Use langcodes to match to_lang to chat_sample name.
#872
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
Change `chat_sample` handling: - Add function `get_chat_sample(to_lang)` to return chat_sample for requested language - Use `langcodes` to match `to_lang` to the closest available sample languages (within narrow margin) * `max_difference = 5` = `en-US` vs `en-GB` or `pt-BR` vs `pt-PT` - Cache `chat_sample[to_lang]` match as variable (only need to do `langcodes` matching once)
Merge `ollama` --> `custom_openai` migration
- Default: `deepseek-chat` - Option: `deepseek-reasoner` If `reasoning_content` provided: Print to `debug` logger. Add `ConfigGPT` setup.
- https://api-docs.deepseek.com/quick_start/token_usage#calculate-token-usage-offline Use `_assemble_prompts` function from current ChatGPT script ( zyddnys@c3bd2e9 ) - Modified to use true token count
SamuelWN
changed the title
chat_sample handlinglangcodes to match to_lang to chat_sample name.
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Outdated suggestions cannot be applied.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.
Change
chat_samplehandling:get_chat_sample(to_lang)to return chat_sample for requested languagelangcodesto matchto_langto the closest available sample languagesen-USvsen-GBandpt-BRvspt-PThave a scorelangcodesdistance of 5chat_sample[to_lang]match as variable (only need to dolangcodesmatching once)Provides additional flexibility & resilience for handling
chat_samplelanguage IDs (a user-provided value) .Additional changes:
_LANGUAGE_CODE_MAPintoGPTConfigchatgpt.py- Added English comments below Chinese comments