Skip to content

Latest commit

 

History

History
47 lines (25 loc) · 868 Bytes

README.md

File metadata and controls

47 lines (25 loc) · 868 Bytes
Raw

Cosmian AI Backend

Confidential computing backend to run language models

Usage

  • Build and install the app

  • Edit the config file (more info)

  • Run the app

CONFIG_PATH="./run/config.json" cosmian-ai-runner --port 5001
  • Create a supervisord service:

Sample config file: ./run/cosmian-ai-backend.conf

API endpoints

/summarize

Request:

  • doc: content of the document to summarize (String),

  • src_lang: optional source language of the text to summarize (String)

Response:

  • summary: result (String)

/translate

Request:

  • doc: content of the document to translate (String),

  • src_lang: source language of the text to translate (String),

  • tgt_lang: desired output language (String)

Response:

  • translation: result (String)