Most LLM applications have a conversational interface. An essential component of a conversation is being able to refer to information introduced earlier in the conversation. At bare minimum, a conversational system should be able to access some window of past messages directly. We call this ability to store information about past interactions "memory". LangChain provides a lot of utilities for adding memory to a system. These utilities can be used by themselves or incorporated seamlessly into a chain.
In this video we get started with creating memory buffer and using it to take update the PromptTemplate with past messages and finally generate a formatted response.
Subscribe for more videos about Langchain.
Happy learning !!
0:00 Introduction
0:20 Memory demo in ChatGPT
2:41 How Memory works in Langchain
4:13 Implement memory with Langchain
12:56 Conclusion
13:14 Like Share and Subscribe
Langchain playlist - • Langchain and Large language models
Langchain Memory link - https://python.langchain.com/docs/mod...