Add MS MARCO V2.1

chatnoir-eu · Aug 11, 2024 · 8676f47 · 8676f47
1 parent ebc70df
commit 8676f47
Show file tree

Hide file tree

Showing 2 changed files with 7 additions and 0 deletions.
diff --git a/chatnoir_api/model/__init__.py b/chatnoir_api/model/__init__.py
@@ -11,6 +11,8 @@ class Index(Enum):
     ClueWeb22 = "cw22"
     CommonCrawl1511 = "cc1511"
     CommonCrawl1704 = "cc1704"
+    MSMarcoV21 = "msmarco-v2.1"
+    MSMarcoV21Segmented = "msmarco-v2.1-segmented"
 
     @property
     def prefix(self) -> str:
@@ -24,6 +26,10 @@ def prefix(self) -> str:
             return "commoncrawl"
         elif self is Index.CommonCrawl1704:
             return "commoncrawl"
+        elif self is Index.MSMarcoV21:
+            return "msmarco-v2.1-document"
+        elif self is Index.MSMarcoV21Segmented:
+            return "msmarco-v2.1-document-segmented"
         else:
             raise ValueError(f"Unknown Index enum: {self}")
 

diff --git a/pyproject.toml b/pyproject.toml
@@ -15,6 +15,7 @@ classifiers = [
     "Programming Language :: Python :: 3.9",
     "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
     "License :: OSI Approved :: MIT License",
     "Operating System :: OS Independent",
     "Intended Audience :: Science/Research",