jina name

configs/datasets.yaml

@@ -5,7 +5,7 @@ DEFAULT:
     log_dir: ./log
     # embedding: sentence-transformers/all-MiniLM-L6-v2
     # embedding: BAAI/llm-embedder
-    embedding: jina-embeddings-v3
+    embedding: jinaai/jina-embeddings-v3
     embedding_task: text-matching # ONLY FOR JINA_v3, retrieval.passage, text-matching, retrieval.query
     embedding_database: text-matching # ONLY FOR JINA_v3, retrieval.passage, text-matching, retrieval.query
 
@@ -39,4 +39,4 @@ RETRIEVE:
     s_summary: 0.0
     s_abstract: 0.0
     similarity_threshold: 0.95
-    # similarity_threshold: 0.55
+    # similarity_threshold: 0.55

src/paper_manager.py

@@ -664,7 +664,7 @@ class PaperManager:
         postfix_set = {
             "sentence-transformers/all-MiniLM-L6-v2": "",
             "BAAI/llm-embedder": "_llm_embedder",
-            "jina-embeddings-v3": "_jina_v3"
+            "jina/jina-embeddings-v3": "_jina_v3"
         }
         postfix = postfix_set[self.config.DEFAULT.embedding]
         if "jina" in postfix:

src/utils/hash.py

@@ -32,7 +32,7 @@ def check_embedding(repo_id):
                 "vocab.txt",
             ]
         elif repo_id in [
-            "jina-embeddings-v3",
+            "jinaai/jina-embeddings-v3",
         ]:
             files_to_download = [
                 "model.safetensors",

src/utils/paper_retriever.py

@@ -110,7 +110,7 @@ class Retriever(object):
             self.embedding_postfix = ""
         elif self.config.DEFAULT.embedding == "BAAI/llm-embedder":
             self.embedding_postfix = "_llm_embedder"
-        elif self.config.DEFAULT.embedding == "jina-embeddings-v3":
+        elif self.config.DEFAULT.embedding == "jinaai/jina-embeddings-v3":
             self.embedding_postfix = "_jina_v3"
             if self.config.DEFAULT.embedding_database == "text-matching":
                 self.embedding_postfix += "_text_matching"