⚡️ Zep Memory ⚡️ Memory is crucial for LLM applications. It’s also often a pain to set up. Use @danielchalef and co’s new memory store Zep for super easy long-term storage and retrieval of application history! Zep: https://t.co/dSUgXEqJNS In LangChain: https://t.co/usgT07cY8r View Tweet
🏃Step-back prompting A new prompting technique from Google Deepmind, can be used to improve RAG results 🦜🔗Now in LangChain! 💬“STEP-BACK PROMPTING is motivated by the observation that many tasks contain a lot of details, and are hard for LLMs to retrieve relevant facts to tackle the task” Algorithm: ❓Generate a step back question based on the users original question 🌲Do retrieval for both the original question and the step back question 📃Generate an answer based on both sets of retrieved documents Paper: https://t.co/vebW0DvRZr LangChain Implementation: https://t.co/LfuCp1cumF View Tweet
