RAG

All the recommendation systems you see at Twitter, Facebook, TikTok, YouTube, etc. have a similar high-level architecture.

They have a layered architecture that looks something like the following

1. Retrieval - Narrow down the candidates of what to show a user to thousands of potential items


2. First Stage Ranking - Apply a low-level ranking system to

... See more

Pipeline RobustQA Avg. score Avg. response time (secs) Azure Cognitive Search Retriever + GPT4 + Ada 72.36 >1.0s Canopy (Pinecone) 59.61 >1.0s Langchain + Pinecone + OpenAI 61.42 <0.8s Langchain + Pinecone + Cohere 69.02 <0.6s LlamaIndex + Weaviate Vector Store - Hybrid Search 75.89 <1.0s RAG Google Cloud VertexAI-Search + Bison... See more

Balance Latency and Performance¶

Finally, make informed decisions about trade-offs between system latency and search performance based on your specific use case and user requirements.

• Understand the latency and performance requirements for your application


• Measure the impact of different configurations on latency and performance


• Make trade-offs based

... See more

Analyze user queries and feedback to identify topic clusters, capabilities, and areas of user dissatisfaction. This will help you prioritize improvements.

Why should we do this? Let me give you an example. I once worked with a company that provided a technical documentation search system. By clustering user queries, we identified two main issues:

1. Top

... See more

Ragas is a framework that helps you evaluate your Retrieval Augmented Generation (RAG) pipelines. RAG denotes a class of LLM applications that use external data to augment the LLM’s context. There are existing tools and frameworks that help you build these pipelines but evaluating it and quantifying your pipeline performance can be hard. This is... See more

1. Synthetic Data for Baseline Metrics¶

Synthetic data can be used to establish baseline precision and recall metrics for your reverse search. The simplest kind of synthetic data is to take existing text chunks, generate synthetic questions, and verify that when we query our synthetic questions, the sourced text chunk is retrieved correctly.

Benefi... See more

Unlike some other popular algorithms, DiskANN is designed to keep memory usage to a minimum. This makes it a great match for use cases where Turso already excels at.

#Multitenancy

Turso allows for an easy implementation of a database-per-tenant pattern, where databases can be cheaply created on-demand. Keeping memory consumption at bay is critical... See more

Introducing Wren Engine

The advent of Trend AI agents has revolutionized the landscape of business intelligence and data management. In the near future, multiple AI agents will be deployed to harness and interpret vast amounts of internal knowledge stored within databases and data warehouses. To facilitate this, a semantic engine is crucial. This... See more

Welcome to RAGatouille

Easily use and train state of the art retrieval methods in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

The main motivation of RAGatouille is simple: bridging the gap between state-of-the-art research and alchemical RAG pipeline practices. RAG is complex, and there are many moving parts. To... See more