canopy VS Neo4j

To create a PineCone account, sign up via this link: https://www.pinecone.io/

So you might have seen in my last blog post that I showed you how to accelerate video frame extraction using GPU's and Babit multimedia framework. In this blog we are going to improve upon our video frame extractor and create a video similarity search(Reverse video search) utlizing different RAG(Retrival Augemented Gerneation) concepts with Pinecone, the vector database that will help us build knowledgeable AI. Pinecone is designed to perform vector searches effectively. You'll see throughout this blog how we extrapulate vectors from videos to make our search work like a charm. With Pinecone, you can quickly find items in a dataset that are most similar to a query vector, making it handy for tasks like recommendation engines, similar item search, or even detecting duplicate content. It's particularly well-suited for machine learning applications where you deal with high-dimensional data and need fast, accurate similarity search capabilities. Reverse video search works like reverse image search but uses a video to find other videos that are alike. Essentially, you use a video to look for matching ones. While handling videos is generally more complex and the accuracy might not be as good as with other models, the use of AI for video tasks is growing. Reverse video search is really good at finding videos that are connected and can make other video applications better. So why would you want to create a video similarity search app?

Pinecone: A scalable vector database service that facilitates efficient similarity search in high-dimensional spaces. Ideal for building real-time applications in AI, such as personalized recommendation engines and content-based retrieval systems.

In this post we’ll build a Python script that uses StripeDocs Reader, a loader on LlamaIndex, that creates vector embeddings of Stripe's documentation in Pinecone. This allows a user to ask questions about Stripe Docs to an LLM, in this case OpenAI, and receive a generated response.

Pinecone is a managed vector database service that simplifies the process of building and scaling vector search applications. It offers a simple API for embedding vector search into applications, providing accurate, scalable similarity search with minimal setup and maintenance.

In case of AIMD, I am doing this all in-memory, but you could also do this in a database (e.g. Pinecone). It all depends on how much data you have and how much compute you have available.

A RAG implementation's quality and performance highly depend on the similarity-based search of embeddings. The challenge arises from the fact that embeddings are usually high-dimensional vectors, and the knowledge base may have many documents. It's not surprising that the popularity of LLM catalyzed the development of specialized vector databases like Pinecone and Weaviate. However, SQL databases are also evolving to meet the new challenge.

Neo4j

Neo4j: An ACID-compliant graph database with a high-performance distributed architecture. Ideal for complex relationship and pattern analysis in domains like social networks.

After spending millions fighting the committer of ONgDB who removed the commons clause from the AGPL branded license, it looks like the Free Software Foundation got involved and forced them to remove the commons clause or change the license to their own proprietary license.

https://github.com/neo4j/neo4j/commit/b6237ca4e31706b1efbd0f...

The GenAI Stack came about through a collaboration between Docker, Neo4j, LangChain, and Ollama. The goal of the collaboration was to create a pre-built GenAI stack of best-in-class technologies that are well integrated, come with sample applications, and make it easy for developers to get up and running. The goal of the collaboration was to create a pre-built GenAI stack of best-in-class technologies that are well integrated, come with sample applications, and make it easy for developers to get up and running.

Neo4j (GraphQL)

NoSQL is a term that we have become very familiar with in recent times and it is used to describe a set of databases that don't make use of SQL when writing & composing queries. There are loads of different types of NoSQL databases ranging from key-value databases like the Reddis to document-oriented databases like MongoDB and Firestore to graph databases like Neo4J to multi-paradigm databases like FaunaDB and Cassandra.

this thread on this github issue could be useful.

Recently I have taken an interest in big data. https://neo4j.com/ , https://cassandra.apache.org/ , https://clickhouse.com/, https://www.elastic.co/ - are all databases I have experience with. Neo4j and Cassandra only as a hobby, but Clickhouse I have used in production, and Elasticsearch I have used for some 7 years now.

For organizations and their applications that are designed to detect fraud, like International Consortium of Investigative Journalists, or try to improve customer experience via personalization, as in the case of Tourism Media, a NoSQL graph database like Neo4j is a good match. In these kinds of use cases, the quantity of data we're dealing with is enormous, and the pattern we're searching for in the data is often complex.

First, you need to choose a specific graph database platform to work with, such as Neo4j, OrientDB, JanusGraph, Arangodb or Amazon Neptune. Once you have selected a platform, you can then start working with graph data using the platform's query language.