Repository used for the DOPRO project dealing with food AI.
This repository contains:
a full Taiga export plus all other documents that are part of your project planning, including any project presentation materials.
the full final product, including all files, documentation and presentation materials.

lanfr144 f879623616 TG-193: Add scratch directory to gitignore 1 dienu atpakaļ
.agents acc51aa882 TG-439: Deploy Local SearXNG Web Search Tool 4 dienas atpakaļ
alembic 0fd29e16de Reduce partition chunk size to 4 to bypass persistent row size error; include initial alembic migration 3 nedēļas atpakaļ
docker bd75beb4c3 TG-193: Security: Remove hardcoded passwords and resolve DB login issues 1 dienu atpakaļ
docs b0b36ee1ac TG-439: Finalize Capstone Documentation, DR Plan, and VM Arch 4 dienas atpakaļ
k8s bd75beb4c3 TG-193: Security: Remove hardcoded passwords and resolve DB login issues 1 dienu atpakaļ
nginx 50d8206bd3 TG-85: finalize missing Nginx proxy and bookmarks scripts 1 nedēļu atpakaļ
searxng acc51aa882 TG-439: Deploy Local SearXNG Web Search Tool 4 dienas atpakaļ
.dockerignore 05df9bef41 fix: remove GPU reservation, change MySQL port to avoid collision, add dockerignore 1 nedēļu atpakaļ
.gitattributes 0cfdf52814 TG-85: enable export-subst for Format string git identification 1 nedēļu atpakaļ
.gitignore f879623616 TG-193: Add scratch directory to gitignore 1 dienu atpakaļ
Final_Presentation.html 1558f08eca Execute Implementation Plan 2 3 nedēļas atpakaļ
PROJECT_CONTEXT.md e3f96b1f33 Sprint 7: Zabbix and SNMPv3 Monitoring Integration 2 nedēļas atpakaļ
Project.pdf acc51aa882 TG-439: Deploy Local SearXNG Web Search Tool 4 dienas atpakaļ
README.md b0b36ee1ac TG-439: Finalize Capstone Documentation, DR Plan, and VM Arch 4 dienas atpakaļ
Retro Planning.pdf acc51aa882 TG-439: Deploy Local SearXNG Web Search Tool 4 dienas atpakaļ
alembic.ini 73f7a04cd0 Optimize horizontal partitioning to slice into 8-column chunks bypassing InnoDB limits 3 nedēļas atpakaļ
app.py acc51aa882 TG-439: Deploy Local SearXNG Web Search Tool 4 dienas atpakaļ
backup_db.sh 0cfdf52814 TG-85: enable export-subst for Format string git identification 1 nedēļu atpakaļ
check_users.py 7766898050 Add check users script 2 nedēļas atpakaļ
data_sync.sh 214521fd62 TG-85: rewrite data_sync to auto-detach securely with nohup 1 nedēļu atpakaļ
deploy.sh a54dc25344 TG-21: Update deploy.sh to include requests connectivity dependency. 3 nedēļas atpakaļ
docker-compose.yml bd75beb4c3 TG-193: Security: Remove hardcoded passwords and resolve DB login issues 1 dienu atpakaļ
download_csv.sh 1a3cdcaf36 fix: resolve pip encoding issue and add exec permissions to download script 1 nedēļu atpakaļ
generate_docs.py 44fb10980d TG-85: finalize Scrum Sprint 10 with docs mirror and Git keyword expansion 1 nedēļu atpakaļ
ingest_csv.py 84cb5bdc6b TG-85: pre-emptive DB cleaning via Upsert, Cascaded UI Plate Builder, scaled units 1 nedēļu atpakaļ
init.sql 6cb128ca1c TG-86: EMERGENCY FIX schema exact columns and docker compose crash 1 nedēļu atpakaļ
master_trigger.sh 38a83a1bf0 Deployment Finalization: Vitamin schemas, Green UI, and Taiga tools 3 nedēļas atpakaļ
my.cnf 86c76e282d TG-1: Fix MySQL 8.0 startup crash by removing premature validate_password plugin config 4 nedēļas atpakaļ
myloginpath.py 4655c26f1f Add untracked project files and configs 2 nedēļas atpakaļ
proper_reset.sh 776d6a6153 Add proper reset 2 nedēļas atpakaļ
requirements.txt bb2ac28c2e fix requirements.txt encoding for fpdf2 5 dienas atpakaļ
rotate_passwords.py bd75beb4c3 TG-193: Security: Remove hardcoded passwords and resolve DB login issues 1 dienu atpakaļ
snmp_notifier.py 1b9e8b1fab fix: auto-create target tables and sanitize snmp notifications 1 nedēļu atpakaļ
start_batch_ingest.sh 00f1d63625 Fix python virtual env paths 3 nedēļas atpakaļ
unit_converter.py ea04a85037 TG-86: finalize system pre-initialization, auto-pull LLM, egg scales 1 nedēļu atpakaļ
zabbix_telemetry.py 7ca6cd88d5 TG-86: decouple telemetry script from streamlit app 1 nedēļu atpakaļ

README.md

Local Food AI 🍔

A strictly local, privacy-first AI Medical Dietitian and Food Explorer. This project leverages the OpenFoodFacts dataset and local LLMs (Ollama) to provide medically sound dietary advice, recipe parsing, and menu planning without sending any user data to the cloud.

Features

  • Dynamic Medical Profiling: Configure your health profile (e.g., Kidney issues, pregnancy, vegan). The AI dynamically adjusts all responses, recommendations, and warnings based on these exact medical needs.
  • RAG Architecture: The AI is connected to a massively partitioned local MySQL database. When you ask a question or request a meal plan, the AI executes SQL queries autonomously to fetch precise nutritional data.
  • SearXNG Web Integration: When the local Database lacks culinary heuristics, the AI securely queries a local, private instance of SearXNG to answer questions without compromising patient privacy.
  • Plate Builder & Unit Conversion: Input culinary recipes (e.g., "1.5 cups of flour") and the system converts them to metric standard weights based on the product's density.
  • Distributed Microservice Topology: Supports decoupling across VirtualBox, Hyper-V, and WSL2 using Bridged Networking and SNMP container telemetry for Zabbix.

Documentation (Capstone Deliverables)

Please refer to the docs/ folder for detailed guides:

Tech Stack

  • Frontend: Streamlit
  • Database: MySQL 8.0
  • AI Engine: Ollama (Llama 3.2:1B)
  • Web Search: SearXNG
  • Monitoring: Zabbix (SNMPv2c)
  • Deployment: Native Ubuntu, Docker Compose, Hyper-V / VirtualBox
  • Project Management: Taiga (Synced dynamically via Python)