johnsonhk88/AI-Bank-Statement-Document-Automation-By-LLM-And-Personal-Finanical-Analysis-Prediction

AI Bank Statement Document Automation By LLM model and Personal Finanical Analysis

62
/ 100
Established

Combines YOLOv8 layout detection, OCR, and LLM-powered table extraction to convert unstructured bank statement PDFs into queryable structured data. The architecture leverages LangChain with Chroma/FAISS vector stores for RAG pipelines and AG2 autonomous agents for financial analysis, supporting both cloud LLMs (Google Gemini) and local inference (Ollama). Exposes capabilities via Streamlit web UI with built-in financial intelligence (income/expense categorization, trend analysis, monthly/yearly reports) and DeepEval integration for RAG quality evaluation.

561 stars. Actively maintained with 1 commit in the last 30 days.

No Package No Dependents
Maintenance 13 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

561

Forks

106

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Feb 25, 2026

Commits (30d)

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/johnsonhk88/AI-Bank-Statement-Document-Automation-By-LLM-And-Personal-Finanical-Analysis-Prediction"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.