<p align="center">
<img src="logo.jpg" alt="Tinyrag Logo" width="200"/>
</p>
# TinyRag 🚀
[](https://badge.fury.io/py/tinyrag)
[](https://www.python.org/downloads/)
[](https://opensource.org/licenses/MIT)
[](https://tinyrag-docs.netlify.app/docs)
[](https://pepy.tech/projects/tinyrag)
A **lightweight, powerful Python library** for **Retrieval-Augmented Generation (RAG)** that works locally without API keys. Features advanced codebase indexing, multiple document formats, and flexible vector storage backends.
> **🎯 Perfect for developers who need RAG capabilities without complexity or mandatory cloud dependencies.**
## 🌟 Key Features
### 🚀 **Works Locally - No API Keys Required**
- **🧠 Local Embeddings**: Uses all-MiniLM-L6-v2 by default
- **🔍 Direct Search**: Query documents without LLM costs
- **⚡ Zero Setup**: Works immediately after installation
### 📚 **Advanced Document Processing**
- **📄 Multi-Format**: PDF, DOCX, CSV, TXT, and raw text
- **💻 Code Intelligence**: Function-level indexing for 7+ programming languages
- **🧵 Multithreading**: Parallel processing for faster indexing
- **📊 Chunking Strategies**: Smart text segmentation
### 🗄️ **Flexible Storage Options**
- **🔌 Multiple Backends**: Memory, Pickle, Faiss, ChromaDB
- **💾 Persistence**: Automatic or manual data saving
- **⚡ Performance**: Choose speed vs. memory trade-offs
- **🔧 Configuration**: Customizable for any use case
### 💬 **Optional AI Integration**
- **🤖 Custom System Prompts**: Tailor AI behavior for your domain
- **🔗 Provider Support**: OpenAI, Azure, Anthropic, local models
- **💰 Cost Control**: Use only when needed
- **🎯 RAG-Powered Chat**: Contextual AI responses
## 🚀 Quick Start
> **💡 New to TinyRag?** Check out our comprehensive [📖 Documentation](https://tinyrag-docs.netlify.app/docs) with step-by-step guides!
### Installation
```bash
# Basic installation
pip install tinyrag
# With all optional dependencies
pip install tinyrag[all]
# Specific vector stores
pip install tinyrag[faiss] # High performance
pip install tinyrag[chroma] # Persistent storage
pip install tinyrag[docs] # Document processing
```
### Usage Examples
### 🏃♂️ 30-Second Example (No API Key Required)
```python
from tinyrag import TinyRag
# 1. Create TinyRag instance
rag = TinyRag()
# 2. Add your content
rag.add_documents([
"TinyRag makes RAG simple and powerful.",
"docs/user_guide.pdf",
"research_papers/"
])
# 3. Search your content
results = rag.query("How does TinyRag work?", k=3)
for text, score in results:
print(f"Score: {score:.2f} - {text[:100]}...")
```
**Output:**
```
Score: 0.89 - TinyRag makes RAG simple and powerful.
Score: 0.76 - TinyRag is a lightweight Python library for...
Score: 0.72 - The system processes documents using semantic...
```
### 🤖 AI-Powered Chat (Optional)
```python
from tinyrag import Provider, TinyRag
# Set up AI provider
provider = Provider(
api_key="sk-your-openai-key",
model="gpt-4"
)
# Create smart assistant
rag = TinyRag(
provider=provider,
system_prompt="You are a helpful technical assistant."
)
# Add knowledge base
rag.add_documents(["technical_docs/", "api_guides/"])
rag.add_codebase("src/") # Index your codebase
# Get intelligent answers
response = rag.chat("How do I implement user authentication?")
print(response)
# AI response based on your specific docs and code!
```
## 📖 Complete Documentation
**📚 [Full Documentation](docs/README.md)** - Comprehensive guides from beginner to expert
### 🚀 **Getting Started**
- [**Quick Start**](docs/01-quick-start.md) - 5-minute introduction
- [**Installation**](docs/02-installation.md) - Complete setup guide
- [**Basic Usage**](docs/03-basic-usage.md) - Core features without AI
### 🔧 **Core Features**
- [**Document Processing**](docs/04-document-processing.md) - PDF, DOCX, CSV, TXT
- [**Codebase Indexing**](docs/05-codebase-indexing.md) - Function-level code search
- [**Vector Stores**](docs/06-vector-stores.md) - Choose the right storage
- [**Search & Query**](docs/07-search-query.md) - Similarity search techniques
### 🤖 **AI Integration**
- [**System Prompts**](docs/08-system-prompts.md) - Customize AI behavior
- [**Chat Functionality**](docs/09-chat-functionality.md) - Build conversations
- [**Provider Configuration**](docs/10-provider-config.md) - AI model setup
---
## 🔧 Core API Reference
### Provider Class
```python
from tinyrag import Provider
# 🆓 No API key needed - works locally
provider = Provider(embedding_model="default")
# 🤖 With AI capabilities
provider = Provider(
api_key="sk-your-key",
model="gpt-4", # GPT-4, GPT-3.5, local models
embedding_model="text-embedding-ada-002", # or "default" for local
base_url="https://api.openai.com/v1" # OpenAI, Azure, custom
)
```
### TinyRag Class
```python
from tinyrag import TinyRag
# 🎛️ Choose your vector store
rag = TinyRag(
provider=provider, # Optional: for AI chat
vector_store="faiss", # memory, pickle, faiss, chromadb
chunk_size=500, # Text chunk size
max_workers=4, # Parallel processing
system_prompt="Custom prompt" # AI behavior
)
```
### 🗄️ Vector Store Comparison
| Store | Performance | Persistence | Memory | Dependencies | Best For |
|-------|-------------|-------------|---------|--------------|----------|
| **Memory** | ⚡ Fast | ❌ None | 📈 High | ✅ None | Development, testing |
| **Pickle** | 🐌 Fair | 💾 Manual | 📊 Medium | ✅ Minimal | Simple projects |
| **Faiss** | 🚀 Excellent | 💾 Manual | 📉 Low | 📦 faiss-cpu | Large datasets, speed |
| **ChromaDB** | ⚡ Good | 🔄 Auto | 📊 Medium | 📦 chromadb | Production, features |
> **💡 Recommendation:** Start with `memory` for development, use `faiss` for production performance.
## 🔧 Essential Methods
```python
# 📄 Document Management
rag.add_documents(["file.pdf", "text"]) # Add any documents
rag.add_codebase("src/") # Index code functions
rag.clear_documents() # Reset everything
# 🔍 Search & Query (No AI needed)
results = rag.query("search term", k=5) # Find similar content
code = rag.query("auth function") # Search code too
# 🤖 AI Chat (Optional)
response = rag.chat("Explain this code") # Get AI answers
rag.set_system_prompt("Be helpful") # Customize AI
# 💾 Persistence
rag.save_vector_store("my_data.pkl") # Save your work
rag.load_vector_store("my_data.pkl") # Load it back
```
> **📖 [Complete API Reference](docs/18-api-reference.md)** - Full method documentation
## 💻 Code Intelligence
TinyRag indexes your codebase at the **function level** for intelligent code search:
### 🌐 Supported Languages
| Language | Extensions | Detection |
|----------|------------|----------|
| **Python** | `.py` | `def function_name` |
| **JavaScript** | `.js`, `.ts` | `function name()`, `const name =` |
| **Java** | `.java` | `public/private type name()` |
| **C/C++** | `.c`, `.cpp`, `.h` | `return_type function_name()` |
| **Go** | `.go` | `func functionName()` |
| **Rust** | `.rs` | `fn function_name()` |
| **PHP** | `.php` | `function functionName()` |
### 🔍 Code Search Examples
```python
# Index your entire project
rag.add_codebase("my_app/")
# Find authentication code
auth_code = rag.query("user authentication login")
# Database functions
db_code = rag.query("database query SELECT")
# API endpoints
api_code = rag.query("REST API endpoint")
# Get AI explanations (with API key)
response = rag.chat("How does user authentication work?")
# AI analyzes your actual code and explains it!
```
> **💡 [Learn More](docs/05-codebase-indexing.md)** - Advanced code search techniques
## ⚙️ Configuration Examples
### 🚀 Performance Optimized
```python
# Large datasets, maximum speed
rag = TinyRag(
vector_store="faiss",
chunk_size=800,
max_workers=8 # Parallel processing
)
```
### 💾 Production Setup
```python
# Persistent, multi-user ready
rag = TinyRag(
provider=provider,
vector_store="chromadb",
vector_store_config={
"collection_name": "company_docs",
"persist_directory": "/data/vectors/"
}
)
```
### 🤖 Custom AI Assistant
```python
# Domain-specific AI behavior
rag = TinyRag(
provider=provider,
system_prompt="""You are a senior software engineer.
Provide detailed technical explanations with code examples."""
)
```
> **🔧 [Full Configuration Guide](docs/12-configuration.md)** - All options explained
## 📦 Installation
### 🎯 Choose Your Setup
```bash
# 🚀 Quick start (works immediately)
pip install tinyrag
# ⚡ High performance (recommended)
pip install tinyrag[faiss]
# 📄 Document processing (PDF, DOCX)
pip install tinyrag[docs]
# 🗄️ Production database
pip install tinyrag[chroma]
# 🎁 Everything included
pip install tinyrag[all]
```
### 🔧 What Each Option Includes
| Option | Includes | Use Case |
|--------|----------|----------|
| **Base** | Memory store, local embeddings | Development, testing |
| **[faiss]** | + High-performance search | Large datasets |
| **[docs]** | + PDF/DOCX processing | Document analysis |
| **[chroma]** | + Persistent database | Production apps |
| **[all]** | + Everything | Full features |
> **💡 [Installation Guide](docs/02-installation.md)** - Detailed setup instructions
## 🎯 Real-World Use Cases
### 🏢 **Business Applications**
- **📋 Customer Support**: Query company docs and policies
- **📚 Knowledge Management**: Searchable internal documentation
- **🔍 Research Tools**: Semantic search through research papers
- **📊 Report Analysis**: Find insights across business reports
### 👨💻 **Developer Tools**
- **🔧 Code Documentation**: Auto-generate code explanations
- **🔍 Legacy Code Explorer**: Understand large codebases
- **📖 API Assistant**: Query technical documentation
- **🧪 Testing Helper**: Find relevant test patterns
### 🎓 **Educational & Research**
- **📚 Study Assistant**: Query textbooks and notes
- **📝 Writing Helper**: Research paper analysis
- **🧠 Learning Companion**: Personalized explanations
- **📊 Data Analysis**: Explore datasets semantically
> **💡 [See Complete Examples](docs/15-examples.md)** - Production-ready applications
---
## 🛠️ Contributing
We welcome contributions! Here's how to get started:
```bash
# 1. Fork and clone
git clone https://github.com/Kenosis01/TinyRag.git
cd TinyRag
# 2. Install development dependencies
pip install -e ".[all,dev]"
# 3. Run tests
python -m pytest
# 4. Make your changes and submit a PR!
```
### 📋 **Development Setup**
- **Python 3.7+** required
- **Core dependencies**: sentence-transformers, requests, numpy
- **Optional**: faiss-cpu, chromadb, PyPDF2, python-docx
> **🔧 [Development Guide](CONTRIBUTING.md)** - Detailed contributor guidelines
## 🤝 Community & Support
### 📞 **Get Help**
- **📖 [Complete Documentation](docs/README.md)** - Comprehensive guides
- **🐛 [GitHub Issues](https://github.com/Kenosis01/TinyRag/issues)** - Bug reports & feature requests
- **💬 [Discussions](https://github.com/Kenosis01/TinyRag/discussions)** - Community Q&A
- **📋 [FAQ](docs/19-faq.md)** - Common questions answered
### 🎉 **Show Your Support**
- ⭐ **Star this repo** if TinyRag helps you!
- 🐦 **Share on Twitter** - spread the word
- ☕ **[Buy me a coffee](https://buymeacoffee.com/kenosis)** - support development
- 🤝 **Contribute** - help make TinyRag better
---
## 📄 License
MIT License - see [LICENSE](LICENSE) for details.
---
<div align="center">
**🚀 TinyRag - Making RAG Simple, Powerful, and Accessible! 🚀**
*Build intelligent search and Q&A systems in minutes, not hours*
[](https://github.com/Kenosis01/TinyRag)
[](https://pypi.org/project/tinyrag/)
[](https://github.com/Kenosis01/TinyRag)
</div>
Raw data
{
"_id": null,
"home_page": "https://github.com/Kenosis01/TinyRag",
"name": "tinyrag",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.7",
"maintainer_email": "TinyRag Team <transformtrails@gmail.com>",
"keywords": "rag, retrieval, augmented, generation, vector, database, embeddings, similarity, search, nlp, ai, machine-learning, codebase, code-indexing, function-search, code-analysis",
"author": "TinyRag Team",
"author_email": "TinyRag Team <transformtrails@gmail.com>",
"download_url": "https://files.pythonhosted.org/packages/38/5a/e514d4e3dd7737e5e09adbb3b2a8cfc04ead1768bf2d2a5becebd93e4444/tinyrag-0.3.5.tar.gz",
"platform": null,
"description": "<p align=\"center\">\r\n <img src=\"logo.jpg\" alt=\"Tinyrag Logo\" width=\"200\"/>\r\n</p>\r\n\r\n\r\n# TinyRag \ud83d\ude80\r\n\r\n[](https://badge.fury.io/py/tinyrag)\r\n[](https://www.python.org/downloads/)\r\n[](https://opensource.org/licenses/MIT)\r\n[](https://tinyrag-docs.netlify.app/docs)\r\n[](https://pepy.tech/projects/tinyrag)\r\n\r\n\r\n\r\nA **lightweight, powerful Python library** for **Retrieval-Augmented Generation (RAG)** that works locally without API keys. Features advanced codebase indexing, multiple document formats, and flexible vector storage backends.\r\n\r\n> **\ud83c\udfaf Perfect for developers who need RAG capabilities without complexity or mandatory cloud dependencies.**\r\n\r\n## \ud83c\udf1f Key Features\r\n\r\n### \ud83d\ude80 **Works Locally - No API Keys Required**\r\n- **\ud83e\udde0 Local Embeddings**: Uses all-MiniLM-L6-v2 by default\r\n- **\ud83d\udd0d Direct Search**: Query documents without LLM costs\r\n- **\u26a1 Zero Setup**: Works immediately after installation\r\n\r\n### \ud83d\udcda **Advanced Document Processing** \r\n- **\ud83d\udcc4 Multi-Format**: PDF, DOCX, CSV, TXT, and raw text\r\n- **\ud83d\udcbb Code Intelligence**: Function-level indexing for 7+ programming languages\r\n- **\ud83e\uddf5 Multithreading**: Parallel processing for faster indexing\r\n- **\ud83d\udcca Chunking Strategies**: Smart text segmentation\r\n\r\n### \ud83d\uddc4\ufe0f **Flexible Storage Options**\r\n- **\ud83d\udd0c Multiple Backends**: Memory, Pickle, Faiss, ChromaDB\r\n- **\ud83d\udcbe Persistence**: Automatic or manual data saving\r\n- **\u26a1 Performance**: Choose speed vs. memory trade-offs\r\n- **\ud83d\udd27 Configuration**: Customizable for any use case\r\n\r\n### \ud83d\udcac **Optional AI Integration**\r\n- **\ud83e\udd16 Custom System Prompts**: Tailor AI behavior for your domain\r\n- **\ud83d\udd17 Provider Support**: OpenAI, Azure, Anthropic, local models\r\n- **\ud83d\udcb0 Cost Control**: Use only when needed\r\n- **\ud83c\udfaf RAG-Powered Chat**: Contextual AI responses\r\n\r\n## \ud83d\ude80 Quick Start\r\n\r\n> **\ud83d\udca1 New to TinyRag?** Check out our comprehensive [\ud83d\udcd6 Documentation](https://tinyrag-docs.netlify.app/docs) with step-by-step guides!\r\n\r\n### Installation\r\n\r\n```bash\r\n# Basic installation\r\npip install tinyrag\r\n\r\n# With all optional dependencies\r\npip install tinyrag[all]\r\n\r\n# Specific vector stores\r\npip install tinyrag[faiss] # High performance\r\npip install tinyrag[chroma] # Persistent storage\r\npip install tinyrag[docs] # Document processing\r\n```\r\n\r\n### Usage Examples\r\n\r\n### \ud83c\udfc3\u200d\u2642\ufe0f 30-Second Example (No API Key Required)\r\n\r\n```python\r\nfrom tinyrag import TinyRag\r\n\r\n# 1. Create TinyRag instance\r\nrag = TinyRag()\r\n\r\n# 2. Add your content \r\nrag.add_documents([\r\n \"TinyRag makes RAG simple and powerful.\",\r\n \"docs/user_guide.pdf\",\r\n \"research_papers/\"\r\n])\r\n\r\n# 3. Search your content\r\nresults = rag.query(\"How does TinyRag work?\", k=3)\r\nfor text, score in results:\r\n print(f\"Score: {score:.2f} - {text[:100]}...\")\r\n```\r\n\r\n**Output:**\r\n```\r\nScore: 0.89 - TinyRag makes RAG simple and powerful.\r\nScore: 0.76 - TinyRag is a lightweight Python library for...\r\nScore: 0.72 - The system processes documents using semantic...\r\n```\r\n\r\n### \ud83e\udd16 AI-Powered Chat (Optional)\r\n\r\n```python\r\nfrom tinyrag import Provider, TinyRag\r\n\r\n# Set up AI provider\r\nprovider = Provider(\r\n api_key=\"sk-your-openai-key\",\r\n model=\"gpt-4\"\r\n)\r\n\r\n# Create smart assistant\r\nrag = TinyRag(\r\n provider=provider,\r\n system_prompt=\"You are a helpful technical assistant.\"\r\n)\r\n\r\n# Add knowledge base\r\nrag.add_documents([\"technical_docs/\", \"api_guides/\"])\r\nrag.add_codebase(\"src/\") # Index your codebase\r\n\r\n# Get intelligent answers\r\nresponse = rag.chat(\"How do I implement user authentication?\")\r\nprint(response)\r\n# AI response based on your specific docs and code!\r\n```\r\n\r\n## \ud83d\udcd6 Complete Documentation\r\n\r\n**\ud83d\udcda [Full Documentation](docs/README.md)** - Comprehensive guides from beginner to expert\r\n\r\n### \ud83d\ude80 **Getting Started**\r\n- [**Quick Start**](docs/01-quick-start.md) - 5-minute introduction\r\n- [**Installation**](docs/02-installation.md) - Complete setup guide \r\n- [**Basic Usage**](docs/03-basic-usage.md) - Core features without AI\r\n\r\n### \ud83d\udd27 **Core Features**\r\n- [**Document Processing**](docs/04-document-processing.md) - PDF, DOCX, CSV, TXT\r\n- [**Codebase Indexing**](docs/05-codebase-indexing.md) - Function-level code search\r\n- [**Vector Stores**](docs/06-vector-stores.md) - Choose the right storage\r\n- [**Search & Query**](docs/07-search-query.md) - Similarity search techniques\r\n\r\n### \ud83e\udd16 **AI Integration**\r\n- [**System Prompts**](docs/08-system-prompts.md) - Customize AI behavior\r\n- [**Chat Functionality**](docs/09-chat-functionality.md) - Build conversations\r\n- [**Provider Configuration**](docs/10-provider-config.md) - AI model setup\r\n\r\n---\r\n\r\n## \ud83d\udd27 Core API Reference\r\n\r\n### Provider Class\r\n\r\n```python\r\nfrom tinyrag import Provider\r\n\r\n# \ud83c\udd93 No API key needed - works locally\r\nprovider = Provider(embedding_model=\"default\")\r\n\r\n# \ud83e\udd16 With AI capabilities\r\nprovider = Provider(\r\n api_key=\"sk-your-key\",\r\n model=\"gpt-4\", # GPT-4, GPT-3.5, local models\r\n embedding_model=\"text-embedding-ada-002\", # or \"default\" for local\r\n base_url=\"https://api.openai.com/v1\" # OpenAI, Azure, custom\r\n)\r\n```\r\n\r\n### TinyRag Class\r\n\r\n```python\r\nfrom tinyrag import TinyRag\r\n\r\n# \ud83c\udf9b\ufe0f Choose your vector store\r\nrag = TinyRag(\r\n provider=provider, # Optional: for AI chat\r\n vector_store=\"faiss\", # memory, pickle, faiss, chromadb\r\n chunk_size=500, # Text chunk size\r\n max_workers=4, # Parallel processing\r\n system_prompt=\"Custom prompt\" # AI behavior\r\n)\r\n```\r\n\r\n### \ud83d\uddc4\ufe0f Vector Store Comparison\r\n\r\n| Store | Performance | Persistence | Memory | Dependencies | Best For |\r\n|-------|-------------|-------------|---------|--------------|----------|\r\n| **Memory** | \u26a1 Fast | \u274c None | \ud83d\udcc8 High | \u2705 None | Development, testing |\r\n| **Pickle** | \ud83d\udc0c Fair | \ud83d\udcbe Manual | \ud83d\udcca Medium | \u2705 Minimal | Simple projects |\r\n| **Faiss** | \ud83d\ude80 Excellent | \ud83d\udcbe Manual | \ud83d\udcc9 Low | \ud83d\udce6 faiss-cpu | Large datasets, speed |\r\n| **ChromaDB** | \u26a1 Good | \ud83d\udd04 Auto | \ud83d\udcca Medium | \ud83d\udce6 chromadb | Production, features |\r\n\r\n> **\ud83d\udca1 Recommendation:** Start with `memory` for development, use `faiss` for production performance.\r\n\r\n## \ud83d\udd27 Essential Methods\r\n\r\n```python\r\n# \ud83d\udcc4 Document Management\r\nrag.add_documents([\"file.pdf\", \"text\"]) # Add any documents\r\nrag.add_codebase(\"src/\") # Index code functions\r\nrag.clear_documents() # Reset everything\r\n\r\n# \ud83d\udd0d Search & Query (No AI needed)\r\nresults = rag.query(\"search term\", k=5) # Find similar content\r\ncode = rag.query(\"auth function\") # Search code too\r\n\r\n# \ud83e\udd16 AI Chat (Optional)\r\nresponse = rag.chat(\"Explain this code\") # Get AI answers\r\nrag.set_system_prompt(\"Be helpful\") # Customize AI\r\n\r\n# \ud83d\udcbe Persistence\r\nrag.save_vector_store(\"my_data.pkl\") # Save your work\r\nrag.load_vector_store(\"my_data.pkl\") # Load it back\r\n```\r\n\r\n> **\ud83d\udcd6 [Complete API Reference](docs/18-api-reference.md)** - Full method documentation\r\n\r\n## \ud83d\udcbb Code Intelligence\r\n\r\nTinyRag indexes your codebase at the **function level** for intelligent code search:\r\n\r\n### \ud83c\udf10 Supported Languages\r\n\r\n| Language | Extensions | Detection |\r\n|----------|------------|----------|\r\n| **Python** | `.py` | `def function_name` |\r\n| **JavaScript** | `.js`, `.ts` | `function name()`, `const name =` |\r\n| **Java** | `.java` | `public/private type name()` |\r\n| **C/C++** | `.c`, `.cpp`, `.h` | `return_type function_name()` |\r\n| **Go** | `.go` | `func functionName()` |\r\n| **Rust** | `.rs` | `fn function_name()` |\r\n| **PHP** | `.php` | `function functionName()` |\r\n\r\n### \ud83d\udd0d Code Search Examples\r\n\r\n```python\r\n# Index your entire project\r\nrag.add_codebase(\"my_app/\")\r\n\r\n# Find authentication code\r\nauth_code = rag.query(\"user authentication login\")\r\n\r\n# Database functions\r\ndb_code = rag.query(\"database query SELECT\")\r\n\r\n# API endpoints\r\napi_code = rag.query(\"REST API endpoint\")\r\n\r\n# Get AI explanations (with API key)\r\nresponse = rag.chat(\"How does user authentication work?\")\r\n# AI analyzes your actual code and explains it!\r\n```\r\n\r\n> **\ud83d\udca1 [Learn More](docs/05-codebase-indexing.md)** - Advanced code search techniques\r\n\r\n\r\n## \u2699\ufe0f Configuration Examples\r\n\r\n### \ud83d\ude80 Performance Optimized\r\n```python\r\n# Large datasets, maximum speed\r\nrag = TinyRag(\r\n vector_store=\"faiss\",\r\n chunk_size=800,\r\n max_workers=8 # Parallel processing\r\n)\r\n```\r\n\r\n### \ud83d\udcbe Production Setup\r\n```python\r\n# Persistent, multi-user ready\r\nrag = TinyRag(\r\n provider=provider,\r\n vector_store=\"chromadb\",\r\n vector_store_config={\r\n \"collection_name\": \"company_docs\",\r\n \"persist_directory\": \"/data/vectors/\"\r\n }\r\n)\r\n```\r\n\r\n### \ud83e\udd16 Custom AI Assistant\r\n```python\r\n# Domain-specific AI behavior\r\nrag = TinyRag(\r\n provider=provider,\r\n system_prompt=\"\"\"You are a senior software engineer.\r\n Provide detailed technical explanations with code examples.\"\"\"\r\n)\r\n```\r\n\r\n> **\ud83d\udd27 [Full Configuration Guide](docs/12-configuration.md)** - All options explained\r\n\r\n## \ud83d\udce6 Installation\r\n\r\n### \ud83c\udfaf Choose Your Setup\r\n\r\n```bash\r\n# \ud83d\ude80 Quick start (works immediately)\r\npip install tinyrag\r\n\r\n# \u26a1 High performance (recommended)\r\npip install tinyrag[faiss]\r\n\r\n# \ud83d\udcc4 Document processing (PDF, DOCX)\r\npip install tinyrag[docs]\r\n\r\n# \ud83d\uddc4\ufe0f Production database\r\npip install tinyrag[chroma]\r\n\r\n# \ud83c\udf81 Everything included\r\npip install tinyrag[all]\r\n```\r\n\r\n### \ud83d\udd27 What Each Option Includes\r\n\r\n| Option | Includes | Use Case |\r\n|--------|----------|----------|\r\n| **Base** | Memory store, local embeddings | Development, testing |\r\n| **[faiss]** | + High-performance search | Large datasets |\r\n| **[docs]** | + PDF/DOCX processing | Document analysis |\r\n| **[chroma]** | + Persistent database | Production apps |\r\n| **[all]** | + Everything | Full features |\r\n\r\n> **\ud83d\udca1 [Installation Guide](docs/02-installation.md)** - Detailed setup instructions\r\n\r\n## \ud83c\udfaf Real-World Use Cases\r\n\r\n### \ud83c\udfe2 **Business Applications**\r\n- **\ud83d\udccb Customer Support**: Query company docs and policies\r\n- **\ud83d\udcda Knowledge Management**: Searchable internal documentation\r\n- **\ud83d\udd0d Research Tools**: Semantic search through research papers\r\n- **\ud83d\udcca Report Analysis**: Find insights across business reports\r\n\r\n### \ud83d\udc68\u200d\ud83d\udcbb **Developer Tools**\r\n- **\ud83d\udd27 Code Documentation**: Auto-generate code explanations\r\n- **\ud83d\udd0d Legacy Code Explorer**: Understand large codebases\r\n- **\ud83d\udcd6 API Assistant**: Query technical documentation\r\n- **\ud83e\uddea Testing Helper**: Find relevant test patterns\r\n\r\n### \ud83c\udf93 **Educational & Research**\r\n- **\ud83d\udcda Study Assistant**: Query textbooks and notes\r\n- **\ud83d\udcdd Writing Helper**: Research paper analysis\r\n- **\ud83e\udde0 Learning Companion**: Personalized explanations\r\n- **\ud83d\udcca Data Analysis**: Explore datasets semantically\r\n\r\n> **\ud83d\udca1 [See Complete Examples](docs/15-examples.md)** - Production-ready applications\r\n\r\n---\r\n\r\n## \ud83d\udee0\ufe0f Contributing\r\n\r\nWe welcome contributions! Here's how to get started:\r\n\r\n```bash\r\n# 1. Fork and clone\r\ngit clone https://github.com/Kenosis01/TinyRag.git\r\ncd TinyRag\r\n\r\n# 2. Install development dependencies \r\npip install -e \".[all,dev]\"\r\n\r\n# 3. Run tests\r\npython -m pytest\r\n\r\n# 4. Make your changes and submit a PR!\r\n```\r\n\r\n### \ud83d\udccb **Development Setup**\r\n- **Python 3.7+** required\r\n- **Core dependencies**: sentence-transformers, requests, numpy\r\n- **Optional**: faiss-cpu, chromadb, PyPDF2, python-docx\r\n\r\n> **\ud83d\udd27 [Development Guide](CONTRIBUTING.md)** - Detailed contributor guidelines\r\n\r\n## \ud83e\udd1d Community & Support\r\n\r\n### \ud83d\udcde **Get Help**\r\n- **\ud83d\udcd6 [Complete Documentation](docs/README.md)** - Comprehensive guides\r\n- **\ud83d\udc1b [GitHub Issues](https://github.com/Kenosis01/TinyRag/issues)** - Bug reports & feature requests\r\n- **\ud83d\udcac [Discussions](https://github.com/Kenosis01/TinyRag/discussions)** - Community Q&A\r\n- **\ud83d\udccb [FAQ](docs/19-faq.md)** - Common questions answered\r\n\r\n### \ud83c\udf89 **Show Your Support**\r\n- \u2b50 **Star this repo** if TinyRag helps you!\r\n- \ud83d\udc26 **Share on Twitter** - spread the word\r\n- \u2615 **[Buy me a coffee](https://buymeacoffee.com/kenosis)** - support development\r\n- \ud83e\udd1d **Contribute** - help make TinyRag better\r\n\r\n---\r\n\r\n## \ud83d\udcc4 License\r\n\r\nMIT License - see [LICENSE](LICENSE) for details.\r\n\r\n---\r\n\r\n<div align=\"center\">\r\n\r\n**\ud83d\ude80 TinyRag - Making RAG Simple, Powerful, and Accessible! \ud83d\ude80**\r\n\r\n*Build intelligent search and Q&A systems in minutes, not hours*\r\n\r\n[](https://github.com/Kenosis01/TinyRag)\r\n[](https://pypi.org/project/tinyrag/)\r\n[](https://github.com/Kenosis01/TinyRag)\r\n\r\n</div>\r\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "A minimal Python library for Retrieval-Augmented Generation with codebase indexing and multiple vector store backends",
"version": "0.3.5",
"project_urls": {
"Bug Tracker": "https://github.com/Kenosis01/TinyRag/issues",
"Changelog": "https://github.com/Kenosis01/TinyRag/blob/main/CHANGELOG.md",
"Documentation": "https://github.com/Kenosis01/TinyRag#readme",
"Homepage": "https://github.com/Kenosis01/TinyRag",
"Repository": "https://github.com/Kenosis01/TinyRag.git"
},
"split_keywords": [
"rag",
" retrieval",
" augmented",
" generation",
" vector",
" database",
" embeddings",
" similarity",
" search",
" nlp",
" ai",
" machine-learning",
" codebase",
" code-indexing",
" function-search",
" code-analysis"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "e1364819a40f378b9d63708c339e04b452b1e690dc4812a03fa6edd64afa3de6",
"md5": "dfb1d0b39b076867cf0b1a9fd3eaee94",
"sha256": "d1db964d40b5d73fa400c0dfd51dee5b4fa3e8d770d3eb5e8fea01d808173297"
},
"downloads": -1,
"filename": "tinyrag-0.3.5-py3-none-any.whl",
"has_sig": false,
"md5_digest": "dfb1d0b39b076867cf0b1a9fd3eaee94",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7",
"size": 33289,
"upload_time": "2025-08-23T16:55:18",
"upload_time_iso_8601": "2025-08-23T16:55:18.594796Z",
"url": "https://files.pythonhosted.org/packages/e1/36/4819a40f378b9d63708c339e04b452b1e690dc4812a03fa6edd64afa3de6/tinyrag-0.3.5-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "385ae514d4e3dd7737e5e09adbb3b2a8cfc04ead1768bf2d2a5becebd93e4444",
"md5": "756aa7de32c1f4fcace3acbdf3d022b6",
"sha256": "c110ad632982c834f10eaffaddae9e52e9ecc60f875429f9fe00f186be240326"
},
"downloads": -1,
"filename": "tinyrag-0.3.5.tar.gz",
"has_sig": false,
"md5_digest": "756aa7de32c1f4fcace3acbdf3d022b6",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.7",
"size": 102210,
"upload_time": "2025-08-23T16:55:20",
"upload_time_iso_8601": "2025-08-23T16:55:20.115033Z",
"url": "https://files.pythonhosted.org/packages/38/5a/e514d4e3dd7737e5e09adbb3b2a8cfc04ead1768bf2d2a5becebd93e4444/tinyrag-0.3.5.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-23 16:55:20",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "Kenosis01",
"github_project": "TinyRag",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [
{
"name": "sentence-transformers",
"specs": []
},
{
"name": "requests",
"specs": []
},
{
"name": "numpy",
"specs": []
},
{
"name": "faiss-cpu",
"specs": []
},
{
"name": "scikit-learn",
"specs": []
},
{
"name": "chromadb",
"specs": []
},
{
"name": "PyPDF2",
"specs": []
},
{
"name": "python-docx",
"specs": []
},
{
"name": "pdfminer.six",
"specs": [
[
">=",
"20221105"
]
]
}
],
"lcname": "tinyrag"
}
JSON
