From 3f1bfba718b1192b4c1ea409ae5d7a86cc5167a8 Mon Sep 17 00:00:00 2001 From: Damian Stewart Date: Fri, 12 May 2023 19:37:49 +0200 Subject: [PATCH] Clarify how to start server.py with multimodal API support (#2025) --- extensions/multimodal/README.md | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/extensions/multimodal/README.md b/extensions/multimodal/README.md index 24996b3b..0f515ae6 100644 --- a/extensions/multimodal/README.md +++ b/extensions/multimodal/README.md @@ -57,7 +57,10 @@ This extension uses the following parameters (from `settings.json`): ## Usage through API -You can run the multimodal inference through API, by inputting the images to prompt. Images are embedded like so: `f''`, where `img_str` is base-64 jpeg data. Python example: +You can run the multimodal inference through API, by inputting the images to prompt. Images are embedded like so: `f''`, where `img_str` is base-64 jpeg data. Note that you will need to launch `server.py` with the arguments `--api --extensions multimodal`. + +Python example: + ```Python import base64 import requests