From 06657742e7c9c7ae9fa0ff3c969bbeb4508a79a6 Mon Sep 17 00:00:00 2001
From: Patrick Amadeus Irawan <patrickai0309@gmail.com>
Date: Fri, 31 May 2024 17:19:36 +0700
Subject: [PATCH] New schema: Add `chat` schema (#679)

* feat: add chat schema

* Update __init__.py

add whitespace at EoF

* Update chat.py

change the `role` field schema from ClassLabel to string
---
 seacrowd/utils/constants.py        |  4 ++++
 seacrowd/utils/schemas/__init__.py |  2 ++
 seacrowd/utils/schemas/chat.py     | 24 ++++++++++++++++++++++++
 3 files changed, 30 insertions(+)
 create mode 100644 seacrowd/utils/schemas/chat.py

diff --git a/seacrowd/utils/constants.py b/seacrowd/utils/constants.py
index fc7fc5aeb..54efa716b 100644
--- a/seacrowd/utils/constants.py
+++ b/seacrowd/utils/constants.py
@@ -10,6 +10,7 @@
     pairs_features_score,
     pairs_multi_features,
     qa_features,
+    chat_features,
     image_features,
     image_multi_features,
     imqa_features,
@@ -106,6 +107,7 @@ class Tasks(Enum):
     # Multi Text Generation
     DIALOGUE_SYSTEM = "DS"
     E2E_TASK_ORIENTED_DIALOGUE = "TOD"
+    MULTI_TURN_CONVERSATION = "MTC"
 
     # Self Supervised & Unsupervised Text
     PROMPTING = "PRT"
@@ -247,6 +249,7 @@ class Licenses(Enum):
     Tasks.TOKEN_LEVEL_LANGUAGE_IDENTIFICATION: "SEQ_LABEL",
     Tasks.COMMONSENSE_REASONING: "QA",
     Tasks.QUESTION_ANSWERING: "QA",
+    Tasks.MULTI_TURN_CONVERSATION: "CHAT",
     Tasks.QUESTION_ANSWERING_RETRIEVAL: "QA",
     Tasks.CONCEPT_ALIGNMENT_CLASSIFICATION: "PAIRS",
     Tasks.NEXT_SENTENCE_PREDICTION: "PAIRS",
@@ -315,6 +318,7 @@ class Licenses(Enum):
     "KB": kb_features,
     "TREE": tree_features,
     "QA": qa_features,
+    "CHAT": chat_features,
     "T2T": text2text_features,
     "TEXT": text_features(),
     "TEXT_MULTI": text_multi_features(),
diff --git a/seacrowd/utils/schemas/__init__.py b/seacrowd/utils/schemas/__init__.py
index ec4c035f8..5a30ac568 100644
--- a/seacrowd/utils/schemas/__init__.py
+++ b/seacrowd/utils/schemas/__init__.py
@@ -5,6 +5,7 @@
 from .pairs import features_with_continuous_label as pairs_features_score
 from .pairs_multilabel import features as pairs_multi_features
 from .qa import features as qa_features
+from .chat import features as chat_features
 from .image import features as image_features
 from .image import multi_features as image_multi_features
 from .imqa import features as imqa_features
@@ -28,6 +29,7 @@
     "pairs_features_score",
     "pairs_multi_features",
     "qa_features",
+    "chat_features",
     "image_features",
     "image_multi_features",
     "imqa_features",
diff --git a/seacrowd/utils/schemas/chat.py b/seacrowd/utils/schemas/chat.py
new file mode 100644
index 000000000..6443bb649
--- /dev/null
+++ b/seacrowd/utils/schemas/chat.py
@@ -0,0 +1,24 @@
+"""
+Conversational Chat Schema
+"""
+import datasets
+
+features = datasets.Features(
+    {
+        "id": datasets.Value("string"),
+        "input": datasets.Sequence({
+            "role": datasets.Value("string"),
+            "content": datasets.Value("string"),
+        }),
+        "output": datasets.Value("string"),
+
+        # the schema of 'meta' aren't specified either to allow some flexibility
+        "meta": {}
+
+        # notes on how to use this field of 'meta'
+        # you can choose two of options:
+        # 1. defining as empty dict if you don't think it's usable in `_generate_examples`, or
+        # 2. defining meta as dict of key with intended colname meta and its val with dataset.Features class
+        #    in `_info` Dataloader method then populate it with the values in `_general_examples` Dataloader method
+    }
+)