fix: update links

Author: AruneshSingh

docs/articles/forget_text_to_sql.md

@@ -5,6 +5,7 @@ Search technology has evolved significantly – and so have user expectations, e
 In this article, we’ll show you how to build a modern search system for e-commerce products using natural language queries that leverage context, rather than traditional text-to-SQL approaches that struggle with meaning.
 
 ## The Shortcomings of Traditional Search
+
 Traditional keyword-based search with filters often fails to capture the meaning of complex queries that combine multiple attributes - like text descriptions, numerical data (eg. price), categorical information (eg. product type), and ratings. For example:
 
 - "comfortable running shoes for marathon training under $150"
@@ -15,23 +16,24 @@ Traditional keyword-based search with filters often fails to capture the meaning
 ](../assets/use_cases/forget_text_to_sql/example_query_result.webp)
 
 ## A Better Approach: Multi-attribute Vector Search
+
 We can build a system that’s more flexible and effective than converting natural language to SQL queries (text-to-SQL), using:
 
 1. Vector embeddings for all product attributes (i.e., text, numbers, categories)
 2. Natural language query decomposition
 3. Multi-dimensional vector search
 
-
 ### Key Components
+
 1. Superlinked Framework: handles vector embeddings, indexing, and natural query processing
 2. MongoDB Atlas: provides vector database capabilities
 3. OpenAI: powers natural language understanding
 4. Streamlit: offers a user interface
 
 ![](../assets/use_cases/forget_text_to_sql/system_diagram.webp)
 
-
 ## How to Implement - An Overview
+
 1. **Process your Product Data**: clean and prepare Amazon product data (title, description, price, ratings, etc.)
 2. **Define your Schema**: define your product data structure using Superlinked's schema system, much like you would using Python data classes or Pydantic.
 
@@ -53,10 +55,10 @@ product = ProductSchema()
 ```
 
 3. **Create your Vector Embeddings**: Superlinked's approach lets us combine various types of data into a single vector index:
-    - categories
-    - text
-    - numbers (floats and integers)
-    - temporal data (supported, but not used in our example here)
+   - categories
+   - text
+   - numbers (floats and integers)
+   - temporal data (supported, but not used in our example here)
 
 ```python
 # Create similarity spaces for different attributes
@@ -67,19 +69,19 @@ category_space = sl.CategoricalSimilaritySpace(
     negative_filter=-1,
 )
 description_space = sl.TextSimilaritySpace(
-    text=product.description, 
+    text=product.description,
     model="Alibaba-NLP/gte-large-en-v1.5"
 )
 review_rating_maximizer_space = sl.NumberSpace(
-    number=product.review_rating, 
+    number=product.review_rating,
     min_value=-1.0,
-    max_value=5.0, 
+    max_value=5.0,
     mode=sl.Mode.MAXIMUM
 )
 price_minimizer_space = sl.NumberSpace(
-    number=product.price, 
-    min_value=0.0, 
-    max_value=1000, 
+    number=product.price,
+    min_value=0.0,
+    max_value=1000,
     mode=sl.Mode.MINIMUM
 )
 ```
@@ -110,20 +112,19 @@ semantic_query = (
 ```
 
 6. **Set up Search using API and Interface**:
-    - Superlinked’s RESTful API exposes search functionality
-    - Streamlit interface enables user interaction
-
+   - Superlinked’s RESTful API exposes search functionality
+   - Streamlit interface enables user interaction
 
 ## Benefits of Multi-attribute Search
+
 1. **Natural Interaction**: Users can express complex search intentions in plain language
 2. **Multi-attribute Understanding**: System comprehends relationships between different product attributes
 3. **Flexible Architecture**: Easy to extend by adding new attributes, and easy to modify search behavior
 4. **No unreliable SQL Complex queries**: text-to-SQL can’t reliably generate complex SQL queries
 
+## For Example…
 
-## For Example… 
-Using a multi-attribute vector search system, the query 
-
+Using a multi-attribute vector search system, the query
 
 ```text
 "psychology books with a price lower than 100 and a rating bigger than 4"
@@ -132,17 +133,17 @@ Using a multi-attribute vector search system, the query
 gets automatically decoded into:
 
 ```text
-semantic search elements: 
-description="psychology" 
+semantic search elements:
+description="psychology"
 price=100
 rating=4
 filters: type="book"
 ```
 
 Our system then performs vector similarity search across all attributes simultaneously, providing more nuanced and relevant results than traditional filtering.
 
-
 ## How to Get Started
+
 A complete implementation of this system is available on [GitHub](https://rebrand.ly/amazon-tabular-semantic-github). It includes:
 
 - Data processing scripts
@@ -151,11 +152,9 @@ A complete implementation of this system is available on [GitHub](https://rebran
 - Streamlit interface
 
 ## Conclusion
-Combining vector embeddings and natural language processing is by far more intuitive and powerful than traditional text-to-SQL methods in handling the complexities of e-commerce search. Using a multi-attribute vector search platform like Superlinked’s, you can build modern search experiences that meet the expectations of 21st century e-commerce users, without the complexities and deficiencies of manual SQL query generation, or the overhead of maintaining a separate search index for each different attribute type.
-
-
 
+Combining vector embeddings and natural language processing is by far more intuitive and powerful than traditional text-to-SQL methods in handling the complexities of e-commerce search. Using a multi-attribute vector search platform like Superlinked’s, you can build modern search experiences that meet the expectations of 21st century e-commerce users, without the complexities and deficiencies of manual SQL query generation, or the overhead of maintaining a separate search index for each different attribute type.
 
-Ready to try it out yourself? Superlinked is here to help you with your implementation. We also offer a fully-managed cloud service. Don’t hesitate to [get in touch](https://superlinked.typeform.com/to/LXMRzHWk?source=vh-paul-article&typeform-source=vh-paul-article)! 
+Ready to try it out yourself? Superlinked is here to help you with your implementation. We also offer a fully-managed cloud service. Don’t hesitate to [get in touch](http://getdemo.superlinked.com/?utm_source=vh-paul-article)!
 
-*This article is based on [Paul Iusztin](https://www.linkedin.com/in/pauliusztin/)’s tutorial on Decoding ML - check out the full version [here](https://decodingml.substack.com/p/forget-text-to-sql-use-this-natural).*
+_This article is based on [Paul Iusztin](https://www.linkedin.com/in/pauliusztin/)’s tutorial on Decoding ML - check out the full version [here](https://decodingml.substack.com/p/forget-text-to-sql-use-this-natural)._