🚀 create-rag-app
A CLI tool that lets you generate production-ready RAG (Retrieval-Augmented Generation) applications in seconds.
⚙️ Choose your stack. 📦 Get a complete Dockerized project. 🧠 Power your app with your data + LLMs.
🌟 Why create-rag-app?
Building RAG apps is complex—you need to juggle LLMs, embeddings, chunking, retrieval, APIs, and more. With create-rag-app, all of this becomes plug-and-play:
✅ Standardized architecture
✅ Developer-first CLI
✅ Open-source & extensible
Whether you're building an AI chatbot over your docs or a powerful knowledge assistant, this CLI sets you up with a solid, scalable foundation.
🔧 What It Will Do
You run:
npx create-rag-app
And answer a few questions:
- LLM Provider? (OpenAI, Claude, Local)
- Vector DB? (Qdrant)
- Frontend? (None, Streamlit, Next.js)
- Document Loader? (Local, Web, Notion, YouTube)
- Chunking Strategy? (Fixed, Recursive, Metadata-aware)
- Embedding Model? (OpenAI, HuggingFace, Local)
- RAG Framework? (LangChain, LlamaIndex, None)
- Prompt Type? (Basic, Conversational, Agentic)
- Auth? (None, JWT, Basic)
- Extras? (Monitoring, Eval Setup, Dataset preload)
💥 Boom. Your RAG app scaffold is ready inside a Docker container.
📁 Example Output Structure
my-rag-app/
├── backend/
│ ├── api/
│ ├── loaders/
│ ├── retriever/
│ ├── llm/
│ └── main.py
├── frontend/ (optional)
│ └── pages/
├── data/
├── .env.template
├── docker-compose.yml
└── README.md
🚧 Features To Be Implemented
Here's what's on the roadmap for the first MVP:
✅ Core CLI
- Interactive CLI with
inquirer - Dynamic template scaffolding
- Backend stack choices (FastAPI, Express)
🧠 RAG Configuration
- LLM selection (OpenAI, Anthropic, local models)
- Embedder selection (OpenAI, BGE, Cohere, etc.)
- Vector DB support (Qdrant)
- Data loader types (PDF, YouTube, Notion, Web)
🧱 Frontend (optional)
- Streamlit or Next.js integration
- Basic chat UI with source highlighting
🧪 Extras
- Prompt customization options
- Eval flow scaffold (Precision@K, feedback loop)
- Monitoring/logging (basic + OpenTelemetry)
- Auth layer (JWT / basic auth)
🐳 DevOps
- Dockerized full-stack output
- Git auto-init and install
.envtemplating and secrets handling
🤝 Contributing
Got an idea? Want to add a new integration (e.g., Qdrant or Supabase)? We'd love to have you onboard.
git clone https://github.com/yourname/create-rag-app
cd create-rag-app
npm install
npm link
create-rag-app
🛠 Tech Stack (Planned)
- CLI: Node.js + TypeScript
- CLI UI: Inquirer.js, Chalk
- Templates: EJS-based folders
- Backend: FastAPI (Python) or Express (Node)
- Frontend: Next.js or Streamlit
- DevOps: Docker, Docker Compose
Metadata
Release files for create-rag-app 0.1.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| create_rag_app-0.1.2.tar.gz | 21.2 kB | Without provenance | Details for create_rag_app-0.1.2.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| create_rag_app-0.1.2-py3-none-any.whl | Python 3 | none | any | Details for create_rag_app-0.1.2-py3-none-any.whl |
Total release size: 54.2 kB
Release files / create_rag_app-0.1.2.tar.gz
| Download URL | create_rag_app-0.1.2.tar.gz |
|---|---|
| Size | 21.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
64064f8a6158cc1982450c69e2fc1252ba067122946f68fd7ffcefe9c4c4fd67
|
|
BLAKE2b-256 checksum How to use checksums |
f13e0013d461df3dcae9e5e31f2d92d8c8dc22920672c0ddd422a802ce8f33f0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/2.1.3 CPython/3.13.3 Darwin/24.4.0
|
Release files / create_rag_app-0.1.2-py3-none-any.whl
| Download URL | create_rag_app-0.1.2-py3-none-any.whl |
|---|---|
| Size | 33.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
17da7f56c341fa1ea45250da5780000603d289b5a42aa7930e257ba6cf4ec55e
|
|
BLAKE2b-256 checksum How to use checksums |
34c23eefabad004d62daccdba6adbc3f7233c25951667d9e6dae294b5f8357e8
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/2.1.3 CPython/3.13.3 Darwin/24.4.0
|
Security for create-rag-app 0.1.2
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.