Building LLM powered applications using langchain
Sasidhar Donaparthi (~sasidhar) |
Description:
Creation of [Large Language Models (LLMs) is on the rise. This workshop is aimed at building LLM powered application using open source langchain package. I will cover how to use various components and also building an application using these components. These components are abstractions working with language models. Various topics covered in this workshop are
- Document Loaders and Transformers
- Embedding Generation and storing them in Vector Database
- Prompt Templates
- LLMs and LLM Chain
Building an applications of "Question & Answer" for a given set of documents using the above components.
Prerequisites:
Following are the pre-requisites
- Basic knowledge of Python
- Basic understanding of Large Language Models
- Familiarity with HuggingFace Hub
- Familiarity with one of the IDEs like VS Code/Jupyter lab
Content URLs:
It is in progress - will be provided much before the event
Speaker Info:
I am a mechanical engineering graduate with 25+ years of experience in manufacturing and financial services domains, I have started my career as design engineer in hydraulic turbine manufacturing company. After spending 5 years, I have stated my IT journey at Aspect Development/i2 Technology. I have worked primarily on data scrubbing, modelling, analysis and data migration projects for supply chain management. I then joined technology services side of Fidelity, financial services company. I have been using python for last 6+ years for automation, data analysis, web development, etc. I am very excited about the endless opportunities that arise in day today work and application of python for solving problems, automating day to day activities. I am very passionate about teaching python to engineering students thru pythonexpress program. I conduct regular training sessions for data analys ( numpy, pandas and matplotlib) in my company.
I am a regular speaker at Pycon India conference. I have done various talks and workshops in Pycon 2017, 2018, 2022.
Speaker Links:
github link - https://github.com/sdonapar
linkedin profile - https://www.linkedin.com/in/sasidonaparthi
twitter handle - @sdonapar