Add bloop case study (#115)

* Add Bloop case study * Add draft variable * docs auto-sync * Fix YAML formatting * Add footnotes * Fix case studies layout * Add links to https://bloop.ai/ * Add images and change case studies layout * Reduce logo size * Add schema.org desc into case-studies * Add PNG as a social preview image * Resize social preview to 1200x627 --------- Co-authored-by: qdrant <qdrant@users.noreply.github.com>
2026-09-26 06:28:30 +02:00 · 2023-02-28 11:59:22 +01:00
parent fe571ff1ad
commit 3691f76889
16 changed files with 155 additions and 1 deletions
@@ -0,0 +1,94 @@
+---
+title: "Qdrant case study: bloop semantic code search"
+short_description: bloop is a fast code-search engine that combines semantic search, regex search and precise code navigation
+description: bloop is a fast code-search engine that combines semantic search, regex search and precise code navigation
+social_preview_image: /case_studies_data/bloop/social_preview.png
+preview_dir: /case_studies_data/bloop/preview
+date: 2023-02-28T11:48:00.000Z
+---
+
+Founded in early 2021, [bloop](https://bloop.ai/) was one of the first companies to tackle semantic 
+search for codebases. A fast, reliable Vector Search Database is a core component of a semantic 
+search engine, and bloop surveyed the field of available solutions and even considered building 
+their own. They found Qdrant to be the top contender and now use it in production.
+
+This document is intended as a guide for people who intend to introduce semantic search to a novel 
+field and want to find out if Qdrant is a good solution for their use case.
+
+## About bloop
+
+![](/case_studies_data/bloop/screenshot.png)
+
+[bloop](https://bloop.ai/) is a fast code-search engine that combines semantic search, regex search 
+and precise code navigation into a single lightweight desktop application that can be run locally. It 
+helps developers understand and navigate large codebases, enabling them to discover internal libraries, 
+reuse code and avoid dependency bloat. bloop’s chat interface explains complex concepts in simple 
+language so that engineers can spend less time crawling through code to understand what it does, and 
+more time shipping features and fixing bugs.
+
+![](/case_studies_data/bloop/bloop-logo.png)
+
+bloop’s mission is to make software engineers autonomous and semantic code search is the cornerstone 
+of that vision. The project is maintained by a group of Rust and Typescript engineers and ML researchers. 
+It leverages many prominent nascent technologies, such as [Tauri](http://tauri.app), [tantivy](https://docs.rs/tantivy), 
+[Qdrant](http://qdrant.tech) and [Anthropic](https://www.anthropic.com/).
+
+## About Qdrant
+
+![](/case_studies_data/bloop/qdrant-logo.png)
+
+Qdrant is an open-source Vector Search Database written in Rust . It deploys as an API service providing 
+a search for the nearest high-dimensional vectors. With Qdrant, embeddings or neural network encoders 
+can be turned into full-fledged applications for matching, searching, recommending, and many more solutions 
+to make the most of unstructured data. It is easy to use, deploy and scale, blazing fast and is accurate 
+simultaneously.
+
+Qdrant was founded in 2021 in Berlin by Andre Zayarni and Andrey Vasnestov with the mission to power the 
+next generation of AI applications with advanced and high-performant vector similarity search technology. 
+Their flagship product is the vector search database which is available as an open source 
+https://github.com/qdrant/qdrant or managed cloud solution https://cloud.qdrant.io/.
+
+## The Problem
+
+Firstly, what is semantic search? It’s finding relevant information by comparing meaning, rather than 
+simply measuring the textual overlap between queries and documents. We compare meaning by comparing 
+*embeddings* - these are vector representations of text that are generated by a neural network. Each document’s 
+embedding denotes a position in a *latent* space, so to search you embed the query and find its nearest document 
+vectors in that space.
+
+![](/case_studies_data/bloop/vector-space.png)
+
+Why is semantic search so useful for code? As engineers, we often don’t know - or forget - the precise terms 
+needed to find what we’re looking for. Semantic search enables us to find things without knowing the exact 
+terminology. For example, if an engineer wanted to understand “*What library is used for payment processing?*” 
+a semantic code search engine would be able to retrieve results containing “*Stripe*” or “*PayPal*”. A traditional 
+lexical search engine would not.
+
+One peculiarity of this problem is that the **usefulness of the solution increases with the size of the code 
+base** – if you only have one code file, you’ll be able to search it quickly, but you’ll easily get lost in 
+thousands, let alone millions of lines of code. Once a codebase reaches a certain size, it is no longer 
+possible for a single engineer to have read every single line, and so navigating large codebases becomes 
+extremely cumbersome.
+
+In software engineering, we’re always dealing with complexity. Programming languages, frameworks and tools 
+have been developed that allow us to modularize, abstract and compile code into libraries for reuse. Yet we 
+still hit limits: Abstractions are still leaky, and while there have been great advances in reducing incidental 
+complexity, there is still plenty of intrinsic complexity[^1] in the problems we solve, and with software eating 
+the world, the growth of complexity to tackle has outrun our ability to contain it. Semantic code search helps 
+us navigate these inevitably complex systems.
+
+But semantic search shouldn’t come at the cost of speed. Search should still feel instantaneous, even when 
+searching a codebase as large as Rust (which has over 2.8 million lines of code!). Qdrant gives bloop excellent 
+semantic search performance whilst using a reasonable amount of resources, so they can handle concurrent search 
+requests.
+
+## The Upshot
+
+[bloop](https://bloop.ai/) are really happy with how Qdrant has slotted into their semantic code search engine: 
+it’s performant and reliable, even for large codebases. And it’s written in Rust(!) with an easy to integrate 
+qdrant-client crate. In short, Qdrant has helped keep bloop’s code search fast, accurate and reliable.
+
+#### Footnotes:
+
+[^1]: Incidental complexity is the sort of complexity arising from weaknesses in our processes and tools, whereas 
+      intrinsic complexity is the sort that we face when trying to describe, let alone solve the problem.
@@ -279,7 +279,7 @@ client.clear_payload(
 ## Payload indexing

 To search more efficiently with filters, Qdrant allows you to specify payload fields as indexed.
-For marked fields will Qdrant will build an index for the corresponding types of queries.
+For marked fields Qdrant will build an index for the corresponding types of queries.

 The indexed fields also affect the vector index. See [Indexing](../indexing) for details.

@@ -0,0 +1,10 @@
+{{- partial "header.html" . -}}
+
+{{- partial "second_header.html" . -}}
+
+<div id="content">
+    {{ block "main" . }}{{ end }}
+</div>
+
+{{ partial "contact-section" . }}
+{{- partial "footer.html" . -}}
@@ -0,0 +1,2 @@
+{{ define "main" }}
+{{ end }}
@@ -0,0 +1,34 @@
+{{ partial "header" . }}
+<div class="auto-container pt-3 pt-md-2 mb-5">
+    <div class="row clearfix">
+        <!-- Content Side -->
+        <section class="col-lg-12 col-md-12 col-sm-12">
+            {{ .Scratch.Set "scope" "single" }}
+            <article class="article article_narrow article_bb mb-4">
+                <div class="article__cover mt-lg-5 mb-4">
+                    <picture>
+                        <source srcset="{{ .Params.preview_dir }}/title.webp" type="image/webp">
+                        <img src="{{ .Params.preview_dir }}/title.jpg">
+                    </picture>
+                </div>
+                <h1>{{ .Title }}</h1>
+                {{ .Content }}
+            </article>
+        </section>
+    </div>
+</div>
+<div style="background: var(--brand-light);">
+    <div class="auto-container pt-5 pb-5">
+        <div class="row clearfix pt-4">
+            {{ range where site.Pages "Section" "articles" | first 3 }}
+
+            <!-- Project Block -->
+            <div class="d-flex col-md-4 col-sm-12">
+                {{ partial "article-card" (dict "context" .) }}
+            </div>
+            {{ end }}
+        </div>
+    </div>
+</div>
+{{ partial "contact-section" . }}
+{{ partial "footer" . }}
@@ -91,6 +91,20 @@
        }]
    }
 </script>
+{{ else if and (eq .Section "case-studies") .IsPage }}
+<script type="application/ld+json">
+    {
+        "@context": "https://schema.org",
+        "@type": "Article",
+        "headline": "{{ .Params.title }}",
+        "image": [
+            {{ .Params.social_preview_image  | absURL }},
+        ],
+        "abstract": {{ .Params.description }},
+        "datePublished": {{ .Params.date }},
+        "dateModified": {{ .Params.date }}
+    }
+</script>
 {{ end }}

 {{ $url := urls.Parse .Site.BaseURL }}