Sign in
Categories
Your Saved List Become a Channel Partner Sell in AWS Marketplace Amazon Web Services Home Help

Reviews from AWS Marketplace

27 AWS reviews

External reviews

66 reviews
from G2

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


4-star reviews ( Show all reviews )

    Information Technology and Services

Production-ready vector database to get you started quickly

  • November 16, 2023
  • Review verified 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 verified 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.


    Computer Software

Solid Hosted Vector DB

  • November 15, 2023
  • Review verified 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 verified by AWS Marketplace

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 verified by AWS Marketplace

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 verified by AWS Marketplace

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 verified by AWS Marketplace

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.