Improve token counter to handle more response types #15501
Merged
Conversation
This file contains hidden or 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
dosubot
bot
added
the
size:M
dosubot
bot
added
size:L
nerdai
approved these changes
Aug 20, 2024
Comment on lines
+35
to
+36
| possible_input_keys = ("prompt_tokens", "input_tokens") | ||
| possible_output_keys = ("completion_tokens", "output_tokens") |
There was a problem hiding this comment.
Looks like Anthropic uses input_tokens and output_tokens.
vinthree
reviewed
Aug 21, 2024
| response: Union["CompletionResponse", "ChatResponse"] | ||
| ) -> Tuple[int, int]: | ||
| """Get the token counts from a raw response.""" | ||
| usage = response.raw.get("usage", {}) |
There was a problem hiding this comment.
This will error out saying the following.
'ChatCompletion' object has no attribute 'get'
We will have to access the usage attribute like
response.raw.usage
There was a problem hiding this comment.
We can just model dump the raw response if its not already a dict
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Outdated suggestions cannot be applied.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.
APIs like anthropic may have a slightly different naming structure for pulling out token counts
imo longer term, this logic should probably be specific to the LLM class, but this solves some common issues