-
Notifications
You must be signed in to change notification settings - Fork 265
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
feat: add watsonx translation backend (#598)
- Loading branch information
1 parent
7b4eb29
commit f56a528
Showing
7 changed files
with
202 additions
and
2 deletions.
There are no files selected for viewing
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
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
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
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
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
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
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,153 @@ | ||
| # frozen_string_literal: true | ||
|
|
||
| require 'i18n/tasks/translators/base_translator' | ||
| require 'active_support/core_ext/string/filters' | ||
|
|
||
| module I18n::Tasks::Translators | ||
| class WatsonxTranslator < BaseTranslator | ||
| # max allowed texts per request | ||
| BATCH_SIZE = 50 | ||
| DEFAULT_SYSTEM_PROMPT = <<~PROMPT.squish | ||
| You are a helpful assistant that translates content from the %{from} locale | ||
| to the %{to} locale in an i18n locale array. | ||
| You always preserve the structure and formatting exactly as it is. | ||
| The array has a structured format and contains multiple strings. Your task is to translate | ||
| each of these strings and create a new array with the translated strings. | ||
| Reminder: | ||
| - Translate only the text, preserving the structure and formatting. | ||
| - Do not translate any URLs. | ||
| - Do not translate HTML tags like `<details>` and `<summary>`. | ||
| - HTML markups (enclosed in < and > characters) must not be changed under any circumstance. | ||
| - Variables (starting with %%{ and ending with }) must not be changed under any circumstance. | ||
| - Output only the result, without any additional information or comments. | ||
| PROMPT | ||
|
|
||
| def options_for_translate_values(from:, to:, **options) | ||
| options.merge( | ||
| from: from, | ||
| to: to | ||
| ) | ||
| end | ||
|
|
||
| def options_for_html | ||
| {} | ||
| end | ||
|
|
||
| def options_for_plain | ||
| {} | ||
| end | ||
|
|
||
| def no_results_error_message | ||
| I18n.t('i18n_tasks.watsonx_translate.errors.no_results') | ||
| end | ||
|
|
||
| private | ||
|
|
||
| def translator | ||
| @translator ||= WatsonxClient.new(key: api_key) | ||
| end | ||
|
|
||
| def api_key | ||
| @api_key ||= begin | ||
| key = @i18n_tasks.translation_config[:watsonx_api_key] | ||
| fail ::I18n::Tasks::CommandError, I18n.t('i18n_tasks.watsonx_translate.errors.no_api_key') if key.blank? | ||
|
|
||
| key | ||
| end | ||
| end | ||
|
|
||
| def project_id | ||
| @project_id ||= begin | ||
| project_id = @i18n_tasks.translation_config[:watsonx_project_id] | ||
| if project_id.blank? | ||
| fail ::I18n::Tasks::CommandError, | ||
| I18n.t('i18n_tasks.watsonx_translate.errors.no_project_id') | ||
| end | ||
|
|
||
| project_id | ||
| end | ||
| end | ||
|
|
||
| def model | ||
| @model ||= @i18n_tasks.translation_config[:watsonx_model].presence || 'meta-llama/llama-3-2-90b-vision-instruct' | ||
| end | ||
|
|
||
| def system_prompt | ||
| @system_prompt ||= @i18n_tasks.translation_config[:watsonx_system_prompt].presence || DEFAULT_SYSTEM_PROMPT | ||
| end | ||
|
|
||
| def translate_values(list, from:, to:) | ||
| results = [] | ||
|
|
||
| list.each_slice(BATCH_SIZE) do |batch| | ||
| translations = translate(batch, from, to) | ||
|
|
||
| results << JSON.parse(translations) | ||
| end | ||
|
|
||
| results.flatten | ||
| end | ||
|
|
||
| def translate(values, from, to) | ||
| prompt = [ | ||
| '<|eot_id|><|start_header_id|>system<|end_header_id|>', | ||
| format(system_prompt, from: from, to: to), | ||
| '<|eot_id|><|start_header_id|>user<|end_header_id|>Translate this array:', | ||
| "<|eot_id|><|start_header_id|>user<|end_header_id|>#{values.to_json}", | ||
| '<|eot_id|><|start_header_id|>assistant<|end_header_id|>' | ||
| ].join | ||
|
|
||
| response = translator.generate_text( | ||
| model_id: model, | ||
| project_id: project_id, | ||
| input: prompt, | ||
| parameters: { | ||
| decoding_method: :greedy, | ||
| max_new_tokens: 2048, | ||
| repetition_penalty: 1 | ||
| } | ||
| ) | ||
| response.dig('results', 0, 'generated_text') | ||
| end | ||
| end | ||
| end | ||
|
|
||
| class WatsonxClient | ||
| WATSONX_BASE_URL = 'https://us-south.ml.cloud.ibm.com/ml/' | ||
| IBM_CLOUD_IAM_URL = 'https://iam.cloud.ibm.com/identity/token' | ||
|
|
||
| def initialize(key:) | ||
| begin | ||
| require 'faraday' | ||
| rescue LoadError | ||
| raise ::I18n::Tasks::CommandError, "Add gem 'faraday' to your Gemfile to use this command" | ||
| end | ||
|
|
||
| @http = Faraday.new(url: WATSONX_BASE_URL) do |conn| | ||
| conn.use Faraday::Response::RaiseError | ||
| conn.request :json | ||
| conn.response :json | ||
| conn.options.timeout = 600 | ||
| conn.request :authorization, :Bearer, token(key) | ||
| end | ||
| end | ||
|
|
||
| def generate_text(**opts) | ||
| @http.post('v1/text/generation?version=2024-05-20', **opts).body | ||
| end | ||
|
|
||
| private | ||
|
|
||
| def token(key) | ||
| Faraday.new(url: IBM_CLOUD_IAM_URL) do |conn| | ||
| conn.use Faraday::Response::RaiseError | ||
| conn.response :json | ||
| conn.params = { | ||
| grant_type: 'urn:ibm:params:oauth:grant-type:apikey', | ||
| apikey: key | ||
| } | ||
| end.post.body['access_token'] | ||
| end | ||
| end |