Terry ChoLLM application architectureIf you look at the form of development using an LLM model such as ChatGPT, you can see that it usually has the following structure.Jun 24Jun 24
Terry ChoHow langchain agent works internally (Trace by using LangSmith)This time, by explaining how to use create_react_agent, we will take a detailed look at how the agent operates internally, and also learn…Feb 5Feb 5
Terry ChoGoogle Search + ChatGPT by using Langchain Agent/ToolsThe LLM model basically provides answers based only on data saved at the time of learning. Using RAG, you can expand knowledge data by…Feb 2Feb 2
Terry ChoRAG with pinecone and ChatGPT — #3 Saving & Search Text in PineconeIn the last article, we learned about how to use Pinecone.Jan 1Jan 1
Terry ChoRAG with pinecone and ChatGPT — #2 Text Embedding & Embedding API comparisonEmbedding text using the OpenAI Embedding modelDec 20, 2023Dec 20, 2023
Terry Cho4. LLM(ChatGPT) cost controlUnlike simple API server development, LLM development calls an external LLM API service, and this API counts costs in token (word) units…Dec 20, 2023Dec 20, 2023
Terry ChoRAG with pinecone and ChatGPT — #1 What is RAG and Pinecone?The concept of RAGDec 14, 2023Dec 14, 2023
Terry Cho2.Major components of the LangchainLet’s take a look at what components Langchain consists of. As of December 2023, the Langchain library has had many updates, so the…Dec 14, 2023Dec 14, 2023