Mintplex-Labs · timothycarambat · Jan 12, 2024 · Jan 9, 2024 · Jan 12, 2024 · Jan 12, 2024
diff --git a/README.md b/README.md
@@ -87,6 +87,7 @@ Some cool features of AnythingLLM
 - [Chroma](https://trychroma.com)
 - [Weaviate](https://weaviate.io)
 - [QDrant](https://qdrant.tech)
+- [Milvus](https://milvus.io)
 
 ### Technical Overview
 

diff --git a/docker/.env.example b/docker/.env.example
@@ -89,6 +89,12 @@ GID='1000'
 # QDRANT_ENDPOINT="http://localhost:6333"
 # QDRANT_API_KEY=
 
+# Enable all below if you are using vector database: Milvus.
+# VECTOR_DB="milvus"
+# MILVUS_ADDRESS="http://localhost:19530"
+# MILVUS_USERNAME=
+# MILVUS_PASSWORD=
+
 # CLOUD DEPLOYMENT VARIRABLES ONLY
 # AUTH_TOKEN="hunter2" # This is the password to your application if remote hosting.
 

diff --git a/frontend/src/components/VectorDBSelection/MilvusDBOptions/index.jsx b/frontend/src/components/VectorDBSelection/MilvusDBOptions/index.jsx
@@ -0,0 +1,52 @@
+export default function MilvusDBOptions({ settings }) {
+  return (
+    <div className="w-full flex flex-col gap-y-4">
+      <div className="w-full flex items-center gap-4">
+        <div className="flex flex-col w-60">
+          <label className="text-white text-sm font-semibold block mb-4">
+            Milvus DB Address
+          </label>
+          <input
+            type="text"
+            name="MilvusAddress"
+            className="bg-zinc-900 text-white placeholder-white placeholder-opacity-60 text-sm rounded-lg focus:border-white block w-full p-2.5"
+            placeholder="http://localhost:19530"
+            defaultValue={settings?.MilvusAddress}
+            required={true}
+            autoComplete="off"
+            spellCheck={false}
+          />
+        </div>
+
+        <div className="flex flex-col w-60">
+          <label className="text-white text-sm font-semibold block mb-4">
+            Milvus Username
+          </label>
+          <input
+            type="text"
+            name="MilvusUsername"
+            className="bg-zinc-900 text-white placeholder-white placeholder-opacity-60 text-sm rounded-lg focus:border-white block w-full p-2.5"
+            placeholder="username"
+            defaultValue={settings?.MilvusUsername}
+            autoComplete="off"
+            spellCheck={false}
+          />
+        </div>
+        <div className="flex flex-col w-60">
+          <label className="text-white text-sm font-semibold block mb-4">
+            Milvus Password
+          </label>
+          <input
+            type="password"
+            name="MilvusPassword"
+            className="bg-zinc-900 text-white placeholder-white placeholder-opacity-60 text-sm rounded-lg focus:border-white block w-full p-2.5"
+            placeholder="password"
+            defaultValue={settings?.MilvusPassword ? "*".repeat(20) : ""}
+            autoComplete="off"
+            spellCheck={false}
+          />
+        </div>
+      </div>
+    </div>
+  );
+}
diff --git a/frontend/src/media/vectordbs/milvus.png b/frontend/src/media/vectordbs/milvus.png
diff --git a/frontend/src/pages/GeneralSettings/VectorDatabase/index.jsx b/frontend/src/pages/GeneralSettings/VectorDatabase/index.jsx
@@ -8,6 +8,7 @@ import PineconeLogo from "@/media/vectordbs/pinecone.png";
 import LanceDbLogo from "@/media/vectordbs/lancedb.png";
 import WeaviateLogo from "@/media/vectordbs/weaviate.png";
 import QDrantLogo from "@/media/vectordbs/qdrant.png";
+import MilvusLogo from "@/media/vectordbs/milvus.png";
 import PreLoader from "@/components/Preloader";
 import ChangeWarningModal from "@/components/ChangeWarning";
 import { MagnifyingGlass } from "@phosphor-icons/react";
@@ -17,6 +18,7 @@ import PineconeDBOptions from "@/components/VectorDBSelection/PineconeDBOptions"
 import QDrantDBOptions from "@/components/VectorDBSelection/QDrantDBOptions";
 import WeaviateDBOptions from "@/components/VectorDBSelection/WeaviateDBOptions";
 import VectorDBItem from "@/components/VectorDBSelection/VectorDBItem";
+import MilvusDBOptions from "@/components/VectorDBSelection/MilvusDBOptions";
 
 export default function GeneralVectorDatabase() {
   const [saving, setSaving] = useState(false);
@@ -79,6 +81,13 @@ export default function GeneralVectorDatabase() {
       description:
         "Open source local and cloud hosted multi-modal vector database.",
     },
+    {
+      name: "Milvus",
+      value: "milvus",
+      logo: MilvusLogo,
+      options: <MilvusDBOptions settings={settings} />,
+      description: "Open-source, highly scalable, and blazing fast.",
+    },
   ];
 
   const updateVectorChoice = (selection) => {

diff --git a/frontend/src/pages/OnboardingFlow/Steps/DataHandling/index.jsx b/frontend/src/pages/OnboardingFlow/Steps/DataHandling/index.jsx
@@ -14,6 +14,7 @@ import PineconeLogo from "@/media/vectordbs/pinecone.png";
 import LanceDbLogo from "@/media/vectordbs/lancedb.png";
 import WeaviateLogo from "@/media/vectordbs/weaviate.png";
 import QDrantLogo from "@/media/vectordbs/qdrant.png";
+import MilvusLogo from "@/media/vectordbs/milvus.png";
 import React, { useState, useEffect } from "react";
 import paths from "@/utils/paths";
 import { useNavigate } from "react-router-dom";
@@ -123,6 +124,13 @@ const VECTOR_DB_PRIVACY = {
     ],
     logo: WeaviateLogo,
   },
+  milvus: {
+    name: "Milvus",
+    description: [
+      "Your vectors and document text are stored on your Milvus instance (cloud or self-hosted)",
+    ],
+    logo: MilvusLogo,
+  },
   lancedb: {
     name: "LanceDB",
     description: [

diff --git a/frontend/src/pages/OnboardingFlow/Steps/VectorDatabaseConnection/index.jsx b/frontend/src/pages/OnboardingFlow/Steps/VectorDatabaseConnection/index.jsx
@@ -5,13 +5,15 @@ import PineconeLogo from "@/media/vectordbs/pinecone.png";
 import LanceDbLogo from "@/media/vectordbs/lancedb.png";
 import WeaviateLogo from "@/media/vectordbs/weaviate.png";
 import QDrantLogo from "@/media/vectordbs/qdrant.png";
+import MilvusLogo from "@/media/vectordbs/milvus.png";
 import System from "@/models/system";
 import paths from "@/utils/paths";
 import PineconeDBOptions from "@/components/VectorDBSelection/PineconeDBOptions";
 import ChromaDBOptions from "@/components/VectorDBSelection/ChromaDBOptions";
 import QDrantDBOptions from "@/components/VectorDBSelection/QDrantDBOptions";
 import WeaviateDBOptions from "@/components/VectorDBSelection/WeaviateDBOptions";
 import LanceDBOptions from "@/components/VectorDBSelection/LanceDBOptions";
+import MilvusOptions from "@/components/VectorDBSelection/MilvusDBOptions";
 import showToast from "@/utils/toast";
 import { useNavigate } from "react-router-dom";
 import VectorDBItem from "@/components/VectorDBSelection/VectorDBItem";
@@ -81,6 +83,13 @@ export default function VectorDatabaseConnection({
       description:
         "Open source local and cloud hosted multi-modal vector database.",
     },
+    {
+      name: "Milvus",
+      value: "milvus",
+      logo: MilvusLogo,
+      options: <MilvusOptions settings={settings} />,
+      description: "Open-source, highly scalable, and blazing fast.",
+    },
   ];
 
   function handleForward() {

diff --git a/server/.env.example b/server/.env.example
@@ -86,6 +86,11 @@ VECTOR_DB="lancedb"
 # QDRANT_ENDPOINT="http://localhost:6333"
 # QDRANT_API_KEY=
 
+# Enable all below if you are using vector database: Milvus.
+# VECTOR_DB="milvus"
+# MILVUS_ADDRESS="http://localhost:19530"
+# MILVUS_USERNAME=
+# MILVUS_PASSWORD=
 
 # CLOUD DEPLOYMENT VARIRABLES ONLY
 # AUTH_TOKEN="hunter2" # This is the password to your application if remote hosting.

diff --git a/server/models/systemSettings.js b/server/models/systemSettings.js
@@ -56,6 +56,13 @@ const SystemSettings = {
             QdrantApiKey: process.env.QDRANT_API_KEY,
           }
         : {}),
+      ...(vectorDB === "milvus"
+        ? {
+            MilvusAddress: process.env.MILVUS_ADDRESS,
+            MilvusUsername: process.env.MILVUS_USERNAME,
+            MilvusPassword: !!process.env.MILVUS_PASSWORD,
+          }
+        : {}),
       LLMProvider: llmProvider,
       ...(llmProvider === "openai"
         ? {

diff --git a/server/package.json b/server/package.json
@@ -28,6 +28,7 @@
     "@prisma/client": "5.3.0",
     "@qdrant/js-client-rest": "^1.4.0",
     "@xenova/transformers": "^2.10.0",
+    "@zilliz/milvus2-sdk-node": "^2.3.5",
     "archiver": "^5.3.1",
     "bcrypt": "^5.1.0",
     "body-parser": "^1.20.2",
@@ -77,4 +78,4 @@
     "nodemon": "^2.0.22",
     "prettier": "^3.0.3"
   }
-}
+}
diff --git a/server/utils/EmbeddingEngines/azureOpenAi/index.js b/server/utils/EmbeddingEngines/azureOpenAi/index.js
@@ -13,6 +13,7 @@ class AzureOpenAiEmbedder {
       new AzureKeyCredential(process.env.AZURE_OPENAI_KEY)
     );
     this.openai = openai;
+    this.dimensions = 1536;
 
     // Limit of how many strings we can process in a single pass to stay with resource or network limits
     // https://learn.microsoft.com/en-us/azure/ai-services/openai/faq#i-am-trying-to-use-embeddings-and-received-the-error--invalidrequesterror--too-many-inputs--the-max-number-of-inputs-is-1---how-do-i-fix-this-:~:text=consisting%20of%20up%20to%2016%20inputs%20per%20API%20request

diff --git a/server/utils/EmbeddingEngines/localAi/index.js b/server/utils/EmbeddingEngines/localAi/index.js
@@ -16,6 +16,10 @@ class LocalAiEmbedder {
         : {}),
     });
     this.openai = new OpenAIApi(config);
+    // We don't know this for user's set model so for vectorDB integrations that requires dimensionality
+    // in schema, we will throw an error.
+    // Applies to QDrant and Milvus.
+    this.dimensions = null;
 
     // Limit of how many strings we can process in a single pass to stay with resource or network limits
     this.maxConcurrentChunks = 50;

diff --git a/server/utils/EmbeddingEngines/native/index.js b/server/utils/EmbeddingEngines/native/index.js
@@ -12,6 +12,7 @@ class NativeEmbedder {
         : path.resolve(__dirname, `../../../storage/models`)
     );
     this.modelPath = path.resolve(this.cacheDir, "Xenova", "all-MiniLM-L6-v2");
+    this.dimensions = 384;
 
     // Limit of how many strings we can process in a single pass to stay with resource or network limits
     this.maxConcurrentChunks = 50;

diff --git a/server/utils/EmbeddingEngines/openAi/index.js b/server/utils/EmbeddingEngines/openAi/index.js
@@ -9,6 +9,7 @@ class OpenAiEmbedder {
     });
     const openai = new OpenAIApi(config);
     this.openai = openai;
+    this.dimensions = 1536;
 
     // Limit of how many strings we can process in a single pass to stay with resource or network limits
     this.maxConcurrentChunks = 500;

diff --git a/server/utils/helpers/index.js b/server/utils/helpers/index.js
@@ -16,6 +16,9 @@ function getVectorDbClass() {
     case "qdrant":
       const { QDrant } = require("../vectorDbProviders/qdrant");
       return QDrant;
+    case "milvus":
+      const { Milvus } = require("../vectorDbProviders/milvus");
+      return Milvus;
     default:
       throw new Error("ENV: No VECTOR_DB value found in environment!");
   }

diff --git a/server/utils/helpers/updateENV.js b/server/utils/helpers/updateENV.js
@@ -170,6 +170,20 @@ const KEY_MAPPING = {
     checks: [],
   },
 
+  // Milvus Options
+  MilvusAddress: {
+    envKey: "MILVUS_ADDRESS",
+    checks: [isValidURL, validDockerizedUrl],
+  },
+  MilvusUsername: {
+    envKey: "MILVUS_USERNAME",
+    checks: [isNotEmpty],
+  },
+  MilvusPassword: {
+    envKey: "MILVUS_PASSWORD",
+    checks: [isNotEmpty],
+  },
+
   // Together Ai Options
   TogetherAiApiKey: {
     envKey: "TOGETHER_AI_API_KEY",
@@ -279,7 +293,14 @@ function supportedEmbeddingModel(input = "") {
 }
 
 function supportedVectorDB(input = "") {
-  const supported = ["chroma", "pinecone", "lancedb", "weaviate", "qdrant"];
+  const supported = [
+    "chroma",
+    "pinecone",
+    "lancedb",
+    "weaviate",
+    "qdrant",
+    "milvus",
+  ];
   return supported.includes(input)
     ? null
     : `Invalid VectorDB type. Must be one of ${supported.join(", ")}.`;

diff --git a/server/utils/vectorDbProviders/milvus/MILVUS_SETUP.md b/server/utils/vectorDbProviders/milvus/MILVUS_SETUP.md
@@ -0,0 +1,40 @@
+# How to setup a local (or remote) Milvus Vector Database
+
+[Official Milvus Docs](https://milvus.io/docs/example_code.md) for reference.
+
+### How to get started
+
+**Requirements**
+
+Choose one of the following
+
+- Cloud
+
+  - [Cloud account](https://cloud.zilliz.com/)
+
+- Local
+  - Docker
+  - `git` available in your CLI/terminal
+
+**Instructions**
+
+- Cloud
+
+  - Create a Cluster on your cloud account
+  - Get connect Public Endpoint and Token
+  - Set .env.development variable in server
+
+- Local
+  - Download yaml file `wget https://github.com/milvus-io/milvus/releases/download/v2.3.4/milvus-standalone-docker-compose.yml -O docker-compose.yml`
+  - Start Milvus `sudo docker compose up -d`
+  - Check the containers are up and running `sudo docker compose ps`
+  - Get port number and set .env.development variable in server
+
+eg: `server/.env.development`
+
+```
+VECTOR_DB="milvus"
+MILVUS_ADDRESS="http://localhost:19530"
+MILVUS_USERNAME=minioadmin # Whatever your username and password are
+MILVUS_PASSWORD=minioadmin
+```