AI Projects

Completed:

LLM LangChain projects (Generative AI):

• LLMs - AutoPureData: Automated Filtering of Web Data for LLM Fine-tuning
  • Research project. Used Llama 3 to automate the process of filtering web data for LLM fine-tuning
• LLMs - Chat with a Wikipedia page
  • Used LangChain, RAG, and ChainLit (to host web page)
• LLMs - Feedback summarizer
  • Used LangChain, Selenium, and Gradio (for hosting)
• LLMs - Chat with an image
  • Used LangChain, and StreamLit (for hosting)
• LLMs - Prompt shortener
  • Used LangChain and Gradio (for hosting)

• LLMs - Agents
  • Used LangChain Agents for various tasks like searching online, fetching weather, math operations, running python code, etc.
• LLMs - Chat with Data
  • Useful to chat with data to get useful insights to increase the profitability of the companies
  • Generated synthetic data using LLMs
• LLMs - Model Deployment
  • Used LMDeploy and FastAPI to deploy the model by emulating OpenAI API

For demo, please open the page: Demo

Note: Before you run these, please install Ollama and pull the model you prefer. Make sure to copy .env.example to .env and fill in the model name.

---

Data Science projects:

• NLP - Offensive Tweets Classification
• ML - Loan Default Risk Prediction

---

What is special from me:

• Structured code and folders
• Common functions to reuse - common_functions.py
• LLMs - Made the LLM calls faster and cheaper for the profitability of the companies
• Applying more concepts that are useful in the real-world projects