ragup 0.1.0__tar.gz

ragup-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Mehul Dewan
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

ragup-0.1.0/PKG-INFO

@@ -0,0 +1,224 @@
+Metadata-Version: 2.4
+Name: ragup
+Version: 0.1.0
+Summary: Build semantic search, question answering, and FastAPI-powered RAG applications in just a few lines of Python.
+Author-email: Mehul Dewan <mehul.work.17@gmail.com>
+License: MIT
+Project-URL: Homepage, https://github.com/mehuldewan17/RagUp
+Project-URL: Repository, https://github.com/mehuldewan17/RagUp
+Project-URL: Issues, https://github.com/mehuldewan17/RagUp/issues
+Keywords: rag,genai,llm,embeddings,semantic-search,vector-database,chromadb,fastapi,ai,python
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Intended Audience :: Developers
+Classifier: Topic :: Software Development :: Libraries
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pymupdf>=1.24.0
+Requires-Dist: chromadb>=0.5.0
+Requires-Dist: sentence-transformers>=3.0.0
+Requires-Dist: fastapi>=0.115.0
+Requires-Dist: uvicorn>=0.30.0
+Requires-Dist: litellm>=1.40.0
+Requires-Dist: pydantic>=2.8.0
+Requires-Dist: numpy>=1.26.0
+Requires-Dist: tqdm>=4.66.0
+Requires-Dist: typing_extensions>=4.12.0
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0.0; extra == "dev"
+Requires-Dist: black>=24.0.0; extra == "dev"
+Requires-Dist: isort>=5.13.0; extra == "dev"
+Requires-Dist: mypy>=1.10.0; extra == "dev"
+Dynamic: license-file
+
+# 🚀 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
+
+```bash
+pip install ragup
+```
+
+---
+
+## ⚡ Quick Start
+
+```python
+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
+
+```python
+results = doc.search(
+    "shipping charges",
+    top_k=3
+)
+```
+
+Returns the most relevant chunks from your document.
+
+---
+
+# 🤖 AI Question Answering
+
+```python
+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
+
+```python
+doc.serve(
+    api_key="YOUR_GEMINI_API_KEY"
+)
+```
+
+Available endpoints
+
+```
+POST /search
+POST /ask
+GET  /health
+GET  /docs
+```
+
+If no API key is supplied,
+
+```python
+doc.serve()
+```
+
+the `/ask` endpoint is automatically disabled.
+
+---
+
+# 💾 Persistent Indexing
+
+The first time you call
+
+```python
+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.

ragup-0.1.0/README.md

@@ -0,0 +1,185 @@
+# 🚀 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
+
+```bash
+pip install ragup
+```
+
+---
+
+## ⚡ Quick Start
+
+```python
+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
+
+```python
+results = doc.search(
+    "shipping charges",
+    top_k=3
+)
+```
+
+Returns the most relevant chunks from your document.
+
+---
+
+# 🤖 AI Question Answering
+
+```python
+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
+
+```python
+doc.serve(
+    api_key="YOUR_GEMINI_API_KEY"
+)
+```
+
+Available endpoints
+
+```
+POST /search
+POST /ask
+GET  /health
+GET  /docs
+```
+
+If no API key is supplied,
+
+```python
+doc.serve()
+```
+
+the `/ask` endpoint is automatically disabled.
+
+---
+
+# 💾 Persistent Indexing
+
+The first time you call
+
+```python
+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.

ragup-0.1.0/pyproject.toml

@@ -0,0 +1,82 @@
+[build-system]
+requires = ["setuptools>=68.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "ragup"
+version = "0.1.0"
+description = "Build semantic search, question answering, and FastAPI-powered RAG applications in just a few lines of Python."
+readme = "README.md"
+requires-python = ">=3.10"
+license = { text = "MIT" }
+
+authors = [
+    { name="Mehul Dewan", email="mehul.work.17@gmail.com" }
+]
+
+keywords = [
+    "rag",
+    "genai",
+    "llm",
+    "embeddings",
+    "semantic-search",
+    "vector-database",
+    "chromadb",
+    "fastapi",
+    "ai",
+    "python"
+]
+
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+    "Intended Audience :: Developers",
+    "Topic :: Software Development :: Libraries",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence"
+]
+
+dependencies = [
+    "pymupdf>=1.24.0",
+    "chromadb>=0.5.0",
+    "sentence-transformers>=3.0.0",
+    "fastapi>=0.115.0",
+    "uvicorn>=0.30.0",
+    "litellm>=1.40.0",
+    "pydantic>=2.8.0",
+    "numpy>=1.26.0",
+    "tqdm>=4.66.0",
+    "typing_extensions>=4.12.0"
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=8.0.0",
+    "black>=24.0.0",
+    "isort>=5.13.0",
+    "mypy>=1.10.0"
+]
+
+[project.urls]
+Homepage = "https://github.com/mehuldewan17/RagUp"
+Repository = "https://github.com/mehuldewan17/RagUp"
+Issues = "https://github.com/mehuldewan17/RagUp/issues"
+
+[tool.setuptools]
+include-package-data = true
+
+[tool.setuptools.packages.find]
+include = ["ragup*"]
+
+[tool.black]
+line-length = 88
+
+[tool.isort]
+profile = "black"
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+python_files = ["test_*.py"]

ragup-0.1.0/ragup/__init__.py

@@ -0,0 +1,7 @@
+from .core.document import Document
+
+__version__ = "1.0.0"
+
+__all__ = [
+    "Document",
+]

ragup-0.1.0/ragup/api/__init__.py

@@ -0,0 +1,5 @@
+from .server import RagUpServer
+
+__all__ = [
+    "RagUpServer",
+]

ragup-0.1.0/ragup/api/routes.py

@@ -0,0 +1,7 @@
+"""
+FastAPI routes.
+"""
+
+from fastapi import APIRouter
+
+router = APIRouter()

ragup-0.1.0/ragup/api/schemas.py

@@ -0,0 +1,15 @@
+"""
+Pydantic request models.
+"""
+
+from pydantic import BaseModel
+
+
+class SearchRequest(BaseModel):
+    query: str
+    top_k: int = 5
+
+
+class AskRequest(BaseModel):
+    question: str
+    top_k: int = 5

ragup-0.1.0/ragup/api/server.py

@@ -0,0 +1,81 @@
+"""
+FastAPI server for RagUp.
+"""
+
+from __future__ import annotations
+
+import uvicorn
+
+from fastapi import FastAPI
+
+from ..constants import (
+    DEFAULT_HOST,
+    DEFAULT_PORT,
+)
+from .schemas import (
+    AskRequest,
+    SearchRequest,
+)
+
+
+class RagUpServer:
+
+    def __init__(
+        self,
+        document,
+        api_key: str | None = None,
+    ):
+
+        self.document = document
+        self.api_key = api_key
+
+        self.app = FastAPI(
+            title="RagUp API",
+            version="1.0.0",
+        )
+
+        self._register_routes()
+
+    def _register_routes(self):
+
+        @self.app.get("/health")
+        def health():
+
+            return {
+                "status": "healthy"
+            }
+
+        @self.app.post("/search")
+        def search(request: SearchRequest):
+
+            return self.document.search(
+                query=request.query,
+                top_k=request.top_k,
+            )
+
+        if self.api_key:
+
+            @self.app.post("/ask")
+            def ask(request: AskRequest):
+
+                answer = self.document.ask(
+                    question=request.question,
+                    api_key=self.api_key,
+                    top_k=request.top_k,
+                )
+
+                return {
+                    "answer": answer
+                }
+
+    def run(
+        self,
+        host: str = DEFAULT_HOST,
+        port: int = DEFAULT_PORT,
+    ):
+
+        uvicorn.run(
+            self.app,
+            host=host,
+            port=port,
+        )

ragup-0.1.0/ragup/chunking/__init__.py

@@ -0,0 +1,9 @@
+
+
+from .base import BaseChunker
+from .recursive import RecursiveChunker
+
+__all__ = [
+    "BaseChunker",
+    "RecursiveChunker",
+]

ragup-0.1.0/ragup/chunking/base.py

@@ -0,0 +1,36 @@
+"""
+Base interface for all text chunkers.
+"""
+
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+
+
+class BaseChunker(ABC):
+    """
+    Base class for all chunking strategies.
+    """
+
+    def __init__(
+        self,
+        chunk_size: int = 500,
+        overlap: int = 50,
+    ):
+        self.chunk_size = chunk_size
+        self.overlap = overlap
+
+    @abstractmethod
+    def split(self, text: str) -> list[str]:
+        """
+        Split text into chunks.
+
+        Parameters
+        ----------
+        text : str
+
+        Returns
+        -------
+        list[str]
+        """
+        raise NotImplementedError