mirror of
https://github.com/qdrant/landing_page.git
synced 2026-09-29 07:58:31 +02:00
aa1acf0acb
* Created Dev-portal pages * changed structure of documents for dev-portal section, renamed dev-portal to docs, related template changes * keeping learn section for future usage * update dev-portal and documents * added feedback and breadcrumbs components * used the docs-side menu partial on documentation pages, and added active state to the docs-header links * search console on docs * small fixes * assigned partitions, css fix * fix links on the core page * update links for cloud * update links for build * Reference -> API Reference * [WIP] Dev portal light theme (#1250) * light theme - docs side menu * background fix * wip: updating layout * layout update * light theme * card titles with a link * upd page-search package * simplified header * fixes * TOC scroll spy (#1259) * scroll spy on table of contents * packages versions fix * custom scroll spy for toc * make spy work again --------- Co-authored-by: generall <andrey@vasnetsov.com> * limit toc depth to 3 * thin scrollbar * No dev template (#1266) * divided the docs template into smaller partials, increased reusability * removed docs section, moved all to the documentation * review fixes * review fixes --------- Co-authored-by: generall <andrey@vasnetsov.com> * side panel more compact * toc margin bottom fix * Refactoring and renaming (#1277) * renamed and moved partials, fixed link * refactoring: docs-card * fix * fix urls * disable scrollbar on table of content * added scrollbar colors for light theme (#1280) * fix language * Dev portal fixes (#1285) * cards fixes * moved files, fixed paddings * fix for my fix * external header links * fix --------- Co-authored-by: trean <trean.mi@gmail.com> Co-authored-by: Andrey Vasnetsov <andrey@vasnetsov.com> Co-authored-by: davidmyriel <davidmyriel@gmail.com>
28 lines
1.4 KiB
Markdown
28 lines
1.4 KiB
Markdown
---
|
||
title: "FastEmbed"
|
||
weight: 6
|
||
partition: qdrant
|
||
---
|
||
|
||
# What is FastEmbed?
|
||
FastEmbed is a lightweight Python library built for embedding generation. It supports popular embedding models and offers a user-friendly experience for embedding data into vector space.
|
||
|
||
By using FastEmbed, you can ensure that your embedding generation process is not only fast and efficient but also highly accurate, meeting the needs of various machine learning and natural language processing applications.
|
||
|
||
FastEmbed easily integrates with Qdrant for a variety of multimodal search purposes.
|
||
|
||
## How to get started with FastEmbed
|
||
|
||
|Beginner|Advanced|
|
||
|:-:|:-:|
|
||
|[Generate Text Embedings with FastEmbed](/documentation/fastembed/fastembed-quickstart/)|[Combine FastEmbed with Qdrant for Vector Search](/documentation/fastembed/fastembed-semantic-search/)|
|
||
|
||
## Why is FastEmbed useful?
|
||
|
||
- Light: Unlike other inference frameworks, such as PyTorch, FastEmbed requires very little external dependencies. Because it uses the ONNX runtime, it is perfect for serverless environments like AWS Lambda.
|
||
- Fast: By using ONNX, FastEmbed ensures high-performance inference across various hardware platforms.
|
||
- Accurate: FastEmbed aims for better accuracy and recall than models like OpenAI’s `Ada-002`. It always uses model which demonstrate strong results on the MTEB leaderboard.
|
||
- Support: FastEmbed supports a wide range of models, including multilingual ones, to meet diverse use case needs.
|
||
|
||
|