SentenceTransformer
PulseAugur coverage of SentenceTransformer — every cluster mentioning SentenceTransformer across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
Build a RAG System From Scratch in Python: A Technical Deep Dive
This article provides a technical deep-dive into building a Retrieval-Augmented Generation (RAG) system from scratch using Python. It breaks down the RAG pipeline into offline and online phases, emphasizing the critical…
-
BGE embedding models require specific local setup for optimal performance
The BGE embedding model family, developed by the Beijing Academy of Artificial Intelligence, offers several versions with varying dimensions and sequence lengths. For optimal performance, embeddings should be normalized…
-
Retrieve-then-rerank boosts RAG accuracy with dual-encoder approach
A technique called retrieve-then-rerank can significantly improve the accuracy of retrieval-augmented generation (RAG) systems by using a two-stage process. The first stage employs a fast bi-encoder to retrieve a broad …
-
Build a semantic cache for LLM apps to cut costs
A technical guide demonstrates how to build a semantic cache for LLM applications using Python, aiming to reduce API call costs. The approach involves converting user queries into vector embeddings using SentenceTransfo…
-
Guide to Building Production-Ready Embedding Services with Transformers
This article details the process of creating a production-ready embedding service, focusing on the transition from SentenceTransformer models to more advanced Native Transformers. It guides readers through the technical…
-
Fixing local LLM knowledge bases requires better retrieval, not new models
Setting up a local LLM knowledge base often yields poor results due to issues in the retrieval pipeline, not the model itself. Common problems include inadequate chunking that splits sentences or groups unrelated conten…
-
RAG Systems Explained: Enhancing LLMs with External Knowledge
Retrieval-Augmented Generation (RAG) is a technique that enhances Large Language Models (LLMs) by allowing them to access and utilize external knowledge bases before generating a response. This approach addresses LLM li…
-
Researchers develop graph construction for imperative programs using neural methods
Researchers have developed a pipeline to convert imperative programs and their annotations into typed, attributed graphs. This process combines abstract syntax tree parsing with semantic embeddings from models like Sent…