Explaining LLMs for RAG and Summarization
· 9 min read
Learn how to explain LLM outputs in RAG and summarization tasks using a simple similarity-based attribution method.
2 posts tagged with "LLM"
Reranking using Huggingface Transformers for Optimizing Retrieval in RAG Pipelines
· 10 min read
Learn how to improve your RAG pipelines using reranking models from Huggingface Transformers.