Welcome to Rakam Systems’ Documentation!

Rakam Systems is a Python library designed to provide an integrated solution for creating Vector Stores and building Retrieval-Augmented Generation (RAG) systems. It offers a modular architecture to support search, content extraction, and large language model (LLM)-driven tasks, such as text classification and RAG-enabled prompt generation.

Check out the Usage section for further information, including how to Installation the project.

Note

This project is under active development.

Contents

Documentation Contents

• Usage
  • Installation
  • Creating Vector Stores
  • Retrieval-Augmented Generation (RAG)
  • Content Extraction
  • Node Processing
  • Classification with Vector Stores
• API
  • Core Module
  • Vector Store Module
  • Agents Module
  • LLM Module
  • Node Processor Module
  • Data Processor Module
  • Tutorial: Hands-on with Rakam Systems

---

Key Features

• Vector Store Management: Create, manage, and search through vector stores using embeddings for efficient retrieval.

• Retrieval-Augmented Generation (RAG): Combines vector store retrieval and large language model (LLM) generation.

• Content Extraction: Extracts content from various file formats such as PDF, URLs, and JSON files.

• Node Processing: Processes text data for optimized storage and retrieval.

• Modular Action-Based Agents: Supports actions like query classification and custom RAG generation using agents.

---

Installation

Before getting started, ensure you have installed the necessary dependencies. See the installation section for instructions.

---

Usage Guide

This library supports a variety of operations, including:

• Creating and managing Vector Stores for fast, vector-based content retrieval.

• Using Retrieval-Augmented Generation (RAG) to generate LLM-based responses.

• Extracting content from PDFs, URLs, and JSON files for processing.

• Processing content into nodes for efficient querying and storage.

Refer to the Usage section for detailed examples and code snippets on how to use these features.

---

Contributing

We welcome contributions! Check out the contributing section to get started.

---

License

This project is licensed under the MIT License.

---

Support

For any issues, questions, or suggestions, please contact mohammed@rakam.ai.