docs: update README to enhance clarity on features, installation, and…

… usage instructions

README.md

@@ -1,89 +1,96 @@
-# Burro 🫏🌯
+# Burro 🫏
 
-Burro is an AI-powered burrito LLM evaluation CLI tool. It helps you evaluate
-the factuality of responses generated by language models.
 
-## Features
+Burro is a command-line interface (CLI) tool built with Deno for evaluating Large Language Model (LLM) outputs. It provides a straightforward way to run different types of evaluations with secure API key management.
 
-- Set and encrypt your OpenAI API key
-- Run evaluations based on JSON input files
-- View detailed evaluation results
+## 🚀 Features
 
-## Installation
+- Three specialized evaluation types:
+  - Answer correctness evaluation with context
+  - Close-ended QA matching
+  - Simple output-expected comparison
+- Secure OpenAI API key management
+- JSON-based evaluation configurations
+- SQLite storage for results and settings
 
-1. Clone the repository:
-   ```sh
-   git clone <repository-url>
-   cd <repository-directory>
-   ```
-
-2. Install dependencies:
-   ```sh
-   deno task check
-   ```
+## 📋 Prerequisites
 
-## Build Process
+- [Deno](https://deno.land/) installed on your system
+- OpenAI API key
 
-To build the project, follow these steps:
+## 🛠️ Installation
 
-1. Ensure you have Deno installed. If not, you can install it from
-   [here](https://deno.land/#installation).
+1. Clone the repository:
+```bash
+git clone <your-repository-url>
+cd burro
+```
 
-2. Run the following command to build the project:
-   ```sh
-   deno task build
-   ```
+2. Ensure Deno is installed:
+```bash
+deno --version
+```
 
-3. The build output will be available in the `dist` directory.
+## 🔧 Usage
 
-## Usage
+### Setting up API Keys
 
-### Set OpenAI API Key
+```bash
+deno run --allow-read --allow-write --allow-env main.ts set-openai-key
+```
 
-Before running evaluations, you need to set your OpenAI API key:
+### Running Evaluations
 
-```sh
-deno task run set-openai-key
+```bash
+deno run --allow-read --allow-write --allow-env main.ts run-eval <evaluation-file>
 ```
 
-### Run Evaluation
+## 📊 Evaluation Types
 
-To run an evaluation based on a JSON input file:
+### 1. Answer Correctness (answerCorrectness.json)
+Evaluates answers against provided context with specific criteria.
 
-```sh
-deno task run run-eval <path-to-json-file>
+Example format:
+```json
+{
+  "input": {
+    "context": "Tesla's Model 3 was first unveiled on March 31, 2016...",
+    "question": "When did Tesla start delivering the Model 3?"
+  },
+  "output": "July 2017",
+  "criteria": "Answer must be exactly 'July 2017' based on the provided context"
+}
 ```
 
-### Example JSON Input
+### 2. Close QA (closeqa.json)
+Evaluates exact matching responses for close-ended questions.
 
-The JSON input file should have the following structure:
+Example format:
+```json
+{
+  "input": "List the first three prime numbers in ascending order, separated by commas.",
+  "output": "2,3,5",
+  "criteria": "Numbers must be in correct order, separated by commas with no spaces"
+}
+```
 
+### 3. Simple Evals (evals.json)
+Compares model outputs against expected answers.
+
+Example format:
 ```json
-[
-  {
-    "input": "Which country has the highest population?",
-    "output": "People's Republic of China",
-    "expected": "China"
-  },
-  {
-    "input": "What is the capital of France?",
-    "output": "The capital city of France is Paris",
-    "expected": "Paris"
-  },
-  {
-    "input": "Who wrote Romeo and Juliet?",
-    "output": "The famous playwright William Shakespeare wrote Romeo and Juliet",
-    "expected": "William Shakespeare"
-  }
-]
+{
+  "input": "What is the capital of France?",
+  "output": "The capital city of France is Paris",
+  "expected": "Paris"
+}
 ```
 
-## Development
 
-### Run Tests
+## 🔒 Security Features
+
+- AES encryption for API key storage
+- Secure key generation
+- Encrypted SQLite storage
 
-To run the tests:
 
-```sh
-deno test
-```