From 097563caa0a5e178c2f569c609f2c5d269e9ff0a Mon Sep 17 00:00:00 2001
From: 0xacx <99351112+0xacx@users.noreply.github.com>
Date: Tue, 28 Feb 2023 15:38:25 +0200
Subject: [PATCH] Update README.md

---
 README.md | 23 ++++++++++++++++++++++-
 1 file changed, 22 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 924e437..cb5e543 100644
--- a/README.md
+++ b/README.md
@@ -11,6 +11,7 @@ The script uses the `completions` endpoint and the `text-davinci-003` model for
 - Generate images from a text prompt
 - View your chat history
 - Chat context, GPT remembers previous chat questions and answers
+- Pass the input prompt with pipe, as a script parameter or normal chat mode
 - List all available OpenAI models 
 - Set OpenAI request parameters
 
@@ -18,6 +19,26 @@ The script uses the `completions` endpoint and the `text-davinci-003` model for
 
 ![Screenshot 2023-01-13 at 16 39 27](https://user-images.githubusercontent.com/99351112/212346562-ea568cce-2ca2-4b03-9ebc-ece8902c923d.png)
 
+Chat mode:
+```shell
+$ chatgpt
+Welcome to chatgpt. You can quit with 'exit'.
+
+Enter a prompt:
+
+```
+
+Using pipe:
+```shell
+echo "How to view running processes on Ubuntu?" | chatgpt
+```
+Using script arguments
+```shell
+chatgpt -p "What is the regex to match an email address?"
+```
+
+
+
 ## Getting Started
 
 ### Prerequisites
@@ -87,7 +108,7 @@ This script relies on curl for the requests to the api and jq to parse the json
       - max number of tokens, `--max-tokens`
       - image size, `-s` or `--size` (The sizes that are accepted by the OpenAI API are 256x256, 512x512, 1024x1024)
       - prompt, `p` or `--prompt` 
-      - prompt from a file, `--prompt-from-file`
+      - prompt from a file in your file system, `--prompt-from-file`
       
     To learn more about these parameters you can view the [API documentation](https://platform.openai.com/docs/api-reference/completions/create)