Skip to content

Fix ValueError on literal special-token strings in TiktokenCounter (#… #13016

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
ramashishmaurya wants to merge 1 commit into from
Closed

Fix ValueError on literal special-token strings in TiktokenCounter (#… #13016

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion haystack/token_counters/tiktoken_counter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -74,7 +74,7 @@ def count(self, messages: list[ChatMessage], tools: ToolsType | None = None) ->
if not messages and not tools:
return 0
self.warm_up()
text_tokens = len(self._encoder.encode(_rendered_conversation(messages) + _rendered_tools(tools)))
text_tokens = len(self._encoder.encode_ordinary(_rendered_conversation(messages) + _rendered_tools(tools)))
return text_tokens + _non_text_tokens(
messages, tokens_per_image=self.tokens_per_image, tokens_per_file=self.tokens_per_file
)
Expand Down
5 changes: 5 additions & 0 deletions test/token_counters/test_tiktoken_counter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -136,6 +136,11 @@ def test_nothing_to_measure_is_zero(self):
class TestTiktokenCounterIntegration:
"""Exercises the real encoder, which downloads its vocabulary on first use."""

def test_counts_literal_special_tokens(self):
counter = TiktokenCounter()
count = counter.count([ChatMessage.from_user("The manual documents <|endoftext|> as a literal marker.")])
assert count > 0

def test_counts_grow_with_content(self):
counter = TiktokenCounter()

Expand Down