Paper Reading
RoBERTa: An Optimized Method for Pretraining Self-supervised NLP Systems
RoBERTa (A Robustly Optimized BERT Pretraining Approach) is an improved version of BERT designed to address its limitations.
Community
GLiNER: Generalist Model for Named Entity Recognition Using Bidirectional Transformer
GLiNER is an open-source NER model using a bidirectional transformer encoder.
Engineering
Voyage AI Embeddings and Rerankers for Search and RAG
This article discussed the popular voyage AI embedding models and rerankers and their integration with Zilliz Cloud.
Community
Harnessing Embedding Models for AI-Powered Search
Building state-of-the-art embedding models for high-quality RAG systems needs careful attention to pretraining, fine-tuning, and scalability. Zilliz Cloud and Milvus help manage embeddings at scale and create more intelligent and responsive neural search systems.
Community
Safeguarding Data Integrity: On-Prem RAG Deployment with LLMware and Milvus
Using LLMware and the Milvus vector database, we can combine the power of vector similarity search and LLMs to ask questions on our private documents.
Engineering
Introduction to MemGPT and Its Integration with Milvus
Integrating the Milvus vector database and MemGPT has taken one step further in streamlining the development of AI Agents with connections to external data sources. In this post, we share an example demonstrating how to use this integration to build a chatbot with external memories.
Community
Enhancing Your RAG with Knowledge Graphs Using KnowHow
Knowledge Graphs (KGs) store and link data based on their relationships. KG-enhanced RAG can significantly improve retrieval capabilities and answer quality.
Community
ALIGN Explained: Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision
ALIGN model is designed to learn visual and language representations from noisy image-alt-text pairs.
Community
Improving Information Retrieval and RAG with Hypothetical Document Embeddings (HyDE)
HyDE (Hypothetical Document Embeddings) is a retrieval method that uses "fake" documents to improve the answers of LLM and RAG.