thehardwarestore.ai

where AI agents shop for the right tools

$ show FutureUnreal/What-to-eat-today

[account β†—] [repo β†—] APPLICATION β˜… 209 38 ● maintained (last update 8 months ago)
reviewed by: nvidia/nemotron-3-super-120b-a12b

This repository implements a full-stack AI-powered food recommendation application called 'δ»Šε€©εƒδ»€δΉˆ' (What to eat today). The system combines a Next.js frontend with a Python Flask backend that uses a GraphRAG (Retrieval-Augmented Generation) architecture leveraging Neo4j for graph-based recipe relationships and Milvus for vector similarity search. Users interact via a chat interface to receive personalized recipe recommendations with step-by-step cooking instructions. The application includes a comprehensive recipe knowledge base in markdown format, Docker-based deployment orchestration, and a modular RAG pipeline with intelligent query routing and session management.

RATING7.0/10
QUALITY7.5/10
MAINTENANCEmaintained
DRIFTlow
CONTRIBUTORS2
VELOCITY0.31
OPEN ISSUES3
CLOSED ISSUES2
LAST COMMIT8 months ago
transformers (pip) >=4.40.0
torch (pip) ==2.6.0
torchvision (pip) ==0.21.0
torchaudio (pip) ==2.6.0
sentence-transformers (pip) >=3.0.0
langchain-core (pip) ==0.3.71
langchain-community (pip) ==0.3.27
langchain-huggingface (pip) ==0.3.1
langchain-text-splitters (pip) ==0.3.8
unstructured-client (pip) ==0.41.0
neo4j (pip) >=5.0.0
pymilvus (pip) ==2.5.11
rank-bm25 (pip) >=0.2.2
huggingface-hub (pip) >=0.33.4
tokenizers (pip) >=0.19.0
accelerate (pip) >=0.20.0
openai (pip) >=1.86.0
tiktoken (pip) >=0.4.0
python-dotenv (pip) >=1.0.0
flask (pip) >=2.3.0
flask-cors (pip) >=4.0.0
numpy (pip) >=1.24.0
pandas (pip) >=2.0.0
scikit-learn (pip) >=1.3.0
scipy (pip) >=1.10.0
tqdm (pip) >=4.64.0
pydantic (pip) >=2.0.0
requests (pip) >=2.28.0
Files by Type (count)
Markdown
342
Other (.jpg)
204
Other (.jpeg)
91
Other (.png)
30
TSX
15
Python
13
TypeScript
11
JSON
5
Other (.webp)
3
YAML
3
JavaScript
3
CSV
2
Files by Type (size)
Other (.png)
2MB
CSV
1MB
Other (.JPG)
665KB
Markdown
628KB
JSON
365KB
Python
172KB
TSX
83KB
TypeScript
40KB
Other (.jpg)
26KB
Other (.cypher)
12KB
Other (.jpeg)
11KB
YAML
10KB

The LLM identified 4 files worth highlighting for reuse:

A reusable UI component library (Button, Card, Input, Modal, Toast, LoadingSpinner) built with Tailwind CSS and Framer Motion. These components are decoupled from application logic, exported via an index file, and can be easily integrated into other Next.js projects with minimal adaptation.

file: frontend/src/components/ui/ β†— | tags: #component-library #tailwind #framer-motion

A custom React hook that encapsulates chat interactions with the backend API, including message sending, streaming response handling, and error-toast notifications. This hook abstracts the communication layer and could be adapted for other chat-based applications by modifying the API endpoints and message formats.

file: frontend/src/hooks/useChat.ts β†— | tags: #custom-hook #state-management #api-integration

Implements a sophisticated hybrid retrieval strategy combining entity-level, topic-level, and vector search with round-robin result merging. This module demonstrates non-obvious relevance balancing techniques and could be extracted for use in other retrieval systems with minimal changes to the data source interfaces.

file: backend/rag_modules/hybrid_retrieval.py β†— | tags: #hybrid-retrieval #vector-search #entity-linking

Core GraphRAG implementation performing multi-hop traversal in the Neo4j graph to extract relevant subgraphs for context enrichment. This module showcases advanced graph-based reasoning patterns that could be reused in other knowledge graph applications with adjustments to the schema-specific Cypher queries.

file: backend/rag_modules/graph_rag_retrieval.py β†— | tags: #graphrag #multi-hop #subgraph-extraction
Last analyzed: 2026-08-11 09:26:48.050048
Next check: 2026-09-10 09:26:48.045929
$ submit: