I have used Pinecone for the last five years, when I started my career in generative AI. It is very useful for creating POCs. I created more than 15 POCs on Pinecone because it is very useful for use and implementation.

I have created many POCs using Pinecone. Let's suppose we have some documents in PDF format. We are getting the data from the text format, chunking and embedding it, and storing it in Pinecone. This is something we do in many applications, mostly in the POCs, because the client is not allowing it to be used on the production server. Mostly we are using the Oracle vector database on the production server. That is the issue from the client side.

I have not used Pinecone in my organization. In most cases, I use Pinecone for small projects as well as POCs. In the small projects, I use private servers for implementation and deployment.

I have not used large data. I use Pinecone for small projects, mostly single files. The file contains more than 100 pages, and it is performing well. There is nothing I'm seeing, such as drawbacks or lagging somewhere. It is working fine for us.

I use it mostly for AI applications, primarily in RAG applications. For the implementation, for the embedding, storing the embedding, and getting the data later, Pinecone works well.

Pinecone is very easy to use and it's very easy to make the connection. I use both cloud-based and local Pinecone, and the performance is much better as compared to other tools for embedding.

Faster retrieval and low latency are significant advantages. The results are mostly correct in most cases.

With Pinecone's features, we can use it both locally and in the cloud. It is a good feature because sometimes we are unable to install Pinecone on a local machine, so we can use the cloud. Pinecone provides credentials so we can directly connect to Pinecone using our script. It is a good feature, so I appreciate what Pinecone company has provided.

It is very fast and it saves us a lot of time for implementation.

Data privacy is important, and there are many layers of security provided by Pinecone.

Pinecone needs to be upgraded because many companies are not using Pinecone for production. I don't know why, but it is very useful for us because my team and I use Pinecone in many POCs. This is very useful for us, but on the production server, the client is not allowing us to use it.

Pinecone should be made ready for production servers. Many companies are not using Pinecone in production. I don't know the reason. We need to work on understanding why companies are not adopting it for production servers.

It would be better to provide better documentation on how to use it, and also provide some videos, because most of the time we are using videos for implementation and use. The documentation is also helpful, but videos are a good option for us.

I have used Pinecone for the last five years, when I started my career in generative AI.

Pinecone is good for POCs and small projects because it's very easy to implement and very easy to use. This is very good for us. I would rate this product a 10 out of 10.

The main use case for Pinecone is to build RAG applications, but I have also built an image search engine on Pinecone by storing image embeddings and searching those image embeddings on it.

The first important thing about Pinecone is that it's a managed vector database, so there is no DevOps involved; it handles scaling, backups, replicas, and other infrastructure concerns, which is really helpful to me.

The best outcome of using Pinecone is that we don't have to manage one more application or one more thing in the overall application architecture because the vector database is the heart of any AI agent. When it's on Pinecone, we are safe and we don't have to worry about it; we can just use it via API and that's done.

In terms of time saved with Pinecone, it's really a time-saving solution because we don't have to manage the infrastructure. It streamlines our workflow and helps us create a proof of concept much faster because it becomes very easy to interact with Pinecone. It's really helpful, time-saving, and a faster way to build AI applications.

Pinecone has capabilities way beyond RAG applications because it can be used for recommendation systems, image similarity, and audio similarity as well, so it would be best if they could market those capabilities as well.

If Pinecone could increase the free quota and not kill the free quota after seven days, that would be great.

I have been using Pinecone for three years and have been building RAG applications on top of it.

Pinecone is very stable.

Pinecone scales well.

I have not needed the customer support for Pinecone yet.

We were using a file-based vector database, but as I mentioned, it's not a good solution beyond a proof of concept. When scaling beyond proof of concept, it's not a viable solution, so we were forced to switch to a platform, and we found Pinecone very easy to use.

The pricing for Pinecone is fair, and setup is really easy. You just give an index name and a couple of other things such as the dimension you want to have, and then you are good to go with no hassle.

As I mentioned earlier, time is saved with Pinecone. Money-wise, I'm not certain, but on the employee side, fewer employees are needed. DevOps is relieved because they don't have to manage a vector database and security and all the things related to the vector database.

We evaluated Quadrant, but the managed version of Quadrant is not as robust as Pinecone, so we moved to Pinecone.

If I want to use any file-based vector database, it becomes really not possible to use because it cannot scale. You cannot connect or create multiple replicas on top of a single file-based vector database. In the context of managed instances, Pinecone comes to us very easily and it becomes very easy to scale workers on top of Pinecone.

Pinecone is a great platform; it's easy to use with clean SDKs, so it becomes always a go-to option when I think of a vector database.

One piece of advice I would like to give about Pinecone is to make sure you first clearly discuss what embedding size you want because it's not possible to change the embedding size after setup.

I would rate this review a ten out of ten.

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.

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