GitHub - stanford-futuredata/ColBERT: Stanford ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22)

Sounds fancy. Why do we care? GAR involves taking the source documents and having an LLM enrich them, prior to indexing. For example, the LLM might... * Generate titles for documents that are missing them * Standardize author names/formats* Extract dates, URLs, citations and other elements that might be valuable to search as separate fields* Create... See more

Pipeline RobustQA Avg. score Avg. response time (secs) Azure Cognitive Search Retriever + GPT4 + Ada 72.36 >1.0s Canopy (Pinecone) 59.61 >1.0s Langchain + Pinecone + OpenAI 61.42 <0.8s Langchain + Pinecone + Cohere 69.02 <0.6s LlamaIndex + Weaviate Vector Store - Hybrid Search 75.89 <1.0s RAG Google Cloud VertexAI... See more

Text embeddings are a critical piece of many pipelines, from search, to RAG, to vector databases and more. Most embedding models are BERT/Transformer-based and typically have short context lengths (e.g., 512). That’s only about two pages of text, but documents can be very long – books, legal cases, TV screenplays, code repositories, etc can be tens... See more

🥤 Cola [NeurIPS 2023]

Large Language Models are Visual Reasoning Coordinators

Liangyu Chen*,†,♥ Bo Li*,♥ Sheng Shen♣ Jingkang Yang♥

Chunyuan Li♠ Kurt Keutzer♣ Trevor Darrell♣ Ziwei Liu✉,♥

♥S-Lab, Nanyang Technological University

♣University of California, Berkeley ♠Microsoft Research, Redmond

*Equal Contribution †Project Lead ✉Corresponding Author... See more