How shashi108/datascience works
This repository is a portfolio of AI and data-learning examples, not one unified product. Two implemented application workflows are visible in the sampled source: a FastAPI Gemini app that screens prompts and responses, and several LangGraph chatbot variants with memory, SQLite persistence, or tools. The README also advertises PDF/RAG and agentic-AI projects; the tree shows notebooks and examples for these, but their runtime connections were not sampled, so those capabilities are represented as separate documented branches. Edges reflect shown calls or README statements only.
Main entry points: app.py Prompt API · backend_sqlite.py SQLite Chat Graph · backend_tools.py Search, Finance, Calculator Tools · backend.py Basic Chat Graph
Components 20
Guardrails App
- Prompt API
GenAI/LLM_Guardrials/app.py - Input Screening
GenAI/LLM_Guardrials/guardrails.py - Gemini Service
GenAI/LLM_Guardrials/gemini_service.py - Gemini Config
GenAI/LLM_Guardrials/config.py - Output Screening
GenAI/LLM_Guardrials/output_guardrails.py
LangGraph Chatbots
- Streamlit Chat UI
GenAI/Lang Graph/chatbot_LLM/ai_app.py - Threaded Chat UI
GenAI/Lang Graph/chatbot_LLM/4app_resume.py - SQLite Chat UI
GenAI/Lang Graph/chatbot_LLM/5app_sqlite.py - Basic Chat Graph
GenAI/Lang Graph/chatbot_LLM/backend.py - SQLite Chat Graph
GenAI/Lang Graph/chatbot_LLM/backend_sqlite.py - Tool Chat Graph
GenAI/Lang Graph/chatbot_LLM/backend_tools.py - SQLite Checkpoints
GenAI/Lang Graph/chatbot_LLM/backend_sqlite.py - Search, Finance, Calculator Tools
GenAI/Lang Graph/chatbot_LLM/backend_tools.py
AI Portfolio Capabilities
- PDF RAG Chatbot
GenAI/casestudy/2.Q&A from PDF document/PDF Q&A.ipynb - FAISS Index
GenAI/casestudy/2.Q&A from PDF document/pdf_faiss_index - Agentic AI Examples
GenAI/Lang Graph/chatbot_LLM
Other components
- User
- Local Ollama Model
- DuckDuckGo Search
- Alpha Vantage
Connections 19
- User → Prompt API: submits prompt
GenAI/LLM_Guardrials/app.py - Prompt API → Input Screening: checks input
GenAI/LLM_Guardrials/app.py - Prompt API → Gemini Service: generates response
GenAI/LLM_Guardrials/app.py - Gemini Service → Gemini Config: loads settings
GenAI/LLM_Guardrials/gemini_service.py - Prompt API → Output Screening: checks output
GenAI/LLM_Guardrials/app.py - User → Streamlit Chat UI: sends message
GenAI/Lang Graph/chatbot_LLM/ai_app.py - Streamlit Chat UI → Basic Chat Graph: invokes graph
GenAI/Lang Graph/chatbot_LLM/ai_app.py - Threaded Chat UI → Basic Chat Graph: streams chat
GenAI/Lang Graph/chatbot_LLM/4app_resume.py - SQLite Chat UI → SQLite Chat Graph: streams chat
GenAI/Lang Graph/chatbot_LLM/5app_sqlite.py - Basic Chat Graph → Local Ollama Model: invokes model
GenAI/Lang Graph/chatbot_LLM/backend.py - SQLite Chat Graph → Local Ollama Model: invokes model
GenAI/Lang Graph/chatbot_LLM/backend_sqlite.py - SQLite Chat Graph → SQLite Checkpoints: persists checkpoints
GenAI/Lang Graph/chatbot_LLM/backend_sqlite.py - Tool Chat Graph → Local Ollama Model: invokes model
GenAI/Lang Graph/chatbot_LLM/backend_tools.py - Tool Chat Graph → Search, Finance, Calculator Tools: routes tool calls
GenAI/Lang Graph/chatbot_LLM/backend_tools.py - Search, Finance, Calculator Tools → DuckDuckGo Search: searches web
GenAI/Lang Graph/chatbot_LLM/backend_tools.py - Search, Finance, Calculator Tools → Alpha Vantage: fetches quotes
GenAI/Lang Graph/chatbot_LLM/backend_tools.py - PDF RAG Chatbot → FAISS Index: uses vector search
README.md - User → PDF RAG Chatbot: asks PDF questions
README.md - User → Agentic AI Examples: explores workflows
README.md