Spaces:
Sleeping
Sleeping
John Graham Reynolds
commited on
Commit
Β·
312a2f7
1
Parent(s):
7100936
limit model to 10 turns
Browse files
app.py
CHANGED
@@ -16,7 +16,7 @@ if DATABRICKS_TOKEN is None:
|
|
16 |
raise ValueError("DATABRICKS_TOKEN environment variable must be set")
|
17 |
|
18 |
MODEL_AVATAR_URL= "./VU.jpeg"
|
19 |
-
MAX_CHAT_TURNS =
|
20 |
MSG_MAX_TURNS_EXCEEDED = f"Sorry! The Vanderbilt AI assistant playground is limited to {MAX_CHAT_TURNS} turns in a single history. Click the 'Clear Chat' button or refresh the page to start a new conversation."
|
21 |
# MSG_CLIPPED_AT_MAX_OUT_TOKENS = "Reached maximum output tokens for DBRX Playground"
|
22 |
|
@@ -37,7 +37,7 @@ terms like **EDW**, **HCERA**, **NRHA** and **thousands more**. (Ask the assista
|
|
37 |
click any of these examples to issue the corresponding query to the AI.
|
38 |
|
39 |
**Feedback**: Feedback is welcomed, encouraged, and invaluable! To give feedback in regards to one of the model's responses, click the **Give Feedback on Last Response** button just below
|
40 |
-
the user input bar. This allows you to provide either positive or negative feedback in regards to the model's most recent response. A
|
41 |
Please be sure to select either π or π before adding additional notes about your choice. Be as brief or as detailed as you like! Note that you are making a difference; this
|
42 |
feedback allows us to later improve this model for your usage through a training technique known as reinforced learning through human feedback. \n
|
43 |
|
|
|
16 |
raise ValueError("DATABRICKS_TOKEN environment variable must be set")
|
17 |
|
18 |
MODEL_AVATAR_URL= "./VU.jpeg"
|
19 |
+
MAX_CHAT_TURNS = 10 # limit this for preliminary testing
|
20 |
MSG_MAX_TURNS_EXCEEDED = f"Sorry! The Vanderbilt AI assistant playground is limited to {MAX_CHAT_TURNS} turns in a single history. Click the 'Clear Chat' button or refresh the page to start a new conversation."
|
21 |
# MSG_CLIPPED_AT_MAX_OUT_TOKENS = "Reached maximum output tokens for DBRX Playground"
|
22 |
|
|
|
37 |
click any of these examples to issue the corresponding query to the AI.
|
38 |
|
39 |
**Feedback**: Feedback is welcomed, encouraged, and invaluable! To give feedback in regards to one of the model's responses, click the **Give Feedback on Last Response** button just below
|
40 |
+
the user input bar. This allows you to provide either positive or negative feedback in regards to the model's most recent response. A **Feedback Form** will appear above the model's title.
|
41 |
Please be sure to select either π or π before adding additional notes about your choice. Be as brief or as detailed as you like! Note that you are making a difference; this
|
42 |
feedback allows us to later improve this model for your usage through a training technique known as reinforced learning through human feedback. \n
|
43 |
|