Jerry Liu sur X : "To better augment LLMs with context, it makes a lot of sense to organize context not just as a flat list of text chunks, but as a hierarchy of high-level to low-level details. RAPTOR..."
Tags:
Au sujet de ce document
Infos sur le fichier
Documents with similar tags (experimental)
Hrishi sur X : "RAPTOR is... one of the very few [RAG architectures] that actively presumes and uses the structure in a document...."
Tags:
2024-03-09 A propos
Jerry Liu sur X : "4 Levels of Agents for RAG..."
Tags:
2024-01-23 A propos
LlamaIndex: "Instead of using a global fixed chunk size for RAG, try splitting based on the semantics of the text"
Tags:
2024-01-13 A propos
Jerry Liu sur X : "Naive chunking strategies cause poor RAG performance...."
Tags:
2023-12-06 A propos
Jerry Liu sur X : "A simple trick to improve retrieval for RAG 💡: Embed “references” to each text chunk instead of the chunk itself (e.g. smaller chunks, summaries)..."
Tags:
2023-09-06 A propos
Jerry Liu sur X : "This might be the first time ChatGPT (+@jxnlco) helped us come up with a better retrieval algorithm for RAG..."
Tags:
2023-08-28 A propos
Jerry Liu sur Twitter : "Some critical data considerations that you must take into account to make your LLM application production-ready"
Tags:
2023-07-23 A propos