notes
notes copied to clipboard
vinhnx
my today I learn (TIL) journal, includes everything that I found interesting, not necessarily relates to programming
https://lifeinthesingularity.com/p/googles-breakthroughs-in-ai-design
https://news.ycombinator.com/item?id=39959790
https://shelbyjenkins.github.io/blog/retrieval-is-all-you-need-2/
⭐ https://docs.cohere.com/docs/llmu https://docs.cohere.com/docs/integrations https://docs.cohere.com/reference/about https://docs.cohere.com/docs/the-cohere-platform https://cohere.com/use-cases/investment-research-assistant?ref=txt.cohere.com https://txt.cohere.com/using-llms-for-search/ https://txt.cohere.com/text-embeddings/ https://cohere.com/embed?ref=txt.cohere.com https://cohere.com/rerank?ref=txt.cohere.com https://docs.cohere.com/page/document-question-answering https://txt.cohere.com/rag-start/ https://docs.cohere.com/reference/chat https://github.com/cohere-ai/notebooks/blob/main/notebooks/Vanilla_RAG.ipynb https://docs.cohere.com/docs/module-8-chat-and-retrieval-augmented-generation-rag https://cohere.com https://txt.cohere.com/command-r/
https://txt.cohere.com/say-hello-to-precision-how-rerankers-and-embeddings-boost-search/
lots of cool gems for RAG here https://huggingface.co/learn/cookbook/index
> [LlamaIndex](https://docs.llamaindex.ai/en/stable/index.html), a data framework for LLM-based applications that’s, unlike [LangChain](https://python.langchain.com/docs/get_started/introduction), designed specifically for RAG; https://huggingface.co/learn/cookbook/rag_llamaindex_librarian