Team N-RAM

nram/.gitignore

@@ -0,0 +1,2 @@
+*/node_modules
+*/.env

nram/.vscode/tasks.json

@@ -0,0 +1,54 @@
+{ 
+    "version": "2.0.0", 
+    "presentation": { 
+        "echo": false, 
+        "reveal": "always", 
+        "focus": false, 
+        "panel": "dedicated", 
+        "showReuseMessage": true 
+    }, 
+    "tasks": [ 
+        { 
+            "label": "Create Terminals", 
+            "dependsOn": ["client", "server", "tsc"], 
+            "group": { 
+                "isDefault": true 
+            }, 
+            "runOptions": { 
+                "runOn": "folderOpen" 
+            },
+            "type": "shell", 
+            "command": "bash"
+        },
+        { 
+            "label": "client", 
+            "type": "shell", 
+            "command": "cd client && npm install && npm run dev", 
+            "isBackground": true, 
+            "problemMatcher": [], 
+            "presentation": { 
+                "group": "my-group" 
+            } 
+        },
+        { 
+            "label": "server", 
+            "type": "shell", 
+            "command": "cd server && npm install && npm start", 
+            "isBackground": true, 
+            "problemMatcher": [], 
+            "presentation": { 
+                "group": "my-group" 
+            } 
+        },
+        { 
+            "label": "tsc", 
+            "type": "shell", 
+            "command": "cd server && tsc -w", 
+            "isBackground": true, 
+            "problemMatcher": [], 
+            "presentation": { 
+                "group": "compile" 
+            } 
+        }
+    ] 
+}

nram/README.MD

@@ -0,0 +1,59 @@
+#### Team Name - N-RAM
+#### Problem Statement - A 3D AI interface for personalized, trustworthy education on securities markets, empowering investors to navigate financial decisions
+#### Team Leader Email - [email protected]
+
+## A Brief of the Prototype:
+  At the prototype level:
+
+- We offer an immersive speech based solution where users can have 
+- Interactive conversation with the AI model
+- The model as a personalized AI companion that helps in portfolio specific way based on the user queries to- optimize their financial understanding.
+- The knowledge of current insights and trends of the market.
+- Comfort of limited typing ability or prefer verbal communication.
+- discover new investment opportunities and strategies
+- More market experience with each interaction
+- Get Tip of the day to learn more everyday.
+- All the interactions are saved so that every next conversation could be more personalised to the user than before.
+Further, we have planned to include a points based system where each interaction gives more user specific experience (exp) points. The model will also provide external links to get more insights on the given scenario as a reference.
+
+Use Case Diagram:
+
+![UseCase](../nram/usecase.png)
+
+
+## Tech Stack: 
+- WhisperAI
+- PaLM API
+- OAuth
+- ThreeJS
+- Vite + React
+- TailwindCSS
+- TypeScript
+- NodeJS
+- ExpressJS
+- MongoDB
+
+## Step-by-Step Code Execution Instructions:
+- Clone the repository using 
+```
+git clone https://github.com/ashishlal2003/Empowering-Investors-Hackathon.git
+```
+- ```cd nram```
+- Request for the ```.env``` file from the project manager - [email protected]
+- Place the file in the ```server``` folder.
+- By default, in VSCode, the web-app starts automatically through the in-built terminal. It can be directly then accessed on ```localhost:3000```.
+- If not, run the following commands:
+Open two terminal windows
+1. ```  cd client && npm install && npm run dev ```
+2. ```   cd server && npm install && npm start ```
+
+## What I Learned:
+    We as a team learnt a lot of aspects of project development through this hackathon. Some of them include:
+- Implementation of Generative AI (using PaLM model API by Google)
+- Implementation of ThreeJS (for the 3d avatar)
+- Understanding the securities market and what a user can expect to learn.
+- Collaboration
+- Leadership
+- Resolving internal conflicts
+- Time management
+- Prioritisation

nram/api/palmAPI.py

@@ -0,0 +1,22 @@
+import pprint
+import google.generativeai as palm
+
+palm.configure(api_key='AIzaSyCcrKRaX4Lx5RjcjEaY7IYN1dA7UUTFm1M')
+
+models = [m for m in palm.list_models() if 'generateText' in m.supported_generation_methods]
+model = models[0].name
+print(model)
+
+prompt = """
+Should i invest in gold bond or in stock market?
+"""
+
+completion = palm.generate_text(
+    model=model,
+    prompt=prompt,
+    temperature=0,
+    # The maximum length of the response
+    max_output_tokens=100,
+)
+
+print(completion.result)

nram/api/speech2text.py

@@ -0,0 +1,15 @@
+import speech_recognition as sr
+
+filename = "sample.wav"
+
+# initialize the recognizer
+r = sr.Recognizer()
+
+# open the file
+with sr.AudioFile(filename) as source:
+    # listen for the data (load audio to memory)
+    audio_data = r.record(source)
+    # recognize (convert from speech to text)
+    text = r.recognize_google(audio_data)
+    print(text)
+

nram/api/tempCodeRunnerFile.py

@@ -0,0 +1,2 @@
+import pprint
+import google.generativeai as palm

nram/client/.eslintrc.cjs

@@ -0,0 +1,20 @@
+module.exports = {
+  root: true,
+  env: { browser: true, es2020: true },
+  extends: [
+    'eslint:recommended',
+    'plugin:react/recommended',
+    'plugin:react/jsx-runtime',
+    'plugin:react-hooks/recommended',
+  ],
+  ignorePatterns: ['dist', '.eslintrc.cjs'],
+  parserOptions: { ecmaVersion: 'latest', sourceType: 'module' },
+  settings: { react: { version: '18.2' } },
+  plugins: ['react-refresh'],
+  rules: {
+    'react-refresh/only-export-components': [
+      'warn',
+      { allowConstantExport: true },
+    ],
+  },
+}

nram/client/.gitignore

@@ -0,0 +1,24 @@
+# Logs
+logs
+*.log
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+pnpm-debug.log*
+lerna-debug.log*
+
+node_modules
+dist
+dist-ssr
+*.local
+
+# Editor directories and files
+.vscode/*
+!.vscode/extensions.json
+.idea
+.DS_Store
+*.suo
+*.ntvs*
+*.njsproj
+*.sln
+*.sw?

nram/client/README.md

@@ -0,0 +1,8 @@
+# React + Vite
+
+This template provides a minimal setup to get React working in Vite with HMR and some ESLint rules.
+
+Currently, two official plugins are available:
+
+- [@vitejs/plugin-react](https://github.com/vitejs/vite-plugin-react/blob/main/packages/plugin-react/README.md) uses [Babel](https://babeljs.io/) for Fast Refresh
+- [@vitejs/plugin-react-swc](https://github.com/vitejs/vite-plugin-react-swc) uses [SWC](https://swc.rs/) for Fast Refresh

nram/client/index.html

@@ -0,0 +1,13 @@
+<!doctype html>
+<html lang="en">
+  <head>
+    <meta charset="UTF-8" />
+    <link rel="icon" type="image/svg+xml" href="/vite.svg" />
+    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+    <title>NRAM.ai</title>
+  </head>
+  <body>
+    <div id="root"></div>
+    <script type="module" src="/src/main.jsx"></script>
+  </body>
+</html>