updated script to use the newest mutlilingual dicitonary RUN

README.md

@@ -22,9 +22,10 @@ The app does not use `aligned_all.vec`.
 
 ## Runtime configuration
 
-By default, the app downloads this artifact folder:
+By default, the app scans the stage 6 prefix and downloads the newest artifact
+folder that contains `config.json`:
 
-`s3://131-component-staging/multilingual-static-word-embeddings/stage-6/multilingual_space_20260521_133953.json`
+`s3://131-component-staging/multilingual-static-word-embeddings/stage-6/`
 
 Set these Hugging Face Space secrets for S3-compatible storage:
 
@@ -35,8 +36,8 @@ Set these Hugging Face Space secrets for S3-compatible storage:
 Optional environment overrides:
 
 - `SPACE_ARTIFACT_S3_URI`: exact artifact folder, for example
-  `s3://131-component-staging/multilingual-static-word-embeddings/stage-6/multilingual_space_20260521_133953.json`
-- `SPACE_ARTIFACT_S3_PREFIX`: prefix to scan for the newest `multilingual_space_*.json`
+  `s3://131-component-staging/multilingual-static-word-embeddings/stage-6/multilingual_dict_20260603_122323`
+- `SPACE_ARTIFACT_S3_PREFIX`: prefix to scan for the newest `multilingual_dict_*` or `multilingual_space_*.json`
 - `SPACE_DIR`: local artifact folder, useful for local testing
 - `ARTIFACT_CACHE_DIR`: local cache directory, default `/tmp/multilingual_space_artifacts`
 

app.py

@@ -22,10 +22,7 @@ DEFAULT_ARTIFACT_PREFIX = (
     "s3://131-component-staging/"
     "multilingual-static-word-embeddings/stage-6/"
 )
-DEFAULT_ARTIFACT_URI = (
-    DEFAULT_ARTIFACT_PREFIX + "multilingual_space_20260521_133953.json"
-)
-DEFAULT_LOCAL_SPACE = Path("multilingual_space_20260521_133953.json")
+DEFAULT_LOCAL_SPACE = Path("multilingual_dict_20260603_122323")
 DEFAULT_LANGS = ["de", "en", "fr", "lb"]
 REQUIRED_FILES = ("aligned_all.faiss", "all_metadata.jsonl", "config.json")
 CACHE_DIR = Path(os.getenv("ARTIFACT_CACHE_DIR", "/tmp/multilingual_space_artifacts"))
@@ -104,13 +101,12 @@ def latest_artifact_uri(client) -> str:
         return explicit
 
     prefix_override = os.getenv("SPACE_ARTIFACT_S3_PREFIX", "").strip()
-    if not prefix_override:
-        return DEFAULT_ARTIFACT_URI
-
-    prefix_uri = prefix_override
+    prefix_uri = prefix_override or DEFAULT_ARTIFACT_PREFIX
     bucket, prefix = parse_s3_uri(prefix_uri)
     prefix = prefix.rstrip("/") + "/"
-    pattern = re.compile(r"(.*multilingual_space_(\d{8}_\d{6})\.json)/config\.json$")
+    pattern = re.compile(
+        r"(.*multilingual_(?:dict|space)_(\d{8}_\d{6})(?:\.json)?)/config\.json$"
+    )
     candidates: list[tuple[str, str]] = []
 
     paginator = client.get_paginator("list_objects_v2")
@@ -122,11 +118,14 @@ def latest_artifact_uri(client) -> str:
 
     if not candidates:
         raise FileNotFoundError(
-            f"No multilingual_space_*.json/config.json found under {prefix_uri}"
+            f"No multilingual_dict_*/config.json or multilingual_space_*.json/config.json found under {prefix_uri}"
         )
 
-    _, key = sorted(candidates)[-1]
-    return f"s3://{bucket}/{key}"
+    # Run ids are timestamps: YYYYMMDD_HHMMSS. Lexicographic sort gives newest run.
+    run_id, key = sorted(candidates)[-1]
+    uri = f"s3://{bucket}/{key}"
+    print(f"Selected latest stage 6 artifact {run_id}: {uri}", file=sys.stderr)
+    return uri
 
 
 def local_cache_for_uri(uri: str) -> Path:
@@ -163,7 +162,9 @@ def find_space_dir() -> tuple[Path, str]:
     if DEFAULT_LOCAL_SPACE.exists():
         return DEFAULT_LOCAL_SPACE, str(DEFAULT_LOCAL_SPACE)
 
-    local_candidates = sorted(Path(".").glob("multilingual_space_*.json"))
+    local_candidates = sorted(
+        [*Path(".").glob("multilingual_dict_*"), *Path(".").glob("multilingual_space_*.json")]
+    )
     if local_candidates:
         return local_candidates[-1], str(local_candidates[-1])