Ready-made tasks and shared services for AI jobs.
@metreeca/llms provides ready-made @metreeca/flow tasks for putting language models to work in a pipeline: prompting a model, extracting structured records from free text, and embedding content for semantic retrieval. The tasks run under the @metreeca/gear job executor, which supplies the shared services they draw on, including the clients of the model providers they reach.
Pipelines are server-side workloads targeting Node.js 22 or later, relying on facilities such
as the filesystem, the process environment and fetch. The packages are not intended for the browser.
npm install @metreeca/gear # job executor and shared services
npm install @metreeca/llms # AI tasks and shared services
npm install @metreeca/llms-<provider> # model connectors, one package per provider
TypeScript consumers must use "moduleResolution": "nodenext"/"node16"/"bundler" in tsconfig.json.
The legacy "node" resolver is not supported.
Install the core package, then add a connector package for each model provider the pipeline reaches. Each connector package pulls in only the SDK its own provider needs. The @metreeca/gear job executor ships separately: install it directly to set up and run the jobs putting tasks and connectors to work.
| Package | Description |
|---|---|
| @metreeca/llms | AI tasks and shared services |
| @metreeca/llms-google | Google model connectors |
| @metreeca/llms-openai | OpenAI model connectors |
Each package documents its own API in its README and API reference; for complete coverage, see the API reference.
This project is licensed under the Apache 2.0 License – see LICENSE file for details.