canopy VS tonic_validate

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.

In the dynamic world of web development, Python has emerged as a dominant force, especially in backend development – the primary focus of this blog post. Although it's worth mentioning that there are ongoing efforts to use Python for the frontend as well, like Reflex (previously known as Pynecone, they presumably had to change their name because of Pinecone vector database), which even garnered support from Y Combinator. Samuel Colvin (creator of Pydantic) is also working on FastUI (he literally just released the first version in December 2023).

I tried out Amazon Bedrock, and used Tonic Validate to do a head to head comparison of very simple RAG system's built using embedding and text models available in Amazon Bedrock. I compared Amazon Titan's embedding and text models to Cohere's embedding and text models in RAG systems that employ Amazon Bedrock Knowledge Bases as the vector db and retrieval components of the system.

The code for the comparison is in this jupyter notebook https://github.com/TonicAI/tonic_validate/blob/main/examples...

Let me know what you think, And your experiences building RAG with Amazon Bedrock!

Tonic's RAG evaluation platform is Tonic Validate, which has open source RAG metrics https://github.com/TonicAI/tonic_validate, and a web app for tracking and monitoring RAG performance https://www.tonic.ai/validate.

Hey HN, Joe and Ethan from Tonic.ai here again. Alongside last week’s announcement of Tonic Validate Metrics (https://news.ycombinator.com/item?id=38012126), we’ve also released an open-source SDK for logging the performance of Retrieval Augmented Generation (RAG) applications during development, Tonic Validate Logging. Tonic Validate Logging is used to log your RAG responses to the Tonic Validate App. When RAG responses are logged, metrics are calculated on the responses using Tonic Validate Metrics.

We were working on a RAG-powered app to enable companies to talk to their free-text data safely when we ran into trouble tracking the performance of our models’ responses. So we built these solutions to help us out: Tonic Validate Metrics for benchmarking, and Tonic Validate Logging + the Tonic Validate UI to track performance improvements to help us choose the best system possible. Tonic Validate provides a simple and convenient UI that you can get for free at https://validate.tonic.ai/.

Two key benefits of using the Tonic Validate tools are (1) automatic logging and metrics calculation with just a few lines of code and (2) a simple, convenient UI to help visualize your experiments, iterations, and benchmarking results for your RAG applications.

Our hope is that these packages will become a useful part of the technique layer behind the growing suite of LLM-powered applications and, more importantly, that the open-source packages evolve and thrive with your contributions.

We’re excited to hear what you all think in the comments!

Read our docs here: https://docs.tonic.ai/validate/

Get the open-source Tonic Validate Metrics package at: https://github.com/TonicAI/tvalmetrics

Get the open-source Tonic Validate Logging SDK at: https://github.com/TonicAI/tvallogging

Sign up for the Tonic Validate UI here: https://validate.tonic.ai/