QCX
Health Gecti
- License — License: Apache-2.0
- Description — Repository has a description
- Active repo — Last push 0 days ago
- Community trust — 17 GitHub stars
Code Uyari
- process.env — Environment variable access in app/actions.tsx
- process.env — Environment variable access in app/api/embeddings/route.ts
Permissions Gecti
- Permissions — No dangerous permissions requested
This tool is a Next.js web application that integrates AI chat functionality with interactive maps. It allows users to leverage generative AI models to explore and interact with geographical data, utilizing services like Mapbox and various search APIs.
Security Assessment
The overall risk is rated as Low. The tool does not request dangerous system permissions or execute arbitrary shell commands. It relies on standard environment variables (defined in a `.env.local` file) to manage API keys for third-party services such as OpenAI, Mapbox, and Upstash Redis. There are no hardcoded secrets, and the flagged environment variable accesses are standard, secure practices for configuring API connections in Next.js applications. It inherently makes external network requests to function (fetching map tiles, querying LLMs, and accessing the Redis database), but these are expected behaviors for its intended purpose.
Quality Assessment
The project appears to be actively maintained, with its last code push occurring very recently. It uses a permissive and standard open-source license (Apache-2.0), making it safe for integration and modification. The repository has a clear description and detailed instructions for local setup. With 17 GitHub stars, the community trust level is relatively low, which is typical for niche or early-stage developer tools rather than a sign of poor quality. The codebase relies on reputable, modern frameworks and well-known SaaS providers.
Verdict
Safe to use. (Standard security practices apply: ensure you securely manage your own API keys and never commit your local `.env` file to public version control.)
Language to Maps
Contributing
Welcome! Please see the issues for items that need attention, and below for some tools to aid in development and debugging. We're working to interpolate chat functionality onto the map module.
Documentation.
https://deepwiki.com/QueueLab/QCX
Running the app on your own machine
Stack
- App framework: Next.js
- Text streaming / Generative UI: Vercel AI SDK
- Generative Model Varies
- Search API: Tavily AI / Exa AI
- Serverless Database: Upstash
- Component library: shadcn/ui
- Headless component primitives: Radix UI
- Styling: Tailwind CSS
- Mapping : [Mapbox]
(https://www.mapbox.com/)
2. Install dependencies
install bun package manager
bun install
bun run build
bun run dev
3. Setting up Upstash Redis
Follow the guide below to set up Upstash Redis. Create a database and obtain UPSTASH_REDIS_REST_URL and UPSTASH_REDIS_REST_TOKEN. Refer to the Upstash guide for instructions on how to proceed.
4. Fill out secrets
cp .env.local.example .env.local
Your .env.local file should look like this:
# XAI API key retrieved here: https://platform.openai.com/api-keys
XAI_API_KEY=
# Tavily API Key retrieved here: https://app.tavily.com/home
TAVILY_API_KEY=
# Upstash Redis URL and Token retrieved here: https://console.upstash.com/redis
UPSTASH_REDIS_REST_URL=
UPSTASH_REDIS_REST_TOKEN=
#Mapbox access token
NEXT_PUBLIC_MAPBOX_ACCESS_TOKEN
Note: This project focuses on Generative UI and requires complex output from LLMs. Currently, it's assumed that the official state of the art models will be used. Although it's possible to set up other models, if you use an Standard-compatible model, but we don't guarantee that it'll work.
5. Run app locally
bun run dev
You can now visit http://localhost:3000.
Verified models
List of non reasoning verified models
Grok-3-mini
Yorumlar (0)
Yorum birakmak icin giris yap.
Yorum birakSonuc bulunamadi