Instant vector search template

instant-vector-search/.gitignore

@@ -0,0 +1,15 @@
+# Ignore macOS system files
+.DS_Store
+
+# Ignore environment variable files
+.env
+.env.*
+
+# Ignore build output directories
+build/
+
+# Ignore node_modules folders
+node_modules/
+
+# Ignore logs generated by as-test
+logs/

instant-vector-search/.prettierrc

@@ -0,0 +1,3 @@
+{
+  "plugins": ["assemblyscript-prettier"]
+}

instant-vector-search/README.md

@@ -0,0 +1,83 @@
+# instant-vector-search
+
+A simplified template demonstrating how to build instant vector search using Hypermode and Modus. This project showcases how to configure collections, embed data, and deploy APIs to perform real-time vector search with minimal setup.
+
+## Guide
+
+Check out the guide on how to create a project using this template:
+[Instant Vector Search Guide](TODO)
+
+## Semantic Search in Action
+
+This template demonstrates how instant vector search can enhance your application by generating embeddings from user queries and performing vector searches in less than 200ms.
+
+## How to Use the Template
+
+Fork or clone this repository to get started:
+
+```
+git clone https://github.com/hypermodeinc/instant-vector-search.git
+cd instant-vector-search
+```
+
+Install Modus CLI:
+
+```
+npm install -g @hypermode/modus-cli
+```
+
+## Initialize and deploy your app:
+
+You can deploy using either the Hypermode Console or Hyp CLI.
+
+Option 1: Hypermode Console
+
+- Create a new project in the Hypermode Console.
+- Connect your GitHub account and select your repository to import.
+
+Option 2: Hyp CLI
+
+- Run the following command to import and deploy your app:
+
+```
+hyp init
+```
+
+## Uploading Data
+
+Once your app is deployed, upload your data to the texts collection to enable vector search.
+
+From the Hypermode Console: Upload a CSV directly using the dashboard.
+
+Using the `upsertTexts` function: Upload data programmatically by calling the function from your code.
+
+Once your data is in place, the embeddings will be generated automatically, and your system will be ready to handle real-time vector searches.
+
+## Making API Calls
+
+You can test the API via the Query page in the Hypermode Console. Run a sample vector search query:
+
+```
+query {
+  search(query: "your search term here")
+}
+```
+
+## Hypermode & Modus Overview
+
+This template leverages Hypermode and Modus to power your backend functions:
+
+[Hypermode](https://docs.hypermode.com/introduction) is a managed service that provides the infrastructure and tools for creating AI-powered applications, including assistants, APIs, and backend services. It offers:
+
+- Automatic building and deployment of functions with each git push
+- A live, scalable API for previewing, testing, and production
+- Access to various AI models for experimentation
+- Integrated console for observability and control
+- GraphQL API generation for easy integration
+
+[Modus](https://docs.hypermode.com/modus/overview) is an open-source, serverless framework that’s part of the Hypermode ecosystem. It focuses on:
+
+- Building functions and APIs using WebAssembly
+- Supporting multiple programming languages (currently Go and AssemblyScript)
+- Providing features to integrate models, data, and external services
+- Scaling from simple CRUD operations to complex AI systems

instant-vector-search/asconfig.json

@@ -0,0 +1,6 @@
+{
+  "extends": "./node_modules/@hypermode/modus-sdk-as/plugin.asconfig.json",
+  "options": {
+    "transform": ["@hypermode/modus-sdk-as/transform", "json-as/transform"]
+  }
+}

instant-vector-search/assembly/index.ts

@@ -0,0 +1,57 @@
+import { collections } from "@hypermode/modus-sdk-as";
+import { models } from "@hypermode/modus-sdk-as";
+import { EmbeddingsModel } from "@hypermode/modus-sdk-as/models/experimental/embeddings";
+
+const textsCollection = "texts";
+const searchMethod = "searchMethod1";
+const embeddingModelName = "minilm";
+
+export function upsertTexts(ids: string[], texts: string[]): string[] {
+  const errors: string[] = [];
+
+  if (ids.length !== texts.length) {
+    errors.push("Length of all arrays must be the same");
+    return errors;
+  }
+
+  let result = collections.upsertBatch(textsCollection, ids, texts);
+
+  if (!result.isSuccessful) {
+    errors.push(result.error);
+    return errors;
+  }
+
+  return ids;
+}
+
+export function search(query: string): string[] {
+  const searchResults = collections.search(
+    textsCollection,
+    searchMethod,
+    query,
+    10,
+    true,
+  );
+
+  if (!searchResults.isSuccessful) {
+    return [searchResults.error];
+  }
+  const searchTexts: string[] = [];
+
+  for (let i = 0; i < searchResults.objects.length; i++) {
+    const obj = searchResults.objects[i];
+    const text = collections.getText(textsCollection, obj.key);
+    if (text) {
+      searchTexts.push(text);
+    }
+  }
+  return searchTexts;
+}
+
+export function miniLMEmbed(texts: string[]): f32[][] {
+  const model = models.getModel<EmbeddingsModel>(embeddingModelName);
+  const input = model.createInput(texts);
+  const output = model.invoke(input);
+
+  return output.predictions;
+}

instant-vector-search/assembly/tsconfig.json

@@ -0,0 +1,4 @@
+{
+  "extends": "assemblyscript/std/assembly.json",
+  "include": ["./**/*.ts"]
+}

instant-vector-search/eslint.config.js

@@ -0,0 +1,11 @@
+// @ts-check
+
+import eslint from "@eslint/js";
+import tseslint from "typescript-eslint";
+import aseslint from "@hypermode/modus-sdk-as/tools/assemblyscript-eslint";
+
+export default tseslint.config(
+  eslint.configs.recommended,
+  ...tseslint.configs.recommended,
+  aseslint.config,
+);

instant-vector-search/modus.json

@@ -0,0 +1,29 @@
+{
+  "$schema": "https://schema.hypermode.com/modus.json",
+  "endpoints": {
+    "default": {
+      "type": "graphql",
+      "path": "/graphql",
+      "auth": "bearer-token"
+    }
+  },
+  "models": {
+    "minilm": {
+      "sourceModel": "sentence-transformers/all-MiniLM-L6-v2",
+      "provider": "hugging-face",
+      "connection": "hypermode"
+    }
+  },
+  "collections": {
+    "texts": {
+      "searchMethods": {
+        "searchMethod1": {
+          "embedder": "miniLMEmbed",
+          "index": {
+            "type": "sequential"
+          }
+        }
+      }
+    }
+  }
+}