizeForJsonb(input);
+    expect(result).toEqual(["", 1, true, { s: "bad" }, ["ok", "bad"]]);
+  });
+
+  it("converts Date to ISO string", () => {
+    const d = new Date("2020-01-02T03:04:05.000Z");
+    expect(Vastbase.sanitizeForJsonb(d)).toBe(d.toISOString());
+  });
+
+  it("returns primitives unchanged (number, boolean, bigint)", () => {
+    expect(Vastbase.sanitizeForJsonb(42)).toBe(42);
+    expect(Vastbase.sanitizeForJsonb(3.14)).toBe(3.14);
+    expect(Vastbase.sanitizeForJsonb(true)).toBe(true);
+    expect(Vastbase.sanitizeForJsonb(false)).toBe(false);
+    expect(Vastbase.sanitizeForJsonb(BigInt(1))).toBe(BigInt(1));
+  });
+
+  it("returns symbol unchanged", () => {
+    const sym = Symbol("x");
+    expect(Vastbase.sanitizeForJsonb(sym)).toBe(sym);
+  });
+
+  it("does not mutate original objects/arrays", () => {
+    const obj = { a: "bad\u0000", nested: { b: "ok" } };
+    const arr = ["\u0001", { c: "bad\u0002" }];
+    const objCopy = JSON.parse(JSON.stringify(obj));
+    const arrCopy = JSON.parse(JSON.stringify(arr));
+    const resultObj = Vastbase.sanitizeForJsonb(obj);
+    const resultArr = Vastbase.sanitizeForJsonb(arr); 
+    // Original inputs remain unchanged
+    expect(obj).toEqual(objCopy);
+    expect(arr).toEqual(arrCopy);
+    // Results are sanitized copies
+    expect(resultObj).toEqual({ a: "bad", nested: { b: "ok" } });
+    expect(resultArr).toEqual(["", { c: "bad" }]);
+  });
+});

server/models/systemSettings.js

@@ -8,6 +8,7 @@ const prisma = require("../utils/prisma");
 const { v4 } = require("uuid");
 const { MetaGenerator } = require("../utils/boot/MetaGenerator");
 const { PGVector } = require("../utils/vectorDbProviders/pgvector");
+const { Vastbase } = require("../utils/vectorDbProviders/vastbase");
 const { NativeEmbedder } = require("../utils/EmbeddingEngines/native");
 const { getBaseLLMProviderModel } = require("../utils/helpers");
 
@@ -458,6 +459,10 @@ const SystemSettings = {
       // PGVector Keys
       PGVectorConnectionString: !!PGVector.connectionString() || false,
       PGVectorTableName: PGVector.tableName(),
+
+      // Vastbase Keys
+      VastbaseConnectionString: !!Vastbase.connectionString() || false,
+      VastbaseTableName: Vastbase.tableName(),
     };
   },
 

server/utils/helpers/index.js

@@ -113,6 +113,9 @@ function getVectorDbClass(getExactly = null) {
     case "pgvector":
       const { PGVector } = require("../vectorDbProviders/pgvector");
       return PGVector;
+    case "vastbase":
+      const { Vastbase } = require("../vectorDbProviders/vastbase");
+      return Vastbase;
     default:
       throw new Error("ENV: No VECTOR_DB value found in environment!");
   }