External reviews are not included in the AWS star rating for the product.
My main use case for Pinecone involves storage of chat data, specifically chat transcripts, and retrieval of matched chat messages.
We store chat transcripts as vectors in Pinecone. When we have a new chat message, we utilize a retrieval mechanism to match and find the last five messages so that it can act as a memory. Essentially, Pinecone serves as a long-term memory for our application, while we use Redis for our short-term memory.
We were looking at multiple options for a vector database, and we found Pinecone to be the easiest to integrate into our solution. Plus, it has a very generous free tier, which helps us as a startup.
The best features Pinecone offers are quick setup and good indexing for us. The retrieval mechanisms are fast, and the integration with Python as with JavaScript and TypeScript libraries that Pinecone provides are very robust. Authentication is also very good.
The namespaces feature allows us to break down or store data for each user separately, reducing interference and maintaining privacy as an important feature.
Pinecone has positively impacted our organization by enhancing efficiency for the team, and the long-term effect has been that the chats have become much more personalized due to the memory added through a vector database. We are seeing that the trainees getting trained on the platform are more satisfied with the results or messages generated by AI.
One major issue I have noticed with Pinecone is that it does not allow me to search based on metadata. This can cause problems because while vector indexing or vector search is good, if you populate certain categories of messages or metadata into a vector database, searching through the data using the filter of metadata is not possible.
For our requirements, Pinecone is more than enough. If improvements are required, I would suggest taking a look at the embeddings and possibly improving the embedding sizes.
I have been using Pinecone with code for one and a half years.
Pinecone is very stable.
Pinecone's scalability is pretty decent for us, as we have not encountered issues. We are storing close to around 600K items or entries in the database, and our indexing and retrievals are within seconds, often in microseconds.
The customer support of Pinecone is very good; you send an email and receive a response within a few hours, typically four to five hours. Additionally, you can set up a call if needed.
Since we are on the minimal plan, I would rate the customer support around 8 out of 10.
Positive
We previously tried setting up with Weaviate and another solution. During my research, we checked out a couple of options, including an on-prem solution that I tried to set up on my machine, but it was very painful, so we went with the cloud service provider because the setup was nearly nonexistent.
The setup cost for us is nil, and the licensing and pricing are pretty decent. Pinecone works on the storage amount, so our bills are pretty low, and we are good.
The setup cost for us is nil, and the licensing and pricing are pretty decent. Pinecone works on the storage amount, so our bills are pretty low, and we are good.
Before choosing Pinecone, I evaluated a few options, including Weaviate.
I would suggest that Pinecone is one of the best options available. I would rank it in the top three for vector databases and qualify it as number one in the market. There are many others such as Weaviate and Milvus, but they come with certain issues such as lacking a free tier or having a very low one.
Moreover, solutions like Milvus and FAISS are on-prem, which makes setup and stability a pain, primarily catering to big enterprises. For startups, Pinecone is indeed the best.
We are just a client of Pinecone; we do not have any other business relationship.
Rating: 4/5
I decided to use Pinecone DB as the vector database for Amazon Bedrock Knowledge Bases. My application required that I use Retrieval Augmented Generation (RAG) to answer questions about PDF business documents that I have stored in an Amazon S3 bucket. Pinecone DB is incredibly high performance and also offers a free tier, along with centralized billing through AWS Marketplace. I would highly recommend using Pinecone DB!
We recently made the switch to Pinecone database for our vector search needs, and we couldn't be happier with the results! The latencies are lower than we expected, making it a fast and reliable solution for us. Additionally, the metadata filtering works out of the box which is crucial for e-commerce. Overall, we highly recommend Pinecone to anyone in need of an efficient and user-friendly vector search solution.
Pinecone is a great service for anyone who needs fast and accurate vector search for their applications. I have been using Pinecone for a few months now and I am very impressed by its features and performance.
It is easy to manage multiple user accounts with Pinecone. I can invite my team members to join my projects and assign them different roles and permissions. I can also monitor their activities and usage through the web console.
It is good to have a support experience with Pinecone. They have a friendly and responsive team that is always ready to help me with any issues or questions. They also have a comprehensive documentation and a community forum where I can find answers and tips.
The Pinecone pay as you go marketplace offering made it easy for us to quickly get up and running to do our evaluation of the tool. The pricing link to their website in the marketplace description is easy to understand and accurate based on our usage of the tool.
I started using Pinecone with a free account when prototyping a new use case for vector search. Pinecone proved easy to work with and simple to get something working off the ground into the hands of my company. I was quite pleased with the setup process moving to the AWS marketplace as we put this prototype into production. It was simple to add to our existing AWS account, the Pinecone UI connects nicely to our test account so I can switch between production and test with ease - really useful for local development and debugging. Overall found the experience working with Pinecone to be great. There are certain areas that would be great to improve, the Node library was a bit funky when I first started using it (but that was a pre 1.0 version), the dashboard in the UI could add a few additional features to navigate and visualize what is stored in the DB, but those are all minor nice to haves that I'm sure will come. The search quality and reliability has been great and that was most critical to our needs right now.l
Pinecone's vector database, with its exceptional performance and user-friendly interface, earns a solid five-star rating. It excels in managing large-scale vector data, offering both fast and accurate search capabilities. The integration process is straightforward, making it accessible for various applications, particularly in machine learning and AI-driven contexts.
We are happy with our decision to build on top of Pinecone's marketplace solution. It was super easy to get up and running, and so far we have been really happy with query performance and data management features both in the Pinecone console and via the API. The developer docs are great. Would definitely be on the top of my list for the next project.
Awaiting for an expansion in the number of AWS cloud regions they are available, as of this writing us-east-1 was the only option.
Been on Pinecone since a while and I'm quite liking it. I did try a few other competitors but the unique namespace concept and various other features makes life easier and at the moment doing great.
Great work team.. Keep it up.
At one point we tried using OpenSearch since our application is solely hosted in AWS, but we found it to be too expensive and troublesome to setup and maintain. Pinecone was a great help for us since everything is quite easy, the latency is good (less than one second to do vector comparisons, our dataset has millions of observations), and is less expensive than Opensearch (also the pricing is more straight-forward).
There are some extra functionalities we would like to have in pinecone, like getting all results from a query that are above a certain threshold (and not just top_k) but that is minor. I think it is a pretty solid option for vector search applications.
