community[patch]: update the default hf bge embeddings (#22627)

**Description:** This updates the langchain_community > huggingface >
default bge embeddings ([the current default recommends this
change](https://huggingface.co/BAAI/bge-large-en))
**Issue:** None
**Dependencies:** None
**Twitter handle:** @jonzeolla

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>

libs/community/langchain_community/embeddings/huggingface.py

@@ -67,6 +67,19 @@ class HuggingFaceEmbeddings(BaseModel, Embeddings):
     def __init__(self, **kwargs: Any):
         """Initialize the sentence_transformer."""
         super().__init__(**kwargs)
+
+        if "model_name" not in kwargs:
+            since = "0.2.16"
+            removal = "0.4.0"
+            warn_deprecated(
+                since=since,
+                removal=removal,
+                message=f"Default values for {self.__class__.__name__}.model_name"
+                + f" were deprecated in LangChain {since} and will be removed in"
+                + f" {removal}. Explicitly pass a model_name to the"
+                + f" {self.__class__.__name__} constructor instead.",
+            )
+
         try:
             import sentence_transformers
 
@@ -159,6 +172,19 @@ class HuggingFaceInstructEmbeddings(BaseModel, Embeddings):
     def __init__(self, **kwargs: Any):
         """Initialize the sentence_transformer."""
         super().__init__(**kwargs)
+
+        if "model_name" not in kwargs:
+            since = "0.2.16"
+            removal = "0.4.0"
+            warn_deprecated(
+                since=since,
+                removal=removal,
+                message=f"Default values for {self.__class__.__name__}.model_name"
+                + f" were deprecated in LangChain {since} and will be removed in"
+                + f" {removal}. Explicitly pass a model_name to the"
+                + f" {self.__class__.__name__} constructor instead.",
+            )
+
         try:
             from InstructorEmbedding import INSTRUCTOR
 
@@ -231,7 +257,7 @@ class HuggingFaceBgeEmbeddings(BaseModel, Embeddings):
 
             from langchain_community.embeddings import HuggingFaceBgeEmbeddings
 
-            model_name = "BAAI/bge-large-en"
+            model_name = "BAAI/bge-large-en-v1.5"
             model_kwargs = {'device': 'cpu'}
             encode_kwargs = {'normalize_embeddings': True}
             hf = HuggingFaceBgeEmbeddings(
@@ -279,6 +305,19 @@ class HuggingFaceBgeEmbeddings(BaseModel, Embeddings):
     def __init__(self, **kwargs: Any):
         """Initialize the sentence_transformer."""
         super().__init__(**kwargs)
+
+        if "model_name" not in kwargs:
+            since = "0.2.5"
+            removal = "0.4.0"
+            warn_deprecated(
+                since=since,
+                removal=removal,
+                message=f"Default values for {self.__class__.__name__}.model_name"
+                + f" were deprecated in LangChain {since} and will be removed in"
+                + f" {removal}. Explicitly pass a model_name to the"
+                + f" {self.__class__.__name__} constructor instead.",
+            )
+
         try:
             import sentence_transformers
 

libs/community/langchain_community/embeddings/openvino.py

@@ -303,7 +303,7 @@ class OpenVINOBgeEmbeddings(OpenVINOEmbeddings):
 
             from langchain_community.embeddings import OpenVINOBgeEmbeddings
 
-            model_name = "BAAI/bge-large-en"
+            model_name = "BAAI/bge-large-en-v1.5"
             model_kwargs = {'device': 'CPU'}
             encode_kwargs = {'normalize_embeddings': True}
             ov = OpenVINOBgeEmbeddings(

libs/community/langchain_community/vectorstores/scann.py

@@ -41,9 +41,10 @@ class ScaNN(VectorStore):
             from langchain_community.embeddings import HuggingFaceEmbeddings
             from langchain_community.vectorstores import ScaNN
 
+            model_name = "sentence-transformers/all-mpnet-base-v2"
             db = ScaNN.from_texts(
                 ['foo', 'bar', 'barz', 'qux'],
-                HuggingFaceEmbeddings())
+                HuggingFaceEmbeddings(model_name=model_name))
             db.similarity_search('foo?', k=1)
     """
 

libs/community/langchain_community/vectorstores/surrealdb.py

@@ -1,12 +1,5 @@
 import asyncio
-from typing import (
-    Any,
-    Dict,
-    Iterable,
-    List,
-    Optional,
-    Tuple,
-)
+from typing import Any, Dict, Iterable, List, Optional, Tuple
 
 import numpy as np
 from langchain_core.documents import Document
@@ -40,7 +33,8 @@ class SurrealDBStore(VectorStore):
             from langchain_community.vectorstores.surrealdb import SurrealDBStore
             from langchain_community.embeddings import HuggingFaceEmbeddings
 
-            embedding_function = HuggingFaceEmbeddings()
+            model_name = "sentence-transformers/all-mpnet-base-v2"
+            embedding_function = HuggingFaceEmbeddings(model_name=model_name)
             dburl = "ws://localhost:8000/rpc"
             ns = "langchain"
             db = "docstore"

libs/community/langchain_community/vectorstores/vald.py

@@ -23,10 +23,11 @@ class Vald(VectorStore):
             from langchain_community.embeddings import HuggingFaceEmbeddings
             from langchain_community.vectorstores import Vald
 
+            model_name = "sentence-transformers/all-mpnet-base-v2"
             texts = ['foo', 'bar', 'baz']
             vald = Vald.from_texts(
                 texts=texts,
-                embedding=HuggingFaceEmbeddings(),
+                embedding=HuggingFaceEmbeddings(model_name=model_name),
                 host="localhost",
                 port=8080,
                 skip_strict_exist_check=False,

libs/community/langchain_community/vectorstores/vdms.py

@@ -161,9 +161,10 @@ class VDMS(VectorStore):
             from langchain_huggingface import HuggingFaceEmbeddings
             from langchain_community.vectorstores.vdms import VDMS, VDMS_Client
 
+            model_name = "sentence-transformers/all-mpnet-base-v2"
             vectorstore = VDMS(
                 client=VDMS_Client("localhost", 55555),
-                embedding=HuggingFaceEmbeddings(),
+                embedding=HuggingFaceEmbeddings(model_name=model_name),
                 collection_name="langchain-demo",
                 distance_strategy="L2",
                 engine="FaissFlat",