https://github.com/oramasearch/oramacore
OramaCore is the complete runtime you need for your projects, answer engines, copilots, and search. It includes a fully-fledged full-text search engine, vector database, LLM interface, and many more utilities.
https://github.com/oramasearch/oramacore
fulltext-search inference llms vector-database vector-search
Last synced: 5 months ago
JSON representation
OramaCore is the complete runtime you need for your projects, answer engines, copilots, and search. It includes a fully-fledged full-text search engine, vector database, LLM interface, and many more utilities.
- Host: GitHub
- URL: https://github.com/oramasearch/oramacore
- Owner: oramasearch
- License: agpl-3.0
- Created: 2024-10-24T07:31:27.000Z (almost 2 years ago)
- Default Branch: develop
- Last Pushed: 2026-02-16T13:20:00.000Z (6 months ago)
- Last Synced: 2026-02-16T19:56:19.888Z (6 months ago)
- Topics: fulltext-search, inference, llms, vector-database, vector-search
- Language: Rust
- Homepage: https://docs.orama.com/docs/cloud
- Size: 30 MB
- Stars: 230
- Watchers: 3
- Forks: 19
- Open Issues: 10
-
Metadata Files:
- Readme: README.md
- License: LICENSE.md
Awesome Lists containing this project
README
**OramaCore** is the AI runtime you need for your projects, answer engines,
copilots, and search.
It includes a fully-fledged full-text search engine, vector database, LLM
interface with action planning and reasoning, a JavaScript runtime to write and
run your own custom agents on your data, and many more utilities.
## Getting Started
The absolute easier way to get started is by following the
[docker-compose.yml](./docker-compose.yml) file that you can find in this
repository.
You can either clone the entire repo or setup `oramasearch/oramacore:latest` as
image in your `docker-compose.yml` file under the `oramacore` service.
Then compile your
[configuration file](https://docs.oramacore.com/docs/guide/configuration) and
run it:
```sh
docker compose up
```
This will create the following architecture, allowing you to perform
high-performance RAG with little to zero configuration.
An NVIDIA GPU is highly recommended for running the application. For production
usage, we recommend using minimum one NVIDIA A100. Optimal configuration would
include four NVIDIA H100.
## Available Dockerfiles
Depending on your machine, you may want to use different Docker images.
| Application | CPU/GPU | Docker image |
| ------------- | ------------------------------------ | ------------------------------------------------------------------------------------------------------- |
| **OramaCore** | X86_64 | [`oramasearch/oramacore`](https://hub.docker.com/r/oramasearch/oramacore) |
| **OramaCore** | ARM64 (Mac M series for example) | [`oramasearch/oramacore-arm64`](https://hub.docker.com/r/oramasearch/oramacore-arm64) |
| **AI Server** | Any CPU architecture, no CUDA access | [`oramasearch/oramacore-ai-server`](https://hub.docker.com/r/oramasearch/oramacore-ai-server) |
| **AI Server** | Any CPU architecture, CUDA available | [`oramasearch/oramacore-ai-server-cuda`](https://hub.docker.com/r/oramasearch/oramacore-ai-server-cuda) |
## Using the JavaScript SDK
You can install the official JavaScript SDK with npm:
```sh
npm i @orama/core
```
Then, you can start by creating a collection (a database index) with all of the
data you want to perform AI search & experiences on:
```js
import { OramaCoreManager } from "@orama/core";
const orama = new OramaCoreManager({
url: "http://localhost:8080",
masterAPIKey: "", // The master API key set in your config file
});
const newCollection = await orama.createCollection({
id: "products",
writeAPIKey: "my-write-api-key", // A custom API key to perform write operations on your collection
readAPIKey: "my-read-api-key", // A custom API key to perform read operations on your collection
});
```
Then, insert some data:
```js
import { CollectionManager } from "@orama/core";
const collection = new CollectionManager({
url: "http://localhost:8080",
collectionID: "",
writeAPIKey: "",
});
// You can insert a single document
await collection.insert({
title: "My first document",
content: "This is the content of my first document.",
});
// Or you can insert multiple documents by passing an array of objects
await collection.insert([
{
title: "My first document",
content: "This is the content of my first document.",
},
{
title: "My second document",
content: "This is the content of my second document.",
},
]);
```
OramaCore will automatically generate highly optimized embeddings for you and
will store them inside its built-in vector database.
Now you can perform vector, hybrid, full-text search, or let OramaCore decide
which one is best for your specific query:
```js
import { CollectionManager } from "@orama/core";
const collection = new CollectionManager({
url: "http://localhost:8080",
collectionID: "",
readAPIKey: "",
});
const results = await collection.search({
term: "The quick brown fox",
mode: "auto", // can be "fulltext", "vector", "hybrid", or "auto"
});
```
You can also perform **Answer Sessions** as you'd do on **Perplexity** or
**SearchGPT**, but on your own data!
```js
import { CollectionManager } from "@orama/core";
const collection = new CollectionManager({
url: "http://localhost:8080",
collectionID: "",
readAPIKey: "",
});
const answerSession = collection.createAnswerSession({
initialMessages: [
{
role: "user",
content: "How do I install OramaCore?",
},
{
role: "assistant",
content:
"You can install OramaCore by pulling the oramasearch/oramacore:latest Docker image",
},
],
events: {
onStateChange(state) {
console.log("State changed:", state);
},
},
});
```
Read more on the [official documentation](https://docs.oramacore.com/docs).
## License
[AGPLv3](/LICENSE.md)