Update configs/prompts.toml
Browse files- configs/prompts.toml +10 -10
configs/prompts.toml
CHANGED
@@ -1,13 +1,20 @@
|
|
1 |
[summarization]
|
2 |
prompt = """
|
3 |
-
Below is the initial summary of our conversation.
|
4 |
-
Based on the given summary and the last conversation between you (assistant) and me (user), I want to update the summary.
|
5 |
-
|
6 |
**Summary:**
|
7 |
$previous_summary
|
8 |
|
9 |
**Last Conversation:**
|
10 |
$latest_conversation
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
|
12 |
Summary Guide:
|
13 |
* Do not rewrite the entire summary.
|
@@ -20,10 +27,3 @@ Summary Guide:
|
|
20 |
* Use markdown formatting to make the summary more readable (using bullet points, numbers are preferred).
|
21 |
* Do not seprate sections for previous and updated summaries.
|
22 |
"""
|
23 |
-
|
24 |
-
system_prompt = """
|
25 |
-
Consider yourself an expert at summarizing content with a high bar
|
26 |
-
for scientific rigor. However, when generating the summaries you
|
27 |
-
must follow the persona of a $persona. This persona will help set
|
28 |
-
the tone of the conversation.
|
29 |
-
"""
|
|
|
1 |
[summarization]
|
2 |
prompt = """
|
|
|
|
|
|
|
3 |
**Summary:**
|
4 |
$previous_summary
|
5 |
|
6 |
**Last Conversation:**
|
7 |
$latest_conversation
|
8 |
+
"""
|
9 |
+
|
10 |
+
system_prompt = """
|
11 |
+
Consider yourself an expert at summarizing content with a high bar
|
12 |
+
for scientific rigor. However, when generating the summaries you
|
13 |
+
must follow the persona of a $persona. This persona will help set
|
14 |
+
the tone of the conversation.
|
15 |
+
|
16 |
+
Based on the given summary and the last conversation between you (assistant) and me (user),
|
17 |
+
update the summary following the below summary guide.
|
18 |
|
19 |
Summary Guide:
|
20 |
* Do not rewrite the entire summary.
|
|
|
27 |
* Use markdown formatting to make the summary more readable (using bullet points, numbers are preferred).
|
28 |
* Do not seprate sections for previous and updated summaries.
|
29 |
"""
|
|
|
|
|
|
|
|
|
|
|
|
|
|