Sign in
Sign in
or
Create a new account
Agent Mode
Categories
Your Saved List Become a Channel Partner Sell in AWS Marketplace Amazon Web Services Home Help

Pinecone Vector Database - Pay As You Go Pricing

Pinecone

Reviews from AWS customer

29 AWS reviews

External reviews

45 reviews
from and

External reviews are not included in the AWS star rating for the product.

4-star reviews ( Show all reviews )

    Cristian V.

fast and easy to setup vector database

  • November 16, 2023
  • Review provided by G2

What do you like best about the product?
The things I mostly like are:
- that is easy to set up by following the docs
- fast for loading and updating embeddings in the index
- easy to scale if needed
What do you dislike about the product?
- that is not open source
- I cannot query the full list of ids from an index (I needed to build a database and a script to track what products I have inside the index)
- customer support by mail takes too much time
What problems is the product solving and how is that benefiting you?
I built a deep learning model for product matching in the ecommerce industry. One of the steps for the system is to find candidates that are potential matches for the searched product. Becase of this, I needed a vector database to store the embeddings (texts and image) for the products for doing a similarity search as a first step of the product matching system.

    Archontellis Rafail S.

GWI on Pinecone

  • November 16, 2023
  • Review provided by G2

What do you like best about the product?
Easy of use and metadata filtering. Pinecone is one of the few products out there that is performant with a query that contains metadata filtering.
What do you dislike about the product?
The pricing doesn't scale well for companies with millions of vectors, especially for p indexes. We experimented with pgvector to move our vectors in a postgres but the metadata filtering performance was not acceptable with the current indexes it supports.
What problems is the product solving and how is that benefiting you?
Semantic search for now.

    Information Technology and Services

Production-ready vector database to get you started quickly

  • November 16, 2023
  • Review provided by G2

What do you like best about the product?
- Good documentation and usage examples
- Easy-to-use Python SDK
- Production-ready with low latency at our scale (10-20M vectors)
- Good integration with the AI/LLM ecosystem
What do you dislike about the product?
- did not find an easy way to export all vectors that we needed for data science/cleaning
- will get expensive when hosting 100s of millions of vectors
What problems is the product solving and how is that benefiting you?
We use Pinecone as a vector database for retrieval augmented generation using LLMs.

    Computer Software

Solid Hosted Vector DB

  • November 15, 2023
  • Review provided by G2

What do you like best about the product?
Ease of deployment! It takes just a few minutes to get an index set up and deployed.
What do you dislike about the product?
The web-based API console could be improved, for example for experiments with metric (cosine vs dotproduct vs euclidean).
What problems is the product solving and how is that benefiting you?
Storing embeddings for RAG.

    Santhosh

Fast VectorDB and Easy to Use

  • November 14, 2023
  • Review from a verified AWS customer

We are using pinecone since a couple of months, we found its fast, easy to use, it has great client library. Ingestion and retrieval speed is great. Collections are great way to backup vector dbs .

    Matteo

Easy, powerful and so far unique

  • November 14, 2023
  • Review from a verified AWS customer

We've been using Pinecone as primary store for sparse / dense vectors in several business cases since some months.
We also did a direct comparison with other solutions but so far Pinecone stands as our selection of choice.

PROs
- Cloud-base managed "as a service" solution: zero installation/maintenance effort
- Easy to implement thanks to outstanding documentation
- Best in class performances
- So far "unique" hybrid search proposition (dense=semantic and sparse=keyword vectors support)

CONs
- Management tools still not mature/complete and evolving
- Basic access control / profiling mechanisms
- Basic logging tools
- Base price for smallest index still a little high for small business cases

Generally speaking you cannot expect to find in a vector DB (which is a quite recent class of tools) the same maturity of a RDBMS, in terms of completeness of the solutions and availability of tools.
Said that, Pinecone sticks to its core job and does it smoothly, no complains so far from our side.
A pleasant plus is the huge and very comprehensive documentation available, which covers a lot of background theory as well.

We are not giving the 5th star since the product is still young, but the direction it the correct one!

    Lucien

Nice and easy to use

  • November 14, 2023
  • Review from a verified AWS customer

I am using Pinecone for my LLM-based app and switching to the Pay As You Go worked seamlessly. It's actually cheaper than hosting the solution.

    Review

Feedback about Pinecone

  • November 08, 2023
  • Review from a verified AWS customer

Performance is quite good for vector storage and retrieval. I feel that cost is bit at higher side. We need to know have better visibility of new features coming into future releases.

showing 21 - 28