Generative AI with Google Cloud: Operationalizing PaLM 2 with LangChain

Generative AI has unleashed a new breed of digital assistants, content creation tools, and applications - changing how apps are built, who can build them, and the capabilities end users expect from them.

LangChain has emerged as a leading open source framework for building generative AI applications powered by Large Language Models (LLMs).  

With the integration of LangChain with Vertex AI PaLM 2 foundation models, you can now create generative AI applications by combining the power of PaLM 2 - Google Cloud’s next-generation language model with improved multilingual, reasoning, and coding capabilities - with the ease of use and flexibility of LangChain. 

Tune into this session with the experts, as we cover how you can achieve better scale and automation while building generative AI applications using the LangChain-PaLM 2 integration.

03:04 Introduction to Google Cloud's AI & ML portfolio
11:13 Typical usage of LLMs
13:13 Common patterns using LLMs
15:29 Introduction to LangChain
20:49 Where does LangChain fit in the LLM stack?
22:59 LangChain concepts: Chains, Agents, Memory, Models, Prompts, and Indexes
26:57 Why use Agents?
28:10 Implementing Agents
28:45 Embeddings
30:33 Demos and developer steps
30:48 1) Simple generative app
38:24 2) Memory-enabled chat app
49:11 3) Retrieval augmented generation
59:06 Q&A

Join, learn, and engage with the Google Cloud Community: https://goo.gle/cloud_community