Retrieval-Augmented Generation (RAG)

Learn how to set up and use Crawl4AI's web scraping capabilities using Docker. This step-by-step tutorial shows you how to set up, configure, and deploy your first AI-powered web crawler in minutes. Free, open-source, and faster than many paid alternatives.

Searching for the right documents and chunks is the most important aspect of a RAG application. However, different chunking methods come with different drawbacks. Using long-context embedding models, we can use 'late chunking' to get the best chunking method for search quality so far.

Google BigQuery recently got support for vector embeddings. Learn how to use them and how to create embeddings of your texts without leaving BigQuery. No external systems required.

Learn how to use GPT-4o to parse data from even the most complex of documents - multi-column PDFs, excel documents, tables, and more.

GPT-4o has phenomenal vision capabilities. Learn how to use the OpenAI API to send images to GPT-4o and use it's vision capabilities to describe the images, label them or provide analytical outputs from them.

Explore how Vertex AI Model Garden simplifies AI model deployment. This guide demonstrates deployment of Llama 3.1 and Claude 3.5 Sonnet, showcasing the platform's approach to hosting advanced AI models.

Learn how to create your custom GPT-4o mini model using OpenAI's finetuning API - for free!

Learn to create knowledge graphs for RAG with Neo4j LLM Knowledge Graph Builder in this easy step-by-step guide. Increase the quality of your RAG model with this modern approach to data modelling.

Simplify complex BigQuery data analysis with a custom conversational interface. Learn how to use OpenAI's GPT-4o model to generate SQL queries and execute them against your BigQuery database.

The more we work with AI, the more we need to extract data from documents. In a scalable manner. While conventional and machine learning based methods provide good results for most cases, especially when the data is rather technical and provides complicated layouts like multicolumn pdfs or tables, these methods often fail. Let's test whether LLMs can help us here.

In this guide, we'll explore how to build an AI chatbot that interfaces with Confluence data, using Airbyte and Langchain for data integration and PGVector for storing our text embeddings. This practical walkthrough aims to provide clear, step-by-step instructions to enable you to set up and deploy your own LLM-powered chatbot

HyDE is a technique used to improve the performance of RAG models by generating hypothetical document embeddings based on the query and using them to retrieve relevant documents from the knowledge base.

OpenAI has released its new embedding models, which have been trained using the new MRL technique. Discover how this not only enhances the accuracy of semantic searches but also can improve the performance of vector databases

Explore the architecture and advantages of Retrieval Augmented Generators (RAG), the innovative technology powering PondhouseAI

Finding the right documents during retrieval is probably the most important aspect of your RAG pipeline. This guide demonstrates how to use 'reranking' for

With recursive retrieval, RAG can generate more coherent and contextually relevant responses. This guide introduces you to the concept of recursive retrieval and how to implement it with llamaindex.

Running your own LLM provides a lot of flexibility and control over your data. This guide introduces you to the seamless integration of vLLM and Caddy web server, enabling HTTPS encryption for a robust, private AI environment.

RAG pipelines are one of the corner-stones of modern AI applications. Evaluating there performance is detrimental for making them robust and production ready.

Strategies for enhancing AI with corporate data