Spaces:
Sleeping
Sleeping
Commit
·
b88a317
1
Parent(s):
c11b68a
remove: verbosity
Browse files
app.py
CHANGED
@@ -345,27 +345,25 @@ Your job is to find out the timestamp of the best answer given by the interviewe
|
|
345 |
The way to know if there are multiple takes to a question is to see in the transcript if the same text is repeated, If not then number of takes is 1.
|
346 |
Question 1 should always be the introduction if the speaker has introduced themselves to find the best introduction time (Last timestamp is the best timestamp), Rest of questions should be in the order they were asked.
|
347 |
Return format is:
|
348 |
-
|
349 |
-
1. Question: question
|
350 |
Number of takes: number
|
351 |
-
Best Answer
|
352 |
For Example:
|
353 |
If the start time is 10:13 and end time is 10:18, the url will be:
|
354 |
{link_start}://roll.ai/colab/1234aq_12314/51234151?st=613&et=618
|
355 |
-
In the URL, make sure that after RSID there is ? and then rest of the fields are added via &.
|
356 |
"""
|
357 |
else:
|
358 |
prompt = f"""Given the transcript {transcript}, For All the speakers, short list all people, news, events, trends, and source that are discussed by speakers along with the start time of that topic and end time of that topic from the transcript. Rank all topics based on what would make for the best social clips. I need atleast 3 topics per speaker.
|
359 |
You should mention the Speaker Name first, then atleast 3 posts with their timestamps, and so on.
|
360 |
Return format is:
|
361 |
Speaker Name
|
362 |
-
1.Topic:
|
363 |
-
[Timestamp: start_time - end_time]({link_start}://{{origin}}/collab/{{cid}}/{{rsid}}?st={{start_time_in_sec}}&et={{end_time_in_sec}}"').
|
364 |
2....
|
365 |
For Example:
|
366 |
If the start time is 10:13 and end time is 10:18, the url will be:
|
367 |
{link_start}://roll.ai/colab/1234aq_12314/51234151?st=613&et=618
|
368 |
-
In the URL, make sure that after RSID there is ? and then rest of the fields are added via &.
|
369 |
"""
|
370 |
|
371 |
completion = client.chat.completions.create(
|
|
|
345 |
The way to know if there are multiple takes to a question is to see in the transcript if the same text is repeated, If not then number of takes is 1.
|
346 |
Question 1 should always be the introduction if the speaker has introduced themselves to find the best introduction time (Last timestamp is the best timestamp), Rest of questions should be in the order they were asked.
|
347 |
Return format is:
|
348 |
+
1. Question Title
|
|
|
349 |
Number of takes: number
|
350 |
+
[Best Answer Timestamp: start_time - end_time]({link_start}://{{origin}}/collab/{{cid}}/{{rsid}}?st={{start_time_in_sec}}&et={{end_time_in_sec}}"').
|
351 |
For Example:
|
352 |
If the start time is 10:13 and end time is 10:18, the url will be:
|
353 |
{link_start}://roll.ai/colab/1234aq_12314/51234151?st=613&et=618
|
354 |
+
In the URL, make sure that after RSID there is ? and then rest of the fields are added via &. Keep the answer less verbose and to the point.
|
355 |
"""
|
356 |
else:
|
357 |
prompt = f"""Given the transcript {transcript}, For All the speakers, short list all people, news, events, trends, and source that are discussed by speakers along with the start time of that topic and end time of that topic from the transcript. Rank all topics based on what would make for the best social clips. I need atleast 3 topics per speaker.
|
358 |
You should mention the Speaker Name first, then atleast 3 posts with their timestamps, and so on.
|
359 |
Return format is:
|
360 |
Speaker Name
|
361 |
+
1. [Topic Title, Timestamp: start_time - end_time]({link_start}://{{origin}}/collab/{{cid}}/{{rsid}}?st={{start_time_in_sec}}&et={{end_time_in_sec}}"').
|
|
|
362 |
2....
|
363 |
For Example:
|
364 |
If the start time is 10:13 and end time is 10:18, the url will be:
|
365 |
{link_start}://roll.ai/colab/1234aq_12314/51234151?st=613&et=618
|
366 |
+
In the URL, make sure that after RSID there is ? and then rest of the fields are added via &. Keep the answer less verbose and to the point.
|
367 |
"""
|
368 |
|
369 |
completion = client.chat.completions.create(
|