Loading repository data…
nus83ca / repository
A lightweight local AI Q&A web app built with FastAPI and Jinja templates. It provides a simple browser interface where users submit a prompt, sends it to a local Ollama model, and displays the generated response page.
A lightweight local AI Q&A web app built with FastAPI and Jinja templates. It provides a simple browser interface where users submit a prompt, sends it to a local Ollama model, and displays the generated response page.
app.py: FastAPI app and routestemplates/index.html: Home page with question formtemplates/answer.html: Answer page rendered after form submitllama3)Use the official Ollama installer for your platform:
.dmg, drag Ollama to Applications, then launch it onceRun the official install script:
curl -fsSL https://ollama.com/install.sh | sh
For manual Linux installation details, see https://docs.ollama.com/linux
After installation, start Ollama if it is not already running and pull the default model used by this app:
ollama pull llama3
python3 -m venv .venv
source .venv/bin/activate
pip install fastapi uvicorn httpx jinja2 python-multipart
Run these in separate terminals.
ollama serve
uvicorn app:app --reload
http://127.0.0.1:8000
/ to load index.html.http://localhost:11434/api/chat./ask using answer.html.Error: Error: [Errno 2] No such file or directory: '.venv/bin/python3'
Cause: This occurs when the .venv directory is partially created or corrupted from a failed setup attempt.
Solution: Remove and recreate the virtual environment:
rm -rf .venv
python3 -m venv .venv
source .venv/bin/activate
pip install fastapi uvicorn httpx jinja2 python-multipart
/ask requests will fail.app.py as MODEL = "llama3".Selected from shared topics, language and repository description—not editorial ratings.
TomBadash /
A lightweight, open-source, fully local alternative to Logitech Options+ for remapping Logitech HID++ mice.
andy-landy /
Adds variables to python traceback. Simple, lightweight, controllable. Customize formats and colors. Debug reasons of exceptions by logging or pretty printing colorful variable contexts for each frame in a stacktrace, showing every value. Dump locals environments after errors to console, files, and loggers. Works in Jupyter too.
whyzhow /
Let AI think and express like you. This framework provides a complete assembly line: from the noise processing of original chat records, to the seamless switching of multi-model adaptation layers, to local lightweight fine-tuning (LoRA).
localstack /
🐍 A lightweight Python client for LocalStack
atompilot /
QMT Bridge is a lightweight API server that wraps xtquant (the Python library behind miniQMT) and exposes market data as standard HTTP/WebSocket endpoints. It runs on your Windows machine alongside the QMT client, allowing any device on your local network - Mac, Linux, or mobile - to access real-time quotes, historical K-lines, sector data...
kyrtstn /
syv ⚡ A dual-threat optimization CLI. Combines local Static Site Generation (SSG) caching and Single Page Application (SPA) payload compression into one lightweight, zero-dependency daemon. Built for Termux and Linux.