https://github.com/NumexaHQ/frugal
⚡️ Transform AI/ML operations: Transparency, Control and Cost Optimization. ⚡️
https://github.com/NumexaHQ/frugal
ai aiops cost-optimization embeddings gpt gpt-4 hacktoberfest llm llmops logging ml models monitoring observability openai resource-management resource-optimization vectordatabase
Last synced: 3 months ago
JSON representation
⚡️ Transform AI/ML operations: Transparency, Control and Cost Optimization. ⚡️
- Host: GitHub
- URL: https://github.com/NumexaHQ/frugal
- Owner: NumexaHQ
- License: apache-2.0
- Created: 2023-08-23T18:48:49.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2023-10-08T10:11:02.000Z (almost 2 years ago)
- Last Synced: 2024-01-29T11:36:22.343Z (over 1 year ago)
- Topics: ai, aiops, cost-optimization, embeddings, gpt, gpt-4, hacktoberfest, llm, llmops, logging, ml, models, monitoring, observability, openai, resource-management, resource-optimization, vectordatabase
- Language: JavaScript
- Homepage: https://docs.numexa.io
- Size: 2.17 MB
- Stars: 16
- Watchers: 1
- Forks: 1
- Open Issues: 9
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-vector-databases - frugal - A platform focused on transforming AI/ML operations with transparency, control, and cost optimization, including support for vector database tasks. ([Read more](/details/frugal.md)) `open-source` `AI` `ML` `vector database` (Open Sources)
README
Numexa
🚀 An open-source Cost & Resource Optimization Platform for LLMs. Be Frugal! 💰
[](https://app.numexa.io)
[](https://discord.gg/XdYtneTJaE)
[](https://docs.numexa.io/)## Introduction
Numexa is an AI-driven cost and resource optimization tool designed to enhance operational efficiency. It achieves this by leveraging contextual insights derived from usage metrics. Numexa employs cutting-edge techniques such as intelligent caching and data retrieval, harnessing the power of vector databases to streamline operations. Explore how Numexa can revolutionize your resource management and cost-saving endeavors.
## Features
- 📝 Model agnostic functionality records unlimited requests from various providers like OpenAI, Cohere, Anthropic and more.
- 📋 Model management
- 🔔 Alerting & Notification with predefined policies, like error rate, threshold, cost, etc.
- 💾 Caching, Custom Rate Limits, and Retries,
- 📊 Track costs and latencies by users, applications, and endpoints
- 🔜 (Coming soon) Intellegient caching and data retrieval
- 🔜 (Coming soon) Cost and resource optimization
# Development Setup 💻
### Prerequisites
Before you begin, ensure you have the following installed on your system:- **Git**: [Installation Guide](https://git-scm.com/book/en/v2/Getting-Started-Installing-Git)
- **Docker**: [Installation Guide](https://docs.docker.com/get-docker/)
- **Docker Compose**: [Installation Guide](https://docs.docker.com/compose/install/)
- **Make**: [Installation Guide](https://www.gnu.org/software/make/)### Getting Started
1. **Clone the Repository:**
```bash
git clone
cd2. **Build and Start the Services:**
Run the following commands to build and start the project services
```bash
make all
docker compose -f docker-compose.dev.yaml up -d
3. **Verify Services:**
After running the above commands, your project services should be up and running. You can verify this by checking the logs# Community 🤝
Join our [#Discord](https://discord.gg/mVBMKVCv) or drop email at hello@numexa.io