ragup 0.1.0

Build semantic search, question answering, and FastAPI-powered RAG applications in just a few lines of Python.

🚀 RagUp

Build semantic search, AI-powered question answering, and FastAPI APIs from your documents in just a few lines of Python.

RagUp is an opinionated Python library that lets you turn documents into searchable AI knowledge bases with almost no setup.

---

✨ Features

• 📄 Supports PDF, TXT and JSON documents
• 🧠 Local embeddings using Sentence Transformers
• 🔍 Semantic Search
• 🤖 AI-powered Question Answering (Gemini)
• ⚡ FastAPI server with automatic Swagger UI
• 💾 Persistent indexing (no re-indexing if nothing changes)
• 🐍 Simple Python API

---

📦 Installation

pip install ragup

---

⚡ Quick Start

from ragup import Document

doc = Document("policy.pdf")

# Build the index
doc.ragup()

# Semantic Search
results = doc.search(
    "refund policy"
)

print(results)

# AI Question Answering
answer = doc.ask(
    "What is the refund policy?",
    api_key="YOUR_GEMINI_API_KEY"
)

print(answer)

# Launch FastAPI
doc.serve(
    api_key="YOUR_GEMINI_API_KEY"
)

Open

http://localhost:8085/docs

to access the interactive Swagger UI.

---

📚 Supported Documents

Format	Supported
PDF	✅
TXT	✅
JSON	✅

---

🔍 Semantic Search

results = doc.search(
    "shipping charges",
    top_k=3
)

Returns the most relevant chunks from your document.

---

🤖 AI Question Answering

answer = doc.ask(
    "Summarize this document",
    api_key="YOUR_GEMINI_API_KEY"
)

RagUp retrieves relevant chunks and asks Gemini to answer using only the document context.

---

🌐 FastAPI Server

doc.serve(
    api_key="YOUR_GEMINI_API_KEY"
)

Available endpoints

POST /search
POST /ask
GET  /health
GET  /docs

If no API key is supplied,

doc.serve()

the /ask endpoint is automatically disabled.

---

💾 Persistent Indexing

The first time you call

doc.ragup()

RagUp creates a local index.

Subsequent calls reuse the cached index automatically if the document hasn't changed, making startup almost instantaneous.

---

🛣 Roadmap

v0.1.0

• ✅ PDF Support
• ✅ TXT Support
• ✅ JSON Support
• ✅ Semantic Search
• ✅ Gemini Question Answering
• ✅ FastAPI Server
• ✅ Persistent Indexing

Upcoming

• DOCX Support
• Markdown Support
• HTML Support
• Multi-document collections
• Multiple LLM providers
• Better chunking strategies
• CLI Support

---

🤝 Contributing

Contributions, feature requests and bug reports are welcome.

Feel free to open an issue or submit a pull request.

---

📄 License

MIT License

---

🧠 Built by the brain of Mehul Dewan. Powered by caffeine.