Topic outline

• Setting Up Your Generative AI Development Environment

  Setting Up Your Generative AI Development Environment

  Content Type
  Video

  Duration
  10m

  Level
  Introductory

  See how to set up your development environment to start creating a RAG application. Learn what to consider when choosing an IDE, which Python libraries will be useful in development, and how to instantiate a basic interaction with a large language model.
• Code Used in This Video

  Code Used in This Video

  All of the code used for the application shown in this video is also available on GitHub.

  Reference	Timestamp	Code
  Initialize a Python virtual environment	4:40	python -m venv .venv
  Access the Python virtual environment	5:00	.\.venv\Scripts\activate.ps1
  Install require packages in the Python virtual environment	5:18	pip install -r .\requirements.txt
  Import specific packages for interfacing with the large language model	7:30	Begin code: from langchain_community.chat_models import ChatOpenAI from langchain.chains import LLMChain, ConversationChain from langchain.chains.conversation.memory import ConversationSummaryMemory from langchain.callbacks import get_openai_callback End code.
  Instantiate connection object to LLM endpoint	8:55	Begin code: import keys llm = ChatOpenAI( temperature=0, open_api_key=keys.openai_key, model_name='gpt-3.5-turbo' ) End code.
  Define chain for storing conversation history	9:27	Begin code: conversation_sum = ConversationChain( llm=llm, memory=ConversationSummaryMemory(llm=llm) ) print(conversation_sum.memory.prompt.template) End code.
  Submit a prompt to the LLM	10:25	Begin code: prompt = "Tell me something about the weather in 2018."End code.
• What's Next?

  What's Next?

  • Explore a RAG application created using the setup described in this video (video, 20m).
  • Learn how to develop your generative AI applications (learning path, 2h).