In this module, we will create an application using RAGs and AI Agents to extract information from various financial documents, including SEC 10Q and 10K files, for a selection of financial securities within a specified universe. This information will then be used to generate trading signals. 

Skills include: 

• Creating a vector database
• Prompt engineering
• Building a retriever
• RAG and AI Agents

In this module we will create end to end LLMOps pipelines using langsmith to do prompt management, monitoring traces, automatic evaluation of the applications using benchmark datasets and or LLM as a judge etc.

Skills include:

• Prompt management
• Evaluation of the RAG pipeline
• Deploying the app on streamlit

This module focuses on the elements of Responsible AI within the finance industry. Considering the highly regulated nature of this sector, we will identify the challenges involved in deploying LLM applications and discuss strategies to overcome these issues.

Skills include: 

• Hallucination
• Prompt injection
• PII detection
• Toxicity detection
• Bias detection
• Interpretation

We will learn open-source tools like langkit, guardrails to implement the above. 

In this module, we will learn how to deploy and host the app using streamlit and get user feedback over time.

Skills/tools include: 

• Streamlit
• Langsmith

• Intermediate Python programming skills
• Comfortable running Jupyter Notebooks using Anaconda/VS Code or Google Colab.
• Basic understanding of machine learning and natural language processing concepts
• Familiarity with financial concepts and terminology
• Experience with data analysis and manipulation
• Basic knowledge of API usage and web technologies
• Basic understanding of cloud computing platforms (e.g., AWS, GCP, or Azure)
• Familiarity with version control systems (e.g., Git)