fix (#90) split text if token larger than 4096 #106
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
should fix #90 |
jeffery9
changed the title
jeffery9
changed the title
yihong0618
reviewed
Mar 10, 2023
Comment on lines
22
to
106
|
|
||
| message_log = [ | ||
| { | ||
| "role": "user", | ||
| # english prompt here to save tokens | ||
| "content": f"Please help me to translate,`{text}` to {self.language}, please return only translated content not include the origin text", | ||
| } | ||
| ] | ||
| count_tokens = num_tokens_from_messages(message_log) | ||
| consumed_tokens = 0 | ||
| t_text = "" | ||
| if count_tokens > 4000: | ||
| print("too long!") | ||
|
|
||
| splits = count_tokens // 4000 + 1 | ||
|
|
||
| text_list = text.split(".") | ||
| sub_text = "" | ||
| t_sub_text = "" | ||
| for n in range(splits): | ||
| text_segment = text_list[n * splits : (n + 1) * splits] | ||
| sub_text = ".".join(text_segment) | ||
| print(sub_text) | ||
|
|
||
| completion = openai.ChatCompletion.create( | ||
| model="gpt-3.5-turbo", | ||
| messages=[ | ||
| { | ||
| "role": "user", | ||
| # english prompt here to save tokens | ||
| "content": f"Please help me to translate,`{sub_text}` to {self.language}, please return only translated content not include the origin text", | ||
| } | ||
| ], | ||
| ) | ||
| t_sub_text = ( | ||
| completion["choices"][0] | ||
| .get("message") | ||
| .get("content") | ||
| .encode("utf8") | ||
| .decode() | ||
| ) | ||
| print(t_sub_text) | ||
| consumed_tokens += completion["usage"]["prompt_tokens"] | ||
|
|
||
| t_text = t_text + t_sub_text | ||
|
|
||
| else: | ||
| try: | ||
| completion = openai.ChatCompletion.create( | ||
| model="gpt-3.5-turbo", | ||
| messages=[ | ||
| { | ||
| "role": "user", | ||
| # english prompt here to save tokens | ||
| "content": f"Please help me to translate,`{text}` to {self.language}, please return only translated content not include the origin text", | ||
| } | ||
| ], | ||
| ) | ||
| t_text = ( | ||
| completion["choices"][0] | ||
| .get("message") | ||
| .get("content") | ||
| .encode("utf8") | ||
| .decode() | ||
| ) | ||
| consumed_tokens += completion["usage"]["prompt_tokens"] | ||
|
|
||
| except Exception as e: | ||
| # TIME LIMIT for open api please pay | ||
| key_len = self.key.count(",") + 1 | ||
| sleep_time = int(60 / key_len) | ||
| time.sleep(sleep_time) | ||
| print(e, f"will sleep {sleep_time} seconds") | ||
| self.rotate_key() | ||
| completion = openai.ChatCompletion.create( | ||
| model="gpt-3.5-turbo", | ||
| messages=[ | ||
| { | ||
| "role": "user", | ||
| "content": f"Please help me to translate,`{text}` to {self.language}, please return only translated content not include the origin text", | ||
| } | ||
| ], | ||
| ) | ||
| t_text = ( | ||
| completion["choices"][0] | ||
| .get("message") | ||
| .get("content") | ||
| .encode("utf8") | ||
| .decode() | ||
| ) | ||
| consumed_tokens += completion["usage"]["prompt_tokens"] | ||
|
|
||
| print(t_text) | ||
| print(f"{consumed_tokens} prompt tokens used.") |
There was a problem hiding this comment.
this functions is too long let's split it
|
have passed ' black . --check' local, but not pass ci. |
|
pip insall -U black |
already formatted. |
|
no worry I will take a look tonight or tomorrow. |
Merged
wayhome
pushed a commit
to wayhome/bilingual_book_maker
that referenced
this pull request
Aug 29, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
split text when token larger than the quota