https://github.com/lloydmeta/elastic-cloud-agent
Elastic Cloud AI agent
https://github.com/lloydmeta/elastic-cloud-agent
agentic-ai elastic langchain llm openapi
Last synced: 7 months ago
JSON representation
Elastic Cloud AI agent
- Host: GitHub
- URL: https://github.com/lloydmeta/elastic-cloud-agent
- Owner: lloydmeta
- Created: 2025-05-11T18:24:17.000Z (11 months ago)
- Default Branch: main
- Last Pushed: 2025-07-15T05:55:35.000Z (9 months ago)
- Last Synced: 2025-07-15T12:25:35.758Z (9 months ago)
- Topics: agentic-ai, elastic, langchain, llm, openapi
- Language: Python
- Homepage:
- Size: 241 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Elastic Cloud Agent
[](https://github.com/lloydmeta/elastic-cloud-agent/actions/workflows/test.yml)
An interactive chat agent that allows administrators to talk to and ask questions about Elastic Cloud. The agent can search for information and perform actions by consuming an OpenAPI specification.
## Features
- Interactive chat interface for Elastic Cloud administration
- Uses LangChain and OpenAI for LLM capabilities
- Consumes Elastic Cloud API via OpenAPI specification
- Performs web searches to find relevant information
- Easy configuration via environment variables
## Prerequisites
- [Poetry](https://python-poetry.org/docs/#installing-with-the-official-installer) for dependency management
- OpenAI API key
- Elastic Cloud account and API key
## Installation
1. Clone the repository:
2. Install dependencies using Poetry:
```bash
make install
```
3. Create a `.env` file by copying the example:
```bash
cp .env.example .env
```
4. Edit the `.env` file and fill in your API keys and configuration.
5. Place your Elastic Cloud OpenAPI specification in `data/elastic_cloud_api.json`.
## Usage
Start the application:
```bash
make run
```
This will launch an interactive chat interface where you can ask questions about Elastic Cloud or request actions.
## Development
- Format code: `make format`
- Run linters: `make lint`
- Run tests: `make test`
- Clean up cache files: `make clean`