Rakam Systems
Rakam Systems is a platform designed to industrialize the construction, deployment, and operation of enterprise-grade AI systems with a focus on quality, scalability, and production-readiness.
Overview
Rakam Systems was born from an internal need at Rakam AI. For every new AI project, teams faced recurring technical challenges: collecting test data, evaluating quality, orchestrating components, configuring cloud infrastructure, and ensuring regulatory compliance. Rather than rebuilding these elements each time, Rakam decided to standardize and automate the entire AI production pipeline.
Why Rakam Systems
- State-of-the-Art Technology: FastAPI, Pydantic AI, FAISS, pgvector, Sentence Transformers, OpenAI, Mistral AI
- Production-First: Type safety, structured data exchange, scalable architecture, Docker templates
- Open Source: Transparent design, community-driven, standard tooling
Core Components
Rakam Systems provides modular, independently installable packages:
| Package | Description |
|---|---|
rakam-systems-core |
Foundational interfaces and utilities required by all other packages |
rakam-systems-agent |
AI agent implementations with multi-LLM support and tool integration |
rakam-systems-vectorstore |
Vector storage and document processing for semantic search and RAG |
rakam-systems-tools |
Evaluation tools, cloud storage utilities, and monitoring |
rakam-systems-cli |
Command-line interface for running evaluations and tracking quality |
Installation
Install all packages
pip install rakam-systems
Install specific packages
# Core only (required by all other packages)
pip install rakam-systems-core
# Agent package
pip install rakam-systems-agent[all]
# Vectorstore package
pip install rakam-systems-vectorstore[all]
# Tools package (evaluation, S3 utilities)
pip install rakam-systems-tools
# CLI
pip install rakam-systems-cli
# Agent + Vectorstore (for RAG applications)
pip install rakam-systems-agent[all] rakam-systems-vectorstore[all]
Requirements
- Python 3.10 or higher
Use Cases
With Rakam Systems, you can build:
- Retrieval-Augmented Generation (RAG) Systems: Combine vector retrieval with LLM prompt generation
- Agent Systems: Create modular agents that perform specific tasks using LLMs
- Chained Gen AI Systems: Chain multiple AI tasks for complex workflows
- Search Engines: Semantic search over documents using fine-tuned embeddings
- Any Custom AI System: Use components to create any AI solution tailored to your needs
Documentation
Full documentation is available in the docs/ directory:
Contributing
We welcome contributions! To contribute:
- Fork the repository and clone it locally.
- Create a feature branch:
git checkout -b feature-branch - Install the package(s) you are working on:
cd <package-dir> uv sync --all-extras --dev
- Make your changes and run tests:
uv run pytest -v - Commit with a meaningful message and submit a pull request.
For more details, see Contributing.
License
This project is licensed under the Apache-2.0 license.
Support
For any issues, questions, or suggestions, please contact mohammed@rakam.ai or open an issue on GitHub.
2 maintainers
Release files for rakam-systems 0.3.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| rakam_systems-0.3.2.tar.gz | 2.8 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| rakam_systems-0.3.2-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 6.2 kB
Release files / rakam_systems-0.3.2.tar.gz
| Download URL | rakam_systems-0.3.2.tar.gz |
|---|---|
| Size | 2.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
bdd784c01fbff6f2b948a746fefd7d601b91102d7ed0089c0fa5f7adc93ad88d
|
|
BLAKE2b-256 checksum How to use checksums |
cf7540423fdc3371ccd5a957e28ee6ad53fac1193db8ddb267379c95cdc16e7d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.11.3 {"installer":{"name":"uv","version":"0.11.3","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Release files / rakam_systems-0.3.2-py3-none-any.whl
| Download URL | rakam_systems-0.3.2-py3-none-any.whl |
|---|---|
| Size | 3.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
3a5fc251efbe297ce1e241adf582ca55bc4ab74973b5432bc14ce0f98536c7f7
|
|
BLAKE2b-256 checksum How to use checksums |
eb931d72efcd84bfffe8bb83514b00140021fae6f12ea5138a61e26b525da99c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.11.3 {"installer":{"name":"uv","version":"0.11.3","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
