Recent Posts
-
Build an Advanced RAG App: Query Rewriting
The new query now matches with the chunk of information I wanted to get my answer from, giving the LLM a better chance of answering a much better response for my question. Conclusion We have taken our first step out of basic RAG pipelines and into Advanced RAG. Query Rewriting i...
-
How to build a basic RAG app
Common problems and pitfalls As the title implies, this solution is a basic or naïve RAG implementation. It will empower your application to make the most out of the LLM it’s using and your data. But it won’t work for all cases. These are just some of the most common problems wi...
-
How to use LLMs: Summarize long documents
And that’s it! You now have a short summary of the most important points of a large document. But before you start processing your whole documentation, there are a few important notes you need to consider: This MapReduce method might not be less expensive than using an LLM with...
-
Understanding LLMs: Mixture of Experts
Another paper, named Switch Transformers, looked at techniques to reduce communication costs between devices and reduce training instabilities. To optimize parallelism, they proposed to use a single expert approach and reduce the capacity factor to almost all tokens being equall...
-
What to Expect for AI in 2024?
2023 was a great year for AI. Large Language Models were already in the spotlight for both users and businesses. ChatGPT had been just released in late 2022 and was taking the world by storm. Still, 2023 has brought more rapid change in the field than we could have imagined. Thi...
-
How to supercharge your LLM with Langchain Agents
Tools and toolkits Tools are functions that will perform actions on behalf of the LLM. An agent gets a list of tools for it to use and it will request to use one, several, or none. The Agent Executor will execute the required tools and feed the result back to the Agent. An examp...
-
Maximizing the Potential of LLMs: Using Vector Databases
What do vector databases do? A vector database stores and indexes vector embeddings. This is useful for fast retrieval of vectors and looking for similar vectors. Similarity search We can find similarity of vectors by calculating a vector's distance to all other vectors. The nea...
-
Maximizing the Potential of LLMs: A Guide to Prompt Engineering
Language models have rapidly improved in recent years, with large language models (LLMs) such as GPT-3 and GPT-4 taking center stage. These models have become popular due to their ability to perform a great variety of tasks with incredible skill. Also, as the number of parameter...
-
How to install (and keep) extensions in SageMaker Studio
Enhance the experience of your data scientists with SageMaker Studio extensions
-
How to disable the download button in SageMaker Studio
If you want to ensure that your data scientists' cloud environment is secure from data leaks, remove this feature from SageMaker