Published onSeptember 9, 2024[Note] Understand how does Dify handle token cost and latency of LLM APIUnderstand how does Dify handle token cost and latency of LLM APITILAIMLLLMCost
Published onJune 14, 2023[Review] - OpenAI - Function calling and other API updatesreview - OpenAI announcing updates including more steerable API models, function calling capabilities, longer context, and lower prices.thinkreviewopenaiChatGPTMLAILLM
Published onMay 22, 2023[Review] Quivr - Chat with your brainQuivr is a promising project that combines the power of generative AI with the convenience of cloud storagereviewChatGPTChatbotLLMAIML
Published onMarch 31, 2023Chat with Your Product Manual: Simplify Your Life with LangChain and ChatGPT?How to use ChatGPT to help you easier to use an extreme long product manualMLAIChatGPTLangChainPromptprogramming
Published onFebruary 24, 2023Improving Your ChatGPT Experience: Simple Trick Of Effective InstructionsThe blog introduces the "Fukatsu-style universal prompt," a method that can improve the accuracy of responses from ChatGPT. It is a must-read for anyone who wants to enhance their use of ChatGPT and obtain more accurate and reliable answers.thinkTILChatGPTAIML
![[Note] Understand how does Dify handle token cost and latency of LLM API](/_next/image?url=https%3A%2F%2Fres.cloudinary.com%2Fdmn6epfdy%2Fimage%2Fupload%2Fv1726112740%2Fttf-blog%2F3bc981d6-4f43-42e8-a95a-9587ee11820a%2F_note_understand_how_does_dify_handle_token_cost_and_latency_of_llm_api.png&w=256&q=75)