Semantic Search API for Retrieval Augmented Generation (RAG)

What is Semantic Search?

Semantic search is about searching content using natural language, exactly the way Google does. When using semantic search, you don't need to search for exact keywords (also known as keyword search) as the AI is able to understand your request and interpret it.

Let's say that you are an HP printers reseller and that you have have thousands of documents like technical descriptions about printers, prices, terms of service... Maybe you want to make it easy to search these documents on your e-shopping website? See these 3 short documents for example:

Now, imagine that one of your customers asks the following question on your e-shopping website:

The semantic search AI model will return the following in the blink of an eye:

Maybe your customer did not ask a properly formed question? No problem, a query like this would work too:

So as you can see, semantic search is much more advanced than the traditional keyword search, as you can ask questions in natural language like you would do with a human. Additionally, semantic search AI is very good at performing disambiguation (understanding the meaning of a word thanks to its context).

Semantic search is a very good solution when it comes to searching and performing question answering on your own data, because it is both blazing fast and accurate.

If you want to answer questions about a large corpus of internal domain knowledge, you might want to set up a Retrieval Augmented Generation (RAG) system. In that case please read our dedicated article about RAG: read it here.

Semantic search can be achieved by populating a vector database with embeddings, which is the approach that vector database providers like Pinecone or Milvus use. But for the most advanced response times, you will want to create your own semantic search model and deploy it on a GPU, which is what we do at NLP Cloud.

NLP Cloud's Semantic Search API

NLP Cloud proposes a semantic search API that allows you to create your own semantic search engine out of your own business data, and then perform semantic search out of the box, based on the best Sentence Transformers models.
The response time (latency) is very good for these models!

For more details, see our documentation about semantic search here.

Testing semantic search locally is one thing, but using it reliably in production is another thing. With NLP Cloud you can just do both!