Develop & Implement on Qdrant - Vector Search Engine

Async API

info@qdrant.tech (Andrey Vasnetsov) — Mon, 01 Jan 0001 00:00:00 +0000

Build High-Throughput Applications with Qdrant’s Async API

Time: 25 min	Level: Intermediate

Asynchronous programming is being broadly adopted in the Python ecosystem. Tools such as FastAPI have embraced this new paradigm, but it is also becoming a standard for ML models served as SaaS. For example, the Cohere SDK provides an async client next to its synchronous counterpart.

Databases are often launched as separate services and are accessed via a network. All the interactions with them are IO-bound and can be performed asynchronously so as not to waste time actively waiting for a server response. In Python, this is achieved by using async/await syntax. That lets the interpreter switch to another task while waiting for a response from the server.

Semantic Search for Code

info@qdrant.tech (Andrey Vasnetsov) — Mon, 01 Jan 0001 00:00:00 +0000

Semantic Search for Code with Qdrant

Time: 45 min	Level: Intermediate

You too can enrich your applications with Qdrant semantic search. In this tutorial, we describe how you can use Qdrant to navigate a codebase, to help you find relevant code snippets. As an example, we will use the Qdrant source code itself, which is mostly written in Rust.

The approach

We want to search codebases using natural semantic queries, and searching for code based on similar logic. You can set up these tasks with embeddings:

Build a Semantic Search API

info@qdrant.tech (Andrey Vasnetsov) — Mon, 01 Jan 0001 00:00:00 +0000

Build a Semantic Search API with Qdrant

Time: 30 min	Level: Beginner	Output: GitHub

This tutorial shows you how to build and deploy your own neural search service to look through descriptions of companies from startups-list.com and pick the most similar ones to your query. The website contains the company names, descriptions, locations, and a picture for each entry.

A neural search service uses artificial neural networks to improve the accuracy and relevance of search results. Besides offering simple keyword results, this system can retrieve results by meaning. It can understand and interpret complex search queries and provide more contextually relevant output, effectively enhancing the user’s search experience.

Serverless Semantic Search

info@qdrant.tech (Andrey Vasnetsov) — Wed, 12 Jul 2023 10:00:00 +0100

Build a Serverless Semantic Search Service with Rust, AWS Lambda, and Qdrant

Time: 45 min	Level: Intermediate

Do you want to add semantic search to your website or online app without running a server? In this tutorial, you build a small search service in Rust on AWS Lambda. For each query, the function embeds the text with Cohere, searches it in Qdrant, and returns the closest texts as JSON. Everything fits in free tiers, so it works as a prototype for your own non-commercial purposes.

Build a Hybrid Search API

info@qdrant.tech (Andrey Vasnetsov) — Mon, 01 Jan 0001 00:00:00 +0000

Build a Search API with Qdrant’s FastEmbed

Time: 20 min	Level: Beginner	Output: GitHub

This tutorial shows you how to build and deploy your own hybrid search service to look through descriptions of companies from startups-list.com and pick the most similar ones to your query. The website contains the company names, descriptions, locations, and a picture for each entry.

As we have already written on our blog, there is no single definition of hybrid search. In this tutorial we are covering the case with a combination of dense and sparse embeddings. The former ones refer to the embeddings generated by such well-known neural networks as BERT, while the latter ones are more related to a traditional full-text search approach.

Semantic Search As You Type

info@qdrant.tech (Andrey Vasnetsov) — Mon, 14 Aug 2023 00:00:00 +0100

Build Search-as-You-Type with Qdrant

Time: 30 min	Level: Intermediate	Output: GitHub

A search-as-you-type box sends a request on almost every keystroke, so it puts a vector search engine under steady load and makes every millisecond of latency visible. This tutorial shows how to build one on Qdrant with a fully semantic backend, and three techniques that keep it fast and relevant:

A prefix cache: embeddings precomputed for short prefixes, so a short query needs no embedding model at all.
Prioritized batch queries: one batch request with four queries, so exact matches and headings come first.
Concurrent fallbacks: both paths start together, so a cache miss costs no extra round trip.

Background

The techniques come from the 2023 rebuild of the Qdrant documentation’s page search. We already had a semantic and keyword hybrid search on the website, written in Python, which had some interpreter overhead. Andre Bogus, who wrote the first version of this article, wanted to see how fast a Rust service could go, and the Rust code is on GitHub. This tutorial teaches the same ideas in Python with the current Query API, so you can run them without a Rust toolchain.