Updated Articles Pages (#1329)

* Updated Articles Pages

* fixes

* Links removed

* Fixed url

* light theme fix

* toc fix

* new article categories

* categorize articles

* fix article preview images

* rename categories

---------

Co-authored-by: trean <[email protected]>
Co-authored-by: generall <[email protected]>

qdrant-landing/content/articles/_index.md

@@ -5,4 +5,8 @@ description: Articles about vector search and similarity larning related topics.
 section_title: Check out our latest publications
 subtitle: Check out our latest publications
 img: /articles_data/title-img.png
+partition: learn
+learnButton: Learn More
+isMainPage: true
+toc_start_level: 2
 ---

qdrant-landing/content/articles/agentic-rag.md

@@ -8,6 +8,7 @@ weight: -150
 author: Kacper Łukawski
 author_link: https://www.kacperlukawski.com
 date: 2024-11-22T00:00:00.000Z
+category: rag-and-genai
 ---
 
 Standard [Retrieval Augmented Generation](/articles/what-is-rag-in-ai/) follows a predictable, linear path: receive 

qdrant-landing/content/articles/batch-vector-search-with-qdrant.md

@@ -13,6 +13,7 @@ tags:
   - Vector Database
   - Machine Learning
   - Information Retrieval
+category: vector-search-manuals
 ---
 
 # How to Optimize Vector Search Using Batch Search in Qdrant 0.10.0

qdrant-landing/content/articles/binary-quantization-openai.md

@@ -22,6 +22,7 @@ tags:
 weight: -130
 
 aliases: [ /blog/binary-quantization-openai/ ]
+category: practicle-examples
 ---
 
 OpenAI Ada-003 embeddings are a powerful tool for natural language processing (NLP). However, the size of the embeddings are a challenge, especially with real-time search and retrieval. In this article, we explore how you can use Qdrant's Binary Quantization to enhance the performance and efficiency of OpenAI embeddings.
@@ -217,4 +218,4 @@ Binary quantization is exceptional if you need to work with large volumes of dat
 
 The article gives examples of data sets and configuration you can use to get going. Our documentation covers [adding large datasets to Qdrant](/documentation/tutorials/bulk-upload/) to your Qdrant instance as well as [more quantization methods](/documentation/guides/quantization/). 
 
-Want to discuss these findings and learn more about Binary Quantization? [Join our Discord community.](https://discord.gg/qdrant) 
+Want to discuss these findings and learn more about Binary Quantization? [Join our Discord community.](https://discord.gg/qdrant) 

qdrant-landing/content/articles/binary-quantization.md

@@ -14,6 +14,7 @@ keywords:
   - vector search
   - binary quantization
   - memory optimization
+category: qdrant-internals
 ---
 
 # Optimizing High-Dimensional Vectors with Binary Quantization

qdrant-landing/content/articles/bm42.md

@@ -12,6 +12,7 @@ keywords:
   - hybrid search
   - sparse embeddings
   - bm25
+category: machine-learning
 ---
 
 <aside role="status">

qdrant-landing/content/articles/cars-recognition.md

@@ -11,6 +11,7 @@ author_link: https://medium.com/@yusufsarigoz
 date: 2022-06-28T13:00:00+03:00
 draft: false
 # aliases: [ /articles/cars-recognition/ ]
+category: machine-learning
 ---
 
 Supervised classification is one of the most widely used training objectives in machine learning,

qdrant-landing/content/articles/chatgpt-plugin.md

@@ -16,6 +16,7 @@ keywords:
   - chatgpt plugin
   - knowledge base
   - similarity search
+category: practicle-examples
 ---
 
 In recent months, ChatGPT has revolutionised the way we communicate, learn, and interact

qdrant-landing/content/articles/cross-encoder-integration-gsoc.md

@@ -15,6 +15,7 @@ keywords:
   - reranking
   - fastembed
   - qsoc'24
+category: machine-learning
 ---
 
 ## Introduction

qdrant-landing/content/articles/data-exploration/_index.md

@@ -0,0 +1,8 @@
+---
+title: Data Exploration
+description: Learn how you can leverage vector similarity beyond just search. Reveal hidden patterns and insights in your data, provide recommendations, and navigate data space.
+category: data-exploration
+url: /articles/data-exploration/
+isCategoryPage: true
+weight: 30
+---

qdrant-landing/content/articles/data-privacy.md

@@ -15,6 +15,7 @@ keywords: # Keywords for SEO
   - Secure AI Data Management
   - Qdrant Data Security
   - Enterprise Data Compliance
+category: vector-search-manuals
 ---
 
 Data stored in vector databases is often proprietary to the enterprise and may include sensitive information like customer records, legal contracts, electronic health records (EHR), financial data, and intellectual property. Moreover, strong security measures become critical to safeguarding this data. If the data stored in a vector database is not secured, it may open a vulnerability known as "[embedding inversion attack](https://arxiv.org/abs/2004.00053)," where malicious actors could potentially [reconstruct the original data from the embeddings](https://arxiv.org/pdf/2305.03010) themselves. 

qdrant-landing/content/articles/dataset-quality.md

@@ -9,6 +9,7 @@ weight: 8
 author: George Panchuk
 author_link: https://medium.com/@george.panchuk
 date: 2022-07-18T10:18:00.000Z
+category: data-exploration
 # aliases: [ /articles/dataset-quality/ ]
 ---
 Nowadays, people create a huge number of applications of various types and solve problems in different areas.

qdrant-landing/content/articles/dedicated-service.md

@@ -15,6 +15,7 @@ keywords:
     - vector search
     - best practices
     - anti-patterns
+category: qdrant-internals
 ---
 
 

qdrant-landing/content/articles/detecting-coffee-anomalies.md

@@ -10,6 +10,7 @@ author: Yusuf Sarıgöz
 author_link: https://medium.com/@yusufsarigoz
 date: 2022-05-04T13:00:00+03:00
 draft: false
+category: machine-learning
 # aliases: [ /articles/detecting-coffee-anomalies/ ]
 ---
 

qdrant-landing/content/articles/dimension-reduction-qsoc.md

@@ -11,13 +11,13 @@ author_link: https://www.linkedin.com/in/j16n/
 date: 2024-08-31T10:39:48.312Z
 draft: false
 keywords:
-
     - dimension reduction
     - web assembly
     - qsoc'24
     - vector similarity
     - tsne
     - qdrant data visualization
+category: ecosystem
 ---
 
 

qdrant-landing/content/articles/discovery-search.md

@@ -17,6 +17,7 @@ keywords:
   - multimodal
   - state-of-the-art
   - vector-search
+category: data-exploration
 ---
 
 # Discovery needs context

qdrant-landing/content/articles/ecosystem/_index.md

@@ -0,0 +1,8 @@
+---
+title: Ecosystem
+description: Tools, libraries and integrations around Qdrant vector search engine.
+category: ecosystem
+url: /articles/ecosystem/
+isCategoryPage: true
+weight: 
+---

qdrant-landing/content/articles/embedding-recycler.md

@@ -11,6 +11,7 @@ author_link: https://medium.com/@yusufsarigoz
 date: 2022-08-23T13:00:00+03:00
 draft: false
 aliases: [ /articles/embedding-recycler/ ]
+category: machine-learning
 ---
 
 A recent [paper](https://arxiv.org/abs/2207.04993)

qdrant-landing/content/articles/faq-question-answering.md

@@ -9,6 +9,7 @@ weight: 9
 author: George Panchuk
 author_link: https://medium.com/@george.panchuk
 date: 2022-06-28T08:57:07.604Z
+category: practicle-examples
 # aliases: [ /articles/faq-question-answering/ ]
 ---
 

qdrant-landing/content/articles/fastembed.md

@@ -19,6 +19,7 @@ keywords:
     - embeddings
     - ONNX Runtime
     - quantized embedding model
+category: ecosystem
 ---
 
 Data Science and Machine Learning practitioners often find themselves navigating through a labyrinth of models, libraries, and frameworks. Which model to choose, what embedding size, and how to approach tokenizing, are just some questions you are faced with when starting your work. We understood how many data scientists wanted an easier and more intuitive means to do their embedding work. This is why we built FastEmbed, a Python library engineered for speed, efficiency, and usability. We have created easy to use default workflows, handling the 80% use cases in NLP embedding.

qdrant-landing/content/articles/filtrable-hnsw.md

@@ -10,6 +10,7 @@ weight: 60
 date: 2019-11-24T22:44:08+03:00
 author: Andrei Vasnetsov
 author_link: https://blog.vasnetsov.com/
+category: qdrant-internals
 # aliases: [ /articles/filtrable-hnsw/ ]
 ---
 

qdrant-landing/content/articles/food-discovery-demo.md

@@ -9,6 +9,7 @@ weight: -30
 author: Kacper Łukawski
 author_link: https://medium.com/@lukawskikacper
 date: 2023-09-05T11:32:00.000Z
+category: practicle-examples
 ---
 
 Not every search journey begins with a specific destination in mind. Sometimes, you just want to explore and see what’s out there and what you might like.

qdrant-landing/content/articles/geo-polygon-filter-gsoc.md

@@ -10,12 +10,12 @@ author: Zein Wen
 author_link: https://www.linkedin.com/in/zishenwen/
 date: 2023-10-12T08:00:00+03:00
 draft: false
-keywords: 
-
+keywords:
     - payload filtering
     - geo polygon
     - search condition
-    - gsoc'23 
+    - gsoc'23
+category: qdrant-internals
 ---
 
 

qdrant-landing/content/articles/hybrid-search.md

@@ -8,6 +8,7 @@ weight: -150
 author: Kacper Łukawski
 author_link: https://kacperlukawski.com
 date: 2024-07-25T00:00:00.000Z
+category: vector-search-manuals
 ---
 
 It's been over a year since we published the original article on how to build a hybrid

qdrant-landing/content/articles/immutable-data-structures.md

@@ -14,6 +14,7 @@ keywords:
   - immutable data structures
   - perfect hashing
   - defragmentation
+category: qdrant-internals
 ---
 
 ## Data Structures 101

qdrant-landing/content/articles/io_uring.md

@@ -15,6 +15,7 @@ keywords:
   - linux
   - optimization
 aliases: [ /articles/io-uring/ ]
+category: qdrant-internals
 ---
 
 With Qdrant [version 1.3.0](https://github.com/qdrant/qdrant/releases/tag/v1.3.0) we

qdrant-landing/content/articles/langchain-integration.md

@@ -18,6 +18,7 @@ keywords:
   - question answering
   - openai
   - embeddings
+category: practicle-examples
 ---
 
 # Streamlining Question Answering: Simplifying Integration with LangChain and Qdrant

qdrant-landing/content/articles/late-interaction-models.md

@@ -8,6 +8,7 @@ weight: -160
 author: Kacper Łukawski
 author_link: https://kacperlukawski.com
 date: 2024-08-14T00:00:00.000Z
+category: machine-learning
 ---
 
 \* At least any open-source model, since you need access to its internals.

qdrant-landing/content/articles/machine-learning/_index.md

@@ -0,0 +1,8 @@
+---
+title: Machine Learning
+description: Explore Machine Learning principles and practices which make modern semantic similarity search possible. Apply Qdrant and vector search capabilities to your ML projects.
+category: machine-learning
+url: /articles/machine-learning/
+isCategoryPage: true
+weight: 40
+---

qdrant-landing/content/articles/memory-consumption.md

@@ -9,6 +9,7 @@ weight: 7
 author: Andrei Vasnetsov
 author_link: https://blog.vasnetsov.com/
 date: 2022-12-07T10:18:00.000Z
+category: qdrant-internals
 # aliases: [ /articles/memory-consumption/ ]
 ---
 

qdrant-landing/content/articles/metric-learning-tips.md

@@ -10,6 +10,7 @@ weight: 20
 author: Andrei Vasnetsov
 author_link: https://blog.vasnetsov.com/
 date: 2021-05-15T10:18:00.000Z
+category: machine-learning
 # aliases: [ /articles/metric-learning-tips/ ]
 ---
 

qdrant-landing/content/articles/modern-sparse-neural-retrieval.md

@@ -12,6 +12,7 @@ tags:
   - sparse retrieval
   - splade
   - bm25
+category: machine-learning
 ---
 
 Finding enough time to study all the modern solutions while keeping your production running is rarely feasible.

qdrant-landing/content/articles/multitenancy.md

@@ -14,6 +14,7 @@ keywords:
   - custom sharding
   - multiple partitions
   - vector database
+category: vector-search-manuals
 ---
 
 # Scaling Your Machine Learning Setup: The Power of Multitenancy and Custom Sharding in Qdrant 

qdrant-landing/content/articles/neural-search-tutorial.md

@@ -10,6 +10,7 @@ weight: 50
 author: Andrey Vasnetsov
 author_link: https://blog.vasnetsov.com/
 date: 2021-06-10T10:18:00.000Z
+category: vector-search-manuals
 # aliases: [ /articles/neural-search-tutorial/ ]
 ---
 # Neural Search 101: A Comprehensive Guide and Step-by-Step Tutorial

qdrant-landing/content/articles/practicle-examples/_index.md

@@ -0,0 +1,8 @@
+---
+title: Practical Examples
+description: Building blocks and reference implementations to help you get started with Qdrant. Learn how to use Qdrant to solve real-world problems and build the next generation of AI applications.
+category: practicle-examples
+url: /articles/practicle-examples/
+isCategoryPage: true
+weight: 60
+---

qdrant-landing/content/articles/product-quantization.md

@@ -14,6 +14,7 @@ keywords:
   - vector search
   - product quantization
   - memory optimization
+category: qdrant-internals
 aliases: [ /articles/product_quantization/ ]
 ---
 

qdrant-landing/content/articles/qa-with-cohere-and-qdrant.md

@@ -16,6 +16,7 @@ keywords:
   - cohere
   - co.embed
   - embeddings
+category: practicle-examples
 ---
 
 Bi-encoders are probably the most efficient way of setting up a semantic Question Answering system. 

qdrant-landing/content/articles/qdrant-internals/_index.md

@@ -0,0 +1,8 @@
+---
+title: Qdrant Internals
+description: Take a look under the hood of Qdrant’s high-performance vector search engine. Explore the architecture, components, and design principles the Qdrant Vector Search Engine is built on.
+category: qdrant-internals
+url: /articles/qdrant-internals/
+isCategoryPage: true
+weight: 20
+---

qdrant-landing/content/articles/rag-and-genai/_index.md

@@ -0,0 +1,8 @@
+---
+title: RAG & GenAI
+description: Leverage Qdrant for Retrieval-Augmented Generation (RAG) and build AI Agents
+category: rag-and-genai
+url: /articles/rag-and-genai/
+isCategoryPage: true
+weight: 50
+---

qdrant-landing/content/articles/rag-is-dead.md

@@ -15,6 +15,7 @@ keywords:
   - vector search
   - retrieval augmented generation
   - gemini 1.5
+category: rag-and-genai
 ---
 
 # Is RAG Dead? The Role of Vector Databases in AI Efficiency and Vector Search 

qdrant-landing/content/articles/rapid-rag-optimization-with-qdrant-and-quotient.md

@@ -17,6 +17,7 @@ keywords:
 - quotient
 - optimization
 - rag
+category: rag-and-genai
 ---
 
 In today's fast-paced, information-rich world, AI is revolutionizing knowledge management. The systematic process of capturing, distributing, and effectively using knowledge within an organization is one of the fields in which AI provides exceptional value today. 

qdrant-landing/content/articles/scalar-quantization.md

@@ -14,6 +14,7 @@ keywords:
   - vector search
   - scalar quantization
   - memory optimization
+category: qdrant-internals
 ---
 # Efficiency Unleashed: The Power of Scalar Quantization
 

qdrant-landing/content/articles/search-as-you-type.md

@@ -11,6 +11,7 @@ author_link: https://llogiq.github.io
 date: 2023-08-14T00:00:00+01:00
 draft: false
 keywords: search, semantic, vector, llm, integration, benchmark, recommend, performance, rust
+category: practicle-examples
 ---
 
 Qdrant is one of the fastest vector search engines out there, so while looking for a demo to show off, we came upon the idea to do a search-as-you-type box with a fully semantic search backend. Now we already have a semantic/keyword hybrid search on our website. But that one is written in Python, which incurs some overhead for the interpreter. Naturally, I wanted to see how fast I could go using Rust.

qdrant-landing/content/articles/semantic-cache-ai-data-retrieval.md

@@ -18,6 +18,7 @@ tags:
   - AI applications
   - data retrieval
   - efficient data storage
+category: rag-and-genai
 ---
 
 ## What is Semantic Cache?

qdrant-landing/content/articles/serverless.md

@@ -11,6 +11,7 @@ author_link: https://llogiq.github.io
 date: 2023-07-12T10:00:00+01:00
 draft: false
 keywords: rust, serverless, lambda, semantic, search
+category: practicle-examples
 ---
 
 Do you want to insert a semantic search function into your website or online app? Now you can do so - without spending any money! In this example, you will learn how to create a free prototype search engine for your own non-commercial purposes.

qdrant-landing/content/articles/sparse-vectors.md

@@ -15,6 +15,7 @@ keywords:
   - SPLADE
   - hybrid search
   - vector search
+category: vector-search-manuals
 ---
 
 Think of a library with a vast index card system. Each index card only has a few keywords marked out (sparse vector) of a large possible set for each book (document). This is what sparse vectors enable for text.