Tuana commited on
Commit
b09d26d
1 Parent(s): 37f8734

update to prompt and length

Browse files
Files changed (1) hide show
  1. utils/haystack.py +9 -10
utils/haystack.py CHANGED
@@ -14,25 +14,23 @@ def start_haystack():
14
  You may go into some detail about what topics they tend to like tweeting about. Please also mention their overall tone, for example: positive,
15
  negative, political, sarcastic or something else.
16
 
17
- Example:
18
 
19
  Twitter stream: Many people in our community asked how to utilize LLMs in their NLP pipelines and how to modify prompts for their tasks.…
20
  RT @deepset_ai: We use parts of news articles from The Guardian as documents and create custom prompt templates to categorize these article
21
 
22
- Voice: This person has lately been tweeting about NLP and LLMs. Their tweets have been in Enlish
23
-
24
- Example:
25
 
26
  Twitter stream: I've directed my team to set sharper rules on how we deal with unidentified objects.\n\nWe will inventory, improve ca…
27
  the incursion by China’s high-altitude balloon, we enhanced radar to pick up slower objects.\n \nBy doing so, w…
28
  I gave an update on the United States’ response to recent aerial objects.
29
 
30
- Voice: This person has lately been tweeting about an unidentified object and an incursion by China with a high-altitude baloon.
31
  They have been tweeting about the USA. They have had a political tone. They mostly post in English.
32
 
33
- Twitter stream: $tweets.
34
 
35
- Voice:
36
  """)
37
  return prompt_node, twitter_template
38
 
@@ -50,8 +48,9 @@ def query(username):
50
  response = requests.request("GET", url, headers = headers)
51
  twitter_stream = ""
52
  for tweet in response.json():
53
- twitter_stream += (tweet["text"])
54
- result = prompter.prompt(prompt_template=template, tweets=twitter_stream[0:4097])
55
- except:
 
56
  result = ["Please make sure you are providing a correct, public twitter accout"]
57
  return result
 
14
  You may go into some detail about what topics they tend to like tweeting about. Please also mention their overall tone, for example: positive,
15
  negative, political, sarcastic or something else.
16
 
17
+ Use the following format:
18
 
19
  Twitter stream: Many people in our community asked how to utilize LLMs in their NLP pipelines and how to modify prompts for their tasks.…
20
  RT @deepset_ai: We use parts of news articles from The Guardian as documents and create custom prompt templates to categorize these article
21
 
22
+ Summary: This person has lately been tweeting about NLP and LLMs. Their tweets have been in Enlish
 
 
23
 
24
  Twitter stream: I've directed my team to set sharper rules on how we deal with unidentified objects.\n\nWe will inventory, improve ca…
25
  the incursion by China’s high-altitude balloon, we enhanced radar to pick up slower objects.\n \nBy doing so, w…
26
  I gave an update on the United States’ response to recent aerial objects.
27
 
28
+ Summary: This person has lately been tweeting about an unidentified object and an incursion by China with a high-altitude baloon.
29
  They have been tweeting about the USA. They have had a political tone. They mostly post in English.
30
 
31
+ Twitter stream: $tweets
32
 
33
+ Summary:
34
  """)
35
  return prompt_node, twitter_template
36
 
 
48
  response = requests.request("GET", url, headers = headers)
49
  twitter_stream = ""
50
  for tweet in response.json():
51
+ twitter_stream += tweet["text"]
52
+ result = prompter.prompt(prompt_template=template, tweets=twitter_stream[0:10000])
53
+ except Exception as e:
54
+ print(e)
55
  result = ["Please make sure you are providing a correct, public twitter accout"]
56
  return result