Spaces:
Sleeping
Sleeping
Kye Gomez
commited on
Update README.md
Browse files
README.md
CHANGED
@@ -1,8 +1,99 @@
|
|
1 |
# Search Arena
|
2 |
|
3 |
-
|
4 |
-
```bash
|
5 |
-
pip3 install -r requirements.txt/
|
6 |
|
7 |
-
|
8 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
# Search Arena
|
2 |
|
3 |
+
**Search Arena** is a comprehensive platform designed to rigorously evaluate and compare search-based web agents. Leveraging a variety of metrics, Search Arena ensures that users can identify the most effective solutions for their needs.
|
|
|
|
|
4 |
|
5 |
+
## Key Features
|
6 |
+
|
7 |
+
- **Output Evaluations:** Analyze the quality and relevance of search results.
|
8 |
+
- **Perplexity:** Measure the predictive uncertainty of language models used by the agents.
|
9 |
+
- **Exa (Exhaustiveness Analysis):** Assess the breadth and depth of search coverage.
|
10 |
+
- **Multi-Agent Comparison:** Compare multiple agents side-by-side.
|
11 |
+
- **Customizable Benchmarks:** Define specific benchmarks and criteria for evaluation.
|
12 |
+
- **User Feedback Integration:** Incorporate user feedback to improve agent performance.
|
13 |
+
- **Performance Metrics:** Detailed reports on response time, precision, recall, and F1 score.
|
14 |
+
|
15 |
+
## Benefits
|
16 |
+
|
17 |
+
- **Enhanced Decision-Making:** Make informed decisions with clear, data-driven evaluations.
|
18 |
+
- **Optimization:** Help developers optimize their search agents.
|
19 |
+
- **Innovation:** Foster innovation by promoting the best-performing search technologies.
|
20 |
+
|
21 |
+
## Getting Started
|
22 |
+
|
23 |
+
Follow these steps to set up the project on your local machine.
|
24 |
+
|
25 |
+
### Prerequisites
|
26 |
+
|
27 |
+
- Git
|
28 |
+
- Python 3.x
|
29 |
+
- Virtualenv (optional but recommended)
|
30 |
+
|
31 |
+
### Installation
|
32 |
+
|
33 |
+
1. **Clone the Repository:**
|
34 |
+
|
35 |
+
```bash
|
36 |
+
git clone https://github.com/leowalker89/SearchArena
|
37 |
+
```
|
38 |
+
|
39 |
+
2. **Navigate to the Project Directory:**
|
40 |
+
|
41 |
+
```bash
|
42 |
+
cd search-arena
|
43 |
+
```
|
44 |
+
|
45 |
+
3. **Create a Virtual Environment:**
|
46 |
+
|
47 |
+
```bash
|
48 |
+
python -m venv env
|
49 |
+
```
|
50 |
+
|
51 |
+
4. **Activate the Virtual Environment:**
|
52 |
+
|
53 |
+
- On Windows:
|
54 |
+
|
55 |
+
```bash
|
56 |
+
.\env\Scripts\activate
|
57 |
+
```
|
58 |
+
|
59 |
+
- On macOS and Linux:
|
60 |
+
|
61 |
+
```bash
|
62 |
+
source env/bin/activate
|
63 |
+
```
|
64 |
+
|
65 |
+
5. **Install the Required Dependencies:**
|
66 |
+
|
67 |
+
```bash
|
68 |
+
pip install -r requirements.txt
|
69 |
+
```
|
70 |
+
|
71 |
+
### Running the Project
|
72 |
+
|
73 |
+
1. **Start the Development Server:**
|
74 |
+
|
75 |
+
```bash
|
76 |
+
streamlit run app.py
|
77 |
+
```
|
78 |
+
|
79 |
+
2. **Open your Browser:**
|
80 |
+
|
81 |
+
Navigate to `http://localhost:5000` to view the platform.
|
82 |
+
|
83 |
+
### Usage
|
84 |
+
|
85 |
+
- Follow the on-screen instructions to evaluate and compare search-based web agents.
|
86 |
+
- Customize benchmarks and criteria as needed.
|
87 |
+
- Analyze detailed reports and visualizations to make informed decisions.
|
88 |
+
|
89 |
+
### Contributing
|
90 |
+
|
91 |
+
We welcome contributions! Please read our [Contributing Guide](CONTRIBUTING.md) to get started.
|
92 |
+
|
93 |
+
### License
|
94 |
+
|
95 |
+
This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for more details.
|
96 |
+
|
97 |
+
### Contact
|
98 |
+
|
99 |
+
If you have any questions, feel free to open an issue or contact us at [[email protected]](mailto:[email protected]).
|