Inspiration
What it does
Using Python to be able to do do statstical analysis, scripting and data processing, PDF parsing, image processing, OCR engine using tesseract, paddleOCR, EasyOCR, RAG pipeline, and computer vision with Python.
How I built it
Tools I will be using: Python for scripting and data processing PyMuPDF, pdfplumber for PDF parsing OpenCV, PIL for image preprocessing OCR Engines: Tesseract, PaddleOCR, EasyOCR LlamaIndex, FAISS or Chroma for vector-based retrieval Gemini API and open-source LLMs (Mistral, Phi-2) Streamlit or Gradio for optional user interface Google Colab for experimentation and collaboration
Project that I'll be building: Scanned Document Images Preprocessor (Project 2) Document Parser (Project 3) Retrieval-Augmented Generation (RAG) Pipeline (Project 5) split_and_route() Pipeline (Project 7) Working UI/Command-line Search Layer (Project 8) Final Report & Reflection Document
Challenges I ran into
Accomplishments that I'm proud of
What I learned
Project that I'll be building: Scanned Document Images Preprocessor (Project 2) Document Parser (Project 3) Retrieval-Augmented Generation (RAG) Pipeline (Project 5) split_and_route() Pipeline (Project 7) Working UI/Command-line Search Layer (Project 8) Final Report & Reflection Document
What's next for Outamation_Externship_internship
Looking to utilize my skills and experience gained from this internship to land a relevant job within my field and not something else or psychology.
Built With
- colab
- python
Log in or sign up for Devpost to join the conversation.