---
title: "Discussion on \"Question Answering as a Service with Cohere and Qdrant\" | Hashnode"
description: "Discussion on \"Question Answering as a Service with Cohere and Qdrant\". Bi-encoders are probably the most efficient way of setting up a semantic Question Answering system. This architecture relies on the same neural model that creates vector embeddings for both questions and answers. The assumption is, both question and ..."
url: "https://hashnode.com/posts/question-answering-as-a-service-with-cohere-and-qdrant/63878831c76de7c43e622b05"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [Question Answering as a Service with Cohere and Qdrant](https://vectorsearch.hashnode.dev/question-answering-as-a-service-with-cohere-and-qdrant?utm_source=hashnode&utm_medium=feed)

Bi-encoders are probably the most efficient way of setting up a semantic Question Answering system. This architecture relies on the same neural model that creates vector embeddings for both questions and answers. The assumption is, both question and ...

Nov 30, 2022 · 1 min read · vectorsearch.hashnode.dev  
Read the article

-   [#vectorsearch](https://hashnode.com/tag/vectorsearch)
-   [#vector-similarity](https://hashnode.com/tag/vector-similarity)

## Written by

[Qdrant](https://hashnode.com/@qdrant)

@qdrant · Germany

  
[View profile](https://hashnode.com/@qdrant)

Vector similarity search engine with advanced filtering support

Qdrant (read: quadrant ) is a vector similarity search engine. It provides a production-ready service with a convenient API to store, search, and manage points - vectors with an additional payload. Qdrant is tailored to extended filtering support. It makes it useful for all sorts of neural-network or semantic-based matching, faceted search, and other applications. Qdrant is written in Rust 🦀, which makes it fast and reliable even under high load. With Qdrant, embeddings or neural network encoders can be turned into full-fledged applications for matching, searching, recommending, and much more!

## Responses

Markdown supported · ⌘↵ to post

No responses yet.
