You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+29-13Lines changed: 29 additions & 13 deletions
Original file line number
Diff line number
Diff line change
@@ -8,7 +8,6 @@
8
8
9
9
</div>
10
10
11
-
12
11
Example of using OpenAI with PyQt (Python cross-platform GUI toolkit)
13
12
14
13
This shows an example of using OpenAI with PyQt as a chatbot and using DALL-E or Stable Diffusion as a image generation tool.
@@ -21,24 +20,26 @@ If you want to study openai with Python-only good old desktop software, this is
21
20
22
21
The OpenAI model this package uses is the <ahref="https://platform.openai.com/docs/models/gpt-3-5">gpt-3.5-turbo</a> model(which is nearly as functional as <b>ChatGPT</b>) by default. You can use gpt-4 as well.
23
22
24
-
Latest model such as gpt-3.5-turbo-0613 is also available
25
-
26
-
Image generation feature(DALL-E and Stable Diffusion) available since v0.1.4.
23
+
Image generation feature(DALL-E and Stable Diffusion) is also available.
27
24
28
25
<b>Stable Diffusion</b> used [DreamStudio API](https://dreamstudio.ai/). This is not entirely free like stable-diffusion-webgui.
29
26
30
27
But this is very lightweight and more accessible. don't need CUDA, torch, expansive PC, anything.
31
28
32
29
This is using <b>sqlite</b> as a database.
33
30
34
-
You can select the model at the right side bar.
31
+
You can select the model and change each parameters of openai from the right side bar.
32
+
33
+
Also you can combine openai with llama-index feature to make gpt model answer your question based on information you had provided!
35
34
36
35
An internet connection is required.
37
36
37
+
If you have any questions or you want to make AI related software with PyQt or PySide, feel free to join Discord server of pyqt-openai.
38
+
38
39
## Table of Contents
39
40
*[Feature](#feature)
40
41
*[Requirements](#requirements)
41
-
*[Preview & Usage](#preview-usage)
42
+
*[Preview and Usage](#preview-and-usage)
42
43
*[How to Install](#how-to-install)
43
44
*[Troubleshooting](#troubleshooting)
44
45
*[Contact](#contact)
@@ -50,20 +51,22 @@ An internet connection is required.
50
51
* text streaming (enable by default, you can disable it)
51
52
* AI remembers past conversation
52
53
* support copy button
53
-
* conversation management
54
+
*<b>conversation management</b>
54
55
* add & delete conversations
55
56
* save conversations - SQlite db, text files compressed file, html files compressed file (both are zip)
56
57
* rename conversation
57
58
* everything above is saved in an SQLite database file named conv.db.
58
-
* support GPT-4 and every other models below GPT3
59
-
* support prompt generator (manageable, autosaved in database)
60
-
* support slash commands
59
+
* support controlling parameters(temperature, top_p, etc) just like openai playground
60
+
* support latest model such as <b>GPT-4-32k-0613</b>
61
+
* support <b>prompt generator</b> (manageable, autosaved in database)
62
+
* support <b>slash commands</b>
61
63
* support beginning and ending part of the prompt
62
-
* you can run this in background application
64
+
* you can <b>run this in background</b> application
63
65
* notification will pop up when response is generated
64
66
* you can make window stack on top or control its transparency
65
67
* image generation (DALL-E, Stable Diffusion with DreamStudio API)
66
68
* you can copy and download the image if you want. just hover the mouse cursor over the image.
69
+
* you can <b>fine-tune</b> openai with llama-index.
67
70
68
71
## Requirements
69
72
* qtpy - the package allowing you to write code that works with both PyQt and PySide
@@ -73,8 +76,11 @@ An internet connection is required.
73
76
* pyperclip - to copy prompt text from prompt generator
74
77
* stability_sdk - for Stable Diffusion
75
78
* jinja2 - for saving the conversation with html file
79
+
* llama-index - to fine-tune
80
+
81
+
## Preview and Usage
82
+
#### Note: A lot of previews below are not from latest version. It is slightly different with current GUI. So if you want to really know what this looks like, you can just see it for yourself :)
If you want to use this with your personal chatbot based on data you've given, then you can check the llamaindex checkbox and go to the tab, select the directory which includes .txt files containing the data.
0 commit comments