Working with Memory and Dialogue History in LLM 🧠

Another tech support chatbot is being rolled out, the user is ranting about their problem, and by the third message the neural network asks: "What's your name and how can I help you?"

The reason is trivial: LLMs are stateless by nature. The model's "memory" is just an architectural crutch, and the problem is usually solved "head-on": take LangChain, collect all previous messages, and throw them into the prompt.

🗓 Today at 18:00 Moscow time in "Assembly Point" we will analyze the memory architecture for LLM assistants and methods for adequate context management.

Required background to understand the material:
🔵Basic Python syntax (classes, dictionaries, functions).
🔵Understanding how HTTP API works and the basic concept of LLM (what a prompt and token are).
🔵 Superficial familiarity with LangChain abstractions.

Access via bot: t.me/TScompiler_bot