#Day7/30 #30DaysofGenerativeAI
What is #LangChain and why is it important?
👉 👉 LangChain is a framework built around LLMs (Large language models)
👉 👉 “LLMs in isolation is often not enough to create a truly powerful app – the real power comes when you are able to combine them with other sources of computation or knowledge” – And #Langchain is the library aimed at assisting in the development of those types of applications
👉 👉 “Chains are an important feature of LangChain that allow users to combine multiple components together to create a single, coherent application”
💬 So as I chat with Startups in this space, there are to clear paths that emerge
1️⃣ You are the infra player with a verticalised path to apps or you are a model+app player customising for a particular use case/niche.
2️⃣ The incumbents train LLMs with publicly available data.
Training on customised, ‘private data’ allows the use cases to be more effective in niche areas.
And LangChain here provides a very effective way to do so.
Here is an use case
💫 “Conversational Memory for LLMs with Langchain”
If you are talking to a person, you expect them to have context to the last conversation you had.
LLMs by default are stateless (process on current input). Here is an application that works on including memory of previous interactions
If you work or are interested in the space of #generativeAI, I’d love to hear from you. Please DM with details.
More resources
https://www.pinecone.io/learn/langchain-conversational-memory/
https://medium.com/@avra42/getting-started-with-langchain-a-powerful-tool-for-working-with-large-language-models-286419ba0842
https://langchain.readthedocs.io/en/latest/index.html
****************************************************
#reviewswithranjani #Day7/30 #30DaysofGenerativeAI
#Technology | #Books | #BeingBetter
