Update README.md
Browse files
README.md
CHANGED
|
@@ -1,25 +1,10 @@
|
|
| 1 |
-
---
|
| 2 |
-
title: VEN - AI Restaurant Matchmaker
|
| 3 |
-
emoji: π
|
| 4 |
-
colorFrom: blue
|
| 5 |
-
colorTo: indigo
|
| 6 |
-
sdk: gradio
|
| 7 |
-
sdk_version: 5.0.0
|
| 8 |
-
app_file: app.py
|
| 9 |
-
pinned: false
|
| 10 |
-
license: mit
|
| 11 |
-
---
|
| 12 |
|
| 13 |
# π VEN: Semantic Restaurant Discovery System
|
| 14 |
|
| 15 |
**VEN** is an AI-powered recommendation engine designed to find the perfect restaurant in Tel Aviv based on user context, vibe, and specific preferences.
|
| 16 |
|
| 17 |
-
Unlike traditional filters (e.g., "Italian", "
|
| 18 |
|
| 19 |
-
## πΈ Interface Preview
|
| 20 |
-
|
| 21 |
-

|
| 22 |
-
*(The VEN interface features a clean dark-mode design with smart filtering)*
|
| 23 |
|
| 24 |
## π Key Features
|
| 25 |
|
|
@@ -31,17 +16,12 @@ Unlike traditional filters (e.g., "Italian", "$$"), VEN uses **Semantic Search**
|
|
| 31 |
|
| 32 |
## π οΈ Tech Stack
|
| 33 |
|
| 34 |
-
* **Python
|
| 35 |
* **Gradio:** For the web interface.
|
| 36 |
* **Sentence-Transformers (`all-mpnet-base-v2`):** For generating high-quality text embeddings.
|
| 37 |
* **Scikit-Learn:** For calculating Cosine Similarity between user input and reviewer profiles.
|
| 38 |
* **Pandas & NumPy:** For data manipulation and vector operations.
|
| 39 |
|
| 40 |
-
## πΌοΈ More Screenshots
|
| 41 |
-
|
| 42 |
-
| Recommendation Card | Filter Settings | Search Results |
|
| 43 |
-
|:-------------------:|:---------------:|:--------------:|
|
| 44 |
-
|  | .jpeg) | .jpeg) |
|
| 45 |
|
| 46 |
## π§ How It Works
|
| 47 |
|
|
@@ -51,10 +31,15 @@ Unlike traditional filters (e.g., "Italian", "$$"), VEN uses **Semantic Search**
|
|
| 51 |
4. **Similarity Search:** It calculates the **Cosine Similarity** to find the closest match.
|
| 52 |
5. **Ranking:** The system ranks restaurants within that Persona cluster and returns the highest-rated match with a relevant review.
|
| 53 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 54 |
## π₯ Authors
|
| 55 |
|
| 56 |
* **Matan** - Data Scientist & Developer
|
| 57 |
* **Gal** - Data Scientist & Developer
|
| 58 |
|
| 59 |
-
---
|
| 60 |
-
*Created as a final project for the Data Analysis Course.*
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
|
| 2 |
# π VEN: Semantic Restaurant Discovery System
|
| 3 |
|
| 4 |
**VEN** is an AI-powered recommendation engine designed to find the perfect restaurant in Tel Aviv based on user context, vibe, and specific preferences.
|
| 5 |
|
| 6 |
+
Unlike traditional filters (e.g., "Italian", "Thai"), VEN uses **Semantic Search** and **Persona Matching** to understand the *intent* behind the search (e.g., "A romantic quiet place for a date" vs. "Lively place for drinks with friends").
|
| 7 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
|
| 9 |
## π Key Features
|
| 10 |
|
|
|
|
| 16 |
|
| 17 |
## π οΈ Tech Stack
|
| 18 |
|
| 19 |
+
* **Python**
|
| 20 |
* **Gradio:** For the web interface.
|
| 21 |
* **Sentence-Transformers (`all-mpnet-base-v2`):** For generating high-quality text embeddings.
|
| 22 |
* **Scikit-Learn:** For calculating Cosine Similarity between user input and reviewer profiles.
|
| 23 |
* **Pandas & NumPy:** For data manipulation and vector operations.
|
| 24 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
|
| 26 |
## π§ How It Works
|
| 27 |
|
|
|
|
| 31 |
4. **Similarity Search:** It calculates the **Cosine Similarity** to find the closest match.
|
| 32 |
5. **Ranking:** The system ranks restaurants within that Persona cluster and returns the highest-rated match with a relevant review.
|
| 33 |
|
| 34 |
+
## πΌοΈ More Screenshots
|
| 35 |
+
|
| 36 |
+
| Recommendation Card | Filter Settings | Search Results |
|
| 37 |
+
|:-------------------:|:---------------:|:--------------:|
|
| 38 |
+
|  | .jpeg) | .jpeg) | 
|
| 39 |
+

|
| 40 |
+
|
| 41 |
## π₯ Authors
|
| 42 |
|
| 43 |
* **Matan** - Data Scientist & Developer
|
| 44 |
* **Gal** - Data Scientist & Developer
|
| 45 |
|
|
|
|
|
|