Natural Language Processing (NLP) and Large Language Models (LLM) with LangChain / ReAct and Building Multi-stage Reasoning Systems
In this notebook we're going to create AI systems:
DataScienceAI
will take the form of an LLM-based agent that will be tasked with performing data science tasks on data that will be stored in a vector database using ChromaDB. We will use LangChain agents as well as the ChromaDB library, as well as the Pandas Dataframe Agent and python REPL (Read-Eval-Print Loop) tool.
By the end of this notebook, you will be able to:
- Build prompt template and create new prompts with different inputs
- Create basic LLM chains to connect prompts and LLMs.
- Construct sequential chains of multiple
LLMChains
to perform multi-stage reasoning analysis. - Use langchain agents to build semi-automated systems with an LM-centric agent to perform internet searches and dataset analysis.