move blogs

2026-09-30 16:38:31 +02:00 · 2024-09-18 15:45:54 -07:00
parent 6619392051
commit e1dfb602a6
27 changed files with 27 additions and 35 deletions
@@ -1,14 +1,11 @@
 ---
-draft: false
+title: "Mastering Batch Search for Vector Optimization"
-title: Mastering Batch Search for Vector Optimization | Qdrant 
+short_description: "Introducing efficient batch vector search capabilities, streamlining and optimizing large-scale searches for enhanced performance."
 slug: batch-vector-search-with-qdrant
 short_description: Introducing efficient batch vector search capabilities,
  streamlining and optimizing large-scale searches for enhanced performance.
 description: "Discover how to optimize your vector search capabilities with efficient batch search. Learn optimization strategies for faster, more accurate results."
-preview_image: /blog/from_cms/andrey.vasnetsov_career_mining_on_the_moon_with_giant_machines_813bc56a-5767-4397-9243-217bea869820.png
+preview_dir: /articles_data/batch-vector-search-with-qdrant/preview
-date: 2022-09-26T15:39:53.751Z
+social_preview_image: /articles_data/batch-vector-search-with-qdrant/social_preview.png
 author: Kacper Łukawski
-featured: false
+date: 2022-09-26T00:00:00-08:00
 tags:
  - Data Science
  - Vector Database
@@ -1,20 +1,19 @@
 ---
-draft: false
+title: "Full-text filter and index are already available!"
 title: Full-text filter and index are already available!
 slug: qdrant-introduces-full-text-filters-and-indexes
-short_description: Qdrant v0.10 introduced full-text filters
+short_description: "Qdrant v0.10 introduced full-text filters."
-description: Qdrant v0.10 introduced full-text filters and indexes to enable
+description: "Qdrant v0.10 introduced full-text filters and indexes to enable more search capabilities for those working with textual data." 
-  more search capabilities for those working with textual data.
+preview_dir: /articles_data/qdrant-introduces-full-text-filters-and-indexes/preview
-preview_image: /blog/from_cms/andrey.vasnetsov_black_hole_sucking_up_the_word_tag_cloud_f349586d-3e51-43c5-9e5e-92abf9a9e871.png
+social_preview_image: /articles_data/qdrant-introduces-full-text-filters-and-indexes/social_preview.jpg
 date: 2022-11-16T09:53:05.860Z
 author: Kacper Łukawski
-featured: false
+date: 2022-11-16T00:00:00-08:00
 tags:
  - Information Retrieval
  - Database
  - Open Source
  - Vector Search Database
 ---
 Qdrant is designed as an efficient vector database, allowing for a quick search of the nearest neighbours. But, you may find yourself in need of applying some extra filtering on top of the semantic search. Up to version 0.10, Qdrant was offering support for keywords only. Since 0.10, there is a possibility to apply full-text constraints as well. There is a new type of filter that you can use to do that, also combined with every other filter type.
 ## Using full-text filters without the payload index
@@ -1,14 +1,12 @@
 ---
 title: "Semantic Cache: Accelerating AI with Lightning-Fast Data Retrieval"
 draft: false
 slug:  
 short_description: "Semantic Cache for Best Results and Optimization."
 description: "Semantic cache is reshaping AI applications by enabling rapid data retrieval. Discover how its implementation benefits your RAG setup." 
-preview_image: /blog/semantic-cache-ai-data-retrieval/social_preview.png
+preview_dir: /articles_data/semantic-cache-ai-data-retrieval/preview
-social_preview_image: /blog/semantic-cache-ai-data-retrieval/social_preview.png
+social_preview_image: /articles_data/semantic-cache-ai-data-retrieval/social_preview.png
 date: 2024-05-07T00:00:00-08:00
 author: Daniel Romero, David Myriel
-featured: false 
+author_link: https://github.com/davidmyriel
 date: 2024-05-07T00:00:00-08:00
 tags:
  - vector search
  - vector database
@@ -19,6 +17,7 @@ tags:
  - data retrieval
  - efficient data storage
 ---
 ## What is Semantic Cache?
 **Semantic cache** is a method of retrieval optimization, where similar queries instantly retrieve the same appropriate response from a knowledge base. 
@@ -27,7 +26,7 @@ Semantic cache differs from traditional caching methods. In computing, **cache**
 > The term **"semantic"** implies that the cache takes into account the meaning or semantics of the data or computation being cached, rather than just its syntactic representation. This can lead to more efficient caching strategies that exploit the structure or relationships within the data or computation.
-![semantic-cache-question](/blog/semantic-cache-ai-data-retrieval/semantic-cache-question.png)
+![semantic-cache-question](/articles_data/semantic-cache-ai-data-retrieval/semantic-cache-question.png)
 Traditional caches operate on an exact match basis, while semantic caches search for the meaning of the key rather than an exact match. For example, **"What is the capital of Brazil?"** and **"Can you tell me the capital of Brazil?"** are semantically equivalent, but not exact matches. A semantic cache recognizes such semantic equivalence and provides the correct result. 
@@ -43,7 +42,7 @@ Qdrant is recommended for setting up semantic cache as semantically evaluates th
 **Diagram:** Semantic cache improves RAG by directly retrieving stored answers to the user. **Follow along with the gif** and see how semantic cache stores and retrieves answers.
-![Alt Text](/blog/semantic-cache-ai-data-retrieval/semantic-cache.gif)
+![Alt Text](/articles_data/semantic-cache-ai-data-retrieval/semantic-cache.gif)
 When using a key-value cache, it's important to consider that slight variations in question wording can lead to different hash values. The two questions convey the same query but differ in wording. A naive cache search might fail due to distinct hashed versions of the questions. Implementing a more nuanced approach is necessary to accommodate phrasing variations and ensure accurate responses.
@@ -79,6 +78,6 @@ The first part of this video explains how caching works. In the second part, you
 [Qdrant](https://github.com/qdrant/qdrant) offers the most flexible way to implement vector search for your RAG and AI applications. You can test out semantic cache on your free Qdrant Cloud instance today! Simply sign up for or log into your [Qdrant Cloud account](https://cloud.qdrant.io/login) and follow our [documentation](/documentation/cloud/).
-You can also deploy Qdrant locally and manage via our UI. To do this, check our [Hybrid Cloud](/blog/hybrid-cloud/)!
+You can also deploy Qdrant locally and manage via our UI. To do this, check our [Hybrid Cloud](/articles_data/hybrid-cloud/)!
-[![hybrid-cloud-get-started](/blog/hybrid-cloud-launch-partners/hybrid-cloud-get-started.png)](https://cloud.qdrant.io/login)
+[![hybrid-cloud-get-started](/articles_data/hybrid-cloud-launch-partners/hybrid-cloud-get-started.png)](https://cloud.qdrant.io/login)
@@ -1,14 +1,11 @@
 ---
-draft: false
+title: "Optimizing Semantic Search by Managing Multiple Vectors"
-title: Optimizing Semantic Search by Managing Multiple Vectors
+short_description: "Qdrant's approach to storing multiple vectors per object, unraveling new possibilities in data representation and retrieval."
-slug: storing-multiple-vectors-per-object-in-qdrant
+description: "Discover the power of vector storage optimization and learn how to efficiently manage multiple vectors per object for enhanced semantic search capabilities." 
-short_description: Qdrant's approach to storing multiple vectors per object,
+preview_dir: /articles_data/storing-multiple-vectors-per-object-in-qdrant/preview
-  unraveling new possibilities in data representation and retrieval.
+social_preview_image: /articles_data/storing-multiple-vectors-per-object-in-qdrant/social_preview.png
 description: Discover the power of vector storage optimization and learn how to efficiently manage multiple vectors per object for enhanced semantic search capabilities.
 preview_image: /blog/from_cms/andrey.vasnetsov_a_space_station_with_multiple_attached_modules_853a27c7-05c4-45d2-aebc-700a6d1e79d0.png
 date: 2022-10-05T10:05:43.329Z
 author: Kacper Łukawski
-featured: false
+date: 2024-09-18T00:00:00-08:00
 tags:
  - Data Science
  - Neural Networks