Spaces:
Build error
Build error
README update for streamlit deployment + development
Browse files
README.md
CHANGED
@@ -4,7 +4,14 @@ This application demonstrates how to setup a simple ChatBot with [Azure OpenAI](
|
|
4 |
|
5 |
The ChatBot enables you to talk with your own data - in this case, to learn about [André's research](https://scholar.google.com/citations?user=U20zUHQAAAAJ).
|
6 |
|
7 |
-
##
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
|
9 |
These instructions were tested on a MacBook Pro with M2 chip running macOS 13.6 Ventura with `Python 3.9.6`.
|
10 |
|
@@ -15,35 +22,23 @@ source venv/bin/activate
|
|
15 |
pip install -r requirements.txt
|
16 |
```
|
17 |
|
18 |
-
2.
|
19 |
-
```
|
20 |
-
export OPENAI_API_KEY=<insert key here>
|
21 |
-
```
|
22 |
-
|
23 |
-
3. Create the `config.json` file and fill in the relevant info:
|
24 |
```
|
25 |
-
|
26 |
-
|
27 |
-
|
28 |
-
|
29 |
-
|
30 |
-
|
31 |
-
}
|
32 |
```
|
33 |
|
34 |
-
|
35 |
```
|
36 |
streamlit run app.py
|
37 |
```
|
38 |
|
39 |
A Streamlit browser window should automatically open. If not, the app can be accessed at `http://localhost:8501`
|
40 |
|
41 |
-
## Demonstration
|
42 |
-
|
43 |
-
Below is a snapshot on how the UI should look. A live demo may be made openly available in the future.
|
44 |
-
|
45 |
-
<img width="800" alt="Screenshot 2023-10-18 at 13 06 51" src="https://github.com/andreped/chatbot-streamlit-demo/assets/29090665/0e367153-9f0e-48d6-8059-dd060f917a97">
|
46 |
-
|
47 |
## Disclaimer
|
48 |
|
49 |
Only public PDFs were used for this demonstration. Some of André's research is sadly behind a paywall and thus we have chosen not to include the PDFs in this demo to avoid copyright issues.
|
|
|
4 |
|
5 |
The ChatBot enables you to talk with your own data - in this case, to learn about [André's research](https://scholar.google.com/citations?user=U20zUHQAAAAJ).
|
6 |
|
7 |
+
## Demo
|
8 |
+
|
9 |
+
The demo is hosted live on Streamlit at `https://chatbot-app-demo.streamlit.app`. A snapshot of the UI can be seen below:
|
10 |
+
|
11 |
+
|
12 |
+
## Development
|
13 |
+
|
14 |
+
If you wish to play around with the app locally, it requires that you provide OpenAI API key and all that fun stuff yourself.
|
15 |
|
16 |
These instructions were tested on a MacBook Pro with M2 chip running macOS 13.6 Ventura with `Python 3.9.6`.
|
17 |
|
|
|
22 |
pip install -r requirements.txt
|
23 |
```
|
24 |
|
25 |
+
2. Create the secrets file at `.streamlit/secrets.toml` file and fill in the relevant info:
|
|
|
|
|
|
|
|
|
|
|
26 |
```
|
27 |
+
OPENAI_API_KEY = "3cc19a1c875749c18c5e5d5a45a08f90"
|
28 |
+
CHATGPT_MODEL = "<insert model name>"
|
29 |
+
OPENAI_API_BASE = "https://<insert-openai-service-name>.openai.azure.com"
|
30 |
+
OPENAI_API_VERSION = "<insert version>"
|
31 |
+
ENGINE = "<insert deployment model name>"
|
32 |
+
ENGINE_EMBEDDING = "<insert deployment embedding name>"
|
|
|
33 |
```
|
34 |
|
35 |
+
3. Launch the app:
|
36 |
```
|
37 |
streamlit run app.py
|
38 |
```
|
39 |
|
40 |
A Streamlit browser window should automatically open. If not, the app can be accessed at `http://localhost:8501`
|
41 |
|
|
|
|
|
|
|
|
|
|
|
|
|
42 |
## Disclaimer
|
43 |
|
44 |
Only public PDFs were used for this demonstration. Some of André's research is sadly behind a paywall and thus we have chosen not to include the PDFs in this demo to avoid copyright issues.
|