Update the list of providers that support custom models

intento · Apr 16, 2020 · 452b861 · 452b861
1 parent 80874d2
commit 452b861
Show file tree

Hide file tree

Showing 3 changed files with 31 additions and 20 deletions.
diff --git a/README.md b/README.md
@@ -483,11 +483,11 @@ Response:
 
 #### Delegated credentials
 
-Some providers do not provide fixed static credentials like API-keys or username/password pair but require you to use temporary tokens instead (like Google Cloud Translation API (v3beta1) or Google AutoML). So it imposes some extra work when using your own credentials — you have to regenerate these temporary credentials by yourself and provide them with each request to Intento. You have to know when you need to regenerate a token, or we let you know when we cannot fulfill a request using a provided token (because it was expired), so you can catch this situation, regenerate a token by yourself and continue using Intento API.
+Some providers do not provide fixed static credentials like API-keys or username/password pair but require you to use temporary tokens instead (like Google Cloud Advanced Translation API or Google AutoML). So it imposes some extra work when using your own credentials — you have to regenerate these temporary credentials by yourself and provide them with each request to Intento. You have to know when you need to regenerate a token, or we let you know when we cannot fulfill a request using a provided token (because it was expired), so you can catch this situation, regenerate a token by yourself and continue using Intento API.
 
 It is not very handy, because some tokens expire just after an hour, so you have to regenerate them each hour. Even if this process can be automated it takes much extra work: you need to catch this particular situation, regenerate a token, resend a bunch of requests which happen to be called with the expired token. The situation becomes harder when you run large async jobs that could take more time than a token lifetime. In this situation a part of such request will fail, so you need to split your requests into smaller parts or resubmit failed tasks with a new token. It is painful.
 
-We provide a much more convenient and hassle-free way to work with temporary credentials. You can provide us with all the required information to generate temporary tokens. The fastest way to set up Google Cloud Translation API (v3beta1) and Google AutoML with Intento is our [Connected accounts Manager](https://console.inten.to/credentials).
+We provide a much more convenient and hassle-free way to work with temporary credentials. You can provide us with all the required information to generate temporary tokens. The fastest way to set up Google Cloud Advanced Translation API and Google AutoML with Intento is our [Connected accounts Manager](https://console.inten.to/credentials).
 
 Another option is to [delegate us the required credentials through the API][delegated_credentials.md], and we take care of the whole process, automatically regenerating tokens when it's needed and substituting an actual token in the request to a provider. You pass a credential id (which is constant now), and we do all the job with translating it to always-working tokens.
 
@@ -527,7 +527,7 @@ Response:
     "service": {
         "provider": {
             "id": "ai.text.translate.google.translate_api.v3",
-            "name": "Google Cloud Translation API (v3beta1)",
+            "name": "Google Cloud Advanced Translation API",
             "timing": { "provider": 0.788544 },
             "category": {
                 "id": "projects/xxx/locations/us-central1/models/zzzzzzzz"

diff --git a/ai.text.translate.md b/ai.text.translate.md
@@ -231,7 +231,7 @@ The response contains the translated text, service information and meta informat
     "service": {
         "provider": {
             "id": "ai.text.translate.google.translate_api.v3",
-            "name": "Google Cloud Translation API (v3beta1)",
+            "name": "Google Cloud Advanced Translation API",
             "timing": { "provider": 0.1 }
         }
     }
@@ -255,7 +255,7 @@ The response contains a list of the providers available for given constraints wi
     {
         "id": "ai.text.translate.google.translate_api.v3",
         "vendor": "Google Cloud",
-        "description": "Translation API (v3beta1)",
+        "description": "Advanced Translation API",
         "own_auth": true,
         "stock_model": true,
         "custom_model": true
@@ -326,7 +326,7 @@ Response:
     {
         "id": "ai.text.translate.google.translate_api.v3",
         "vendor": "Google Cloud",
-        "description": "Translation API (v3beta1)",
+        "description": "Advanced Translation API",
         "own_auth": true,
         "stock_model": true,
         "custom_model": false
@@ -596,18 +596,29 @@ Response:
 
 ### Using previously trained custom models
 
-Right now we support custom models for these providers:
-
-- (SMT) IBM Watson Language Translator Service (`ai.text.translate.ibm-language-translator`). This engine is deprecated and will no longer be available after October 4, 2018.
-- (SMT) Microsoft Translator API v2.0 (`ai.text.translate.microsoft.translator_text_api.3-0`). This engine is deprecated since April 30, 2018 and will be discontinued on April 30, 2019.
-- (NMT) IBM Watson Language Translator Service v3 (`ai.text.translate.ibm-language-translator-v3`).
-- (NMT) Microsoft Translator API v3.0 (`ai.text.translate.microsoft.translator_text_api.3-0`).
-- (NMT) Google Cloud Translation API (v3beta1) (`ai.text.translate.google.translate_api.v3`).
-- ModernMT Enterprise Edition (`ai.text.translate.modernmt.enterprise`).
-- Tilde Machine Translation API (`ai.text.translate.tilde.machine_translation_api`).
+Right now we support custom models for these 14 providers:
+
+1. Alibaba Cloud E-commerce Edition (`ai.text.translate.alibaba.machine_translation_api`).
+1. Google Cloud Advanced Translation API (`ai.text.translate.google.translate_api.v3`).
+1. Google Cloud AutoML Translation API (`ai.text.translate.google.automl_api.v1`).
+1. Google Cloud AutoML Translation API (v1beta1) (`ai.text.translate.google.automl_api.v1beta1`).
+1. Google Cloud Translation API (v3beta1) (`ai.text.translate.google.translate_api.v3beta1`).
+1. IBM Watson Language Translator Service v3 (`ai.text.translate.ibm-language-translator-v3`).
+1. Microsoft Translator API v2.0 (SMT) (`ai.text.translate.microsoft.translator_text_api.2-0`). This engine is deprecated since April 30, 2018 and will be discontinued on April 30, 2019.
+1. Microsoft Translator API v3.0 (`ai.text.translate.microsoft.translator_text_api.3-0`).
+1. ModernMT Human-in-the-loop (`ai.text.translate.modernmt.enterprise`).
+1. SDL BeGlobal Translate API (`ai.text.translate.sdl.beglobal_translate_api.4-0`).
+1. SDL Enterprise Translation Server (`ai.text.translate.sdl.enterprise_translation_server`).
+1. SYSTRAN PNMT API (`ai.text.translate.systran.pnmt`).
+1. Tilde Machine Translation API (`ai.text.translate.tilde.machine_translation_api`).
+1. Yandex Cloud Translate API v2 (`ai.text.translate.yandex.cloud-translate.v2`).
 
 More providers to come!
 
+Archived providers:
+
+- (SMT) IBM Watson Language Translator Service (`ai.text.translate.ibm-language-translator`). This engine is deprecated and will no longer be available after October 4, 2018.
+
 For using a custom model trained with these services just pass the model id in the `category` parameter with your [own credentials](https://github.com/intento/intento-api#using-a-service-provider-with-your-own-keys) (because other users do not have access to your models):
 
 ```sh
@@ -642,7 +653,7 @@ Response
     "service": {
         "provider": {
             "id": "ai.text.translate.google.translate_api.v3",
-            "name": "Google Cloud Translation API (v3beta1)",
+            "name": "Google Cloud Advanced Translation API",
             "timing": { "provider": 0.2 },
             "category": {
                 "id": "cccccccc-cccc-cccc-cccc-cccccccc"
@@ -691,7 +702,7 @@ Response
     "service": {
         "provider": {
             "id": "ai.text.translate.google.translate_api.v3",
-            "name": "Google Cloud Translation API (v3beta1)",
+            "name": "Google Cloud Advanced Translation API",
             "timing": { "provider": 0.2 },
             "glossary": {
                 "id": "projects/automl-123456/locations/us-central1/glossaries/my_EN_ES_Glossary"
@@ -741,7 +752,7 @@ The response contains the translated text with preserved formatting:
     "service": {
         "provider": {
             "id": "ai.text.translate.google.translate_api.v3",
-            "name": "Google Cloud Translation API (v3beta1)",
+            "name": "Google Cloud Advanced Translation API",
             "timing": { "provider": 0.17 }
         }
     }
@@ -890,7 +901,7 @@ Response:
     {
         "id": "ai.text.translate.google.translate_api.v3",
         "vendor": "Google Cloud",
-        "description": "Translation API (v3beta1)",
+        "description": "Advanced Translation API",
         "own_auth": true,
         "stock_model": false,
         "custom_model": true

diff --git a/providers.md b/providers.md
@@ -167,7 +167,7 @@ A provider supports training models (only on their side for now) and passing the
 
 ### `delegated_credentials`
 
-Intento supports connecting your accounts of Google Cloud Translation API (v3beta1) and Google AutoML providers. See more details in the [Connected Accounts section](./delegated_credentials.md). The fastest way to set up Google Cloud Translation API (v3beta1) and Google AutoML with Intento is our [Connected accounts Manager](https://console.inten.to/credentials).
+Intento supports connecting your accounts of Google Cloud Advanced Translation API and Google AutoML providers. See more details in the [Connected Accounts section](./delegated_credentials.md). The fastest way to set up Google Cloud Advanced Translation API and Google AutoML with Intento is our [Connected accounts Manager](https://console.inten.to/credentials).
 
 ### `integrated`