Inicio Explorar Axuda
Iniciar sesión
lanfr
/
LocalFoodAI_lanfr144
1
0
Fork 0
Ficheiros Incidencias 0 Wiki

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.

Árbore: c812444386
Ramas Etiquetas
LocalFoodAI_lan...
lanfr144 c812444386 Sprint 6: Complete documentation and code cleanup hai 2 semanas
.agents 7d59646d57 TG-6: Finalize remaining files hai 1 mes
AI_History f851d49f92 TG-29 TG-31 TG-32 TG-33: Implement EAV Architecture, Dynamic Medical CRUD UI, DataFrame Alert Engine, and Email Resets. TG-30: Fix Windows utf8 Encoding in Ingestion Engine. hai 3 semanas
alembic 0fd29e16de Reduce partition chunk size to 4 to bypass persistent row size error; include initial alembic migration hai 3 semanas
docker 4655c26f1f Add untracked project files and configs hai 2 semanas
docs c812444386 Sprint 6: Complete documentation and code cleanup hai 2 semanas
k8s 4655c26f1f Add untracked project files and configs hai 2 semanas
legacy_scripts c812444386 Sprint 6: Complete documentation and code cleanup hai 2 semanas
taiga_wiki e78a25bf3c TG-2: Populate Sprint 2 accomplishments in Taiga Wiki hai 4 semanas
.gitignore 4655c26f1f Add untracked project files and configs hai 2 semanas
Final_Presentation.html 1558f08eca Execute Implementation Plan 2 hai 3 semanas
PROJECT_CONTEXT.md c812444386 Sprint 6: Complete documentation and code cleanup hai 2 semanas
README.md c812444386 Sprint 6: Complete documentation and code cleanup hai 2 semanas
alembic.ini 73f7a04cd0 Optimize horizontal partitioning to slice into 8-column chunks bypassing InnoDB limits hai 3 semanas
app.py f466e8416e Add dynamic AI health evaluation and fix local DB connection errors hai 2 semanas
deploy.sh a54dc25344 TG-21: Update deploy.sh to include requests connectivity dependency. hai 3 semanas
download_csv.sh 4655c26f1f Add untracked project files and configs hai 2 semanas
generate_taiga_wiki.py e78a25bf3c TG-2: Populate Sprint 2 accomplishments in Taiga Wiki hai 4 semanas
ingest_csv.py 3fd4469aff Implement Grouped Vertical Partitioning architecture hai 2 semanas
init.sql ae711f7d4c TG-3: Docker Setup and DB Creation hai 1 mes
master_trigger.sh 38a83a1bf0 Deployment Finalization: Vitamin schemas, Green UI, and Taiga tools hai 3 semanas
my.cnf 86c76e282d TG-1: Fix MySQL 8.0 startup crash by removing premature validate_password plugin config hai 4 semanas
myloginpath.py 4655c26f1f Add untracked project files and configs hai 2 semanas
requirements.txt 9c6abcff81 TG-4: Data Ingestion Pipeline hai 1 mes
setup_db.py d5eae6eb05 Disable foreign key checks during drop hai 2 semanas
setup_logins.exp c830b35313 TG-2: Automate DB setup and mysql_config_editor passwords for CI/CD hai 4 semanas
setup_mail_forwarding.sh ab7e3b1d3a TG-2: Restructure schema for all CSV columns, async ingestion, and mail forwarding hai 3 semanas
setup_postfix.sh 38a83a1bf0 Deployment Finalization: Vitamin schemas, Green UI, and Taiga tools hai 3 semanas
setup_searxng.sh ebfb102bc7 TG-20: Create setup_searxng.sh to install Docker and bind anonymous SearXNG to localhost:8080. hai 3 semanas
setup_unix_user.sh 4655c26f1f Add untracked project files and configs hai 2 semanas
start_batch_ingest.sh 00f1d63625 Fix python virtual env paths hai 3 semanas
sync_taiga.py ef9531a80d TG-3: Update python sync script with correct username FrancoisLange hai 4 semanas
taiga_sync_fixer.py 4655c26f1f Add untracked project files and configs hai 2 semanas
unit_converter.py 620543f87d Implement full dynamic CSV schema ingestion and unit conversion module hai 2 semanas

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.
  • 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.
  • High-Performance Database: Implements Grouped Vertical Partitioning to bypass InnoDB limits, featuring FULLTEXT indexing for lightning-fast search capabilities across millions of foods.

Documentation

Please refer to the docs/ folder for detailed guides:

Tech Stack

  • Frontend: Streamlit
  • Database: MySQL 8.0
  • AI Engine: Ollama (Mistral / Llama3)
  • Deployment: Native Ubuntu, Docker, Kubernetes
  • Project Management: Taiga (Synced dynamically via Python)