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>

docs/docs/how_to/embed_text.mdx

@@ -94,15 +94,6 @@ from langchain_huggingface import HuggingFaceEmbeddings
 
 embeddings_model = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
 ```
-
-You can also leave the `model_name` blank to use the default [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) model.
-
-```python
-from langchain_huggingface import HuggingFaceEmbeddings
-
-embeddings_model = HuggingFaceEmbeddings()
-```
-
   </TabItem>
 </Tabs>
 

docs/docs/integrations/platforms/huggingface.mdx

@@ -54,7 +54,7 @@ from langchain_community.embeddings import HuggingFaceInstructEmbeddings
 
 ### HuggingFaceBgeEmbeddings
 
->[BGE models on the HuggingFace](https://huggingface.co/BAAI/bge-large-en) are [the best open-source embedding models](https://huggingface.co/spaces/mteb/leaderboard).
+>[BGE models on the HuggingFace](https://huggingface.co/BAAI/bge-large-en-v1.5) are one of [the best open-source embedding models](https://huggingface.co/spaces/mteb/leaderboard).
 >BGE model is created by the [Beijing Academy of Artificial Intelligence (BAAI)](https://en.wikipedia.org/wiki/Beijing_Academy_of_Artificial_Intelligence). `BAAI` is a private non-profit organization engaged in AI research and development.
 
 See a [usage example](/docs/integrations/text_embedding/bge_huggingface).

docs/docs/integrations/providers/vdms.mdx

@@ -44,11 +44,12 @@ from langchain_community.vectorstores.vdms import VDMS_Client
 from langchain_huggingface import HuggingFaceEmbeddings
 
 client = VDMS_Client("localhost", 55555)
+model_name = "sentence-transformers/all-mpnet-base-v2"
 vectorstore = VDMS.from_documents(
     docs,
     client=client,
     collection_name="langchain-demo",
-    embedding_function=HuggingFaceEmbeddings(),
+    embedding_function=HuggingFaceEmbeddings(model_name=model_name),
     engine="FaissFlat"
     distance_strategy="L2",
 )
@@ -58,5 +59,3 @@ results = vectorstore.similarity_search(query)
 ```
 
 For a more detailed walkthrough of the VDMS wrapper, see [this notebook](/docs/integrations/vectorstores/vdms)
-
-

docs/docs/integrations/text_embedding/bge_huggingface.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# BGE on Hugging Face\n",
     "\n",
-    ">[BGE models on the HuggingFace](https://huggingface.co/BAAI/bge-large-en) are [the best open-source embedding models](https://huggingface.co/spaces/mteb/leaderboard).\n",
+    ">[BGE models on the HuggingFace](https://huggingface.co/BAAI/bge-large-en-v1.5) are one of [the best open-source embedding models](https://huggingface.co/spaces/mteb/leaderboard).\n",
     ">BGE model is created by the [Beijing Academy of Artificial Intelligence (BAAI)](https://en.wikipedia.org/wiki/Beijing_Academy_of_Artificial_Intelligence). `BAAI` is a private non-profit organization engaged in AI research and development.\n",
     "\n",
     "This notebook shows how to use `BGE Embeddings` through `Hugging Face`"

docs/docs/integrations/text_embedding/huggingfacehub.ipynb

@@ -36,7 +36,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "embeddings = HuggingFaceEmbeddings()"
+    "embeddings = HuggingFaceEmbeddings(model_name=\"sentence-transformers/all-mpnet-base-v2\")"
    ]
   },
   {

docs/docs/integrations/vectorstores/annoy.ipynb

@@ -57,7 +57,8 @@
     "from langchain_community.vectorstores import Annoy\n",
     "from langchain_huggingface import HuggingFaceEmbeddings\n",
     "\n",
-    "embeddings_func = HuggingFaceEmbeddings()"
+    "model_name = \"sentence-transformers/all-mpnet-base-v2\"\n",
+    "embeddings_func = HuggingFaceEmbeddings(model_name=model_name)"
    ]
   },
   {

docs/docs/integrations/vectorstores/scann.ipynb

@@ -61,7 +61,8 @@
     "docs = text_splitter.split_documents(documents)\n",
     "\n",
     "\n",
-    "embeddings = HuggingFaceEmbeddings()\n",
+    "model_name = \"sentence-transformers/all-mpnet-base-v2\"\n",
+    "embeddings = HuggingFaceEmbeddings(model_name=model_name)\n",
     "\n",
     "db = ScaNN.from_documents(docs, embeddings)\n",
     "query = \"What did the president say about Ketanji Brown Jackson\"\n",

docs/docs/integrations/vectorstores/semadb.ipynb

@@ -45,7 +45,8 @@
    "source": [
     "from langchain_huggingface import HuggingFaceEmbeddings\n",
     "\n",
-    "embeddings = HuggingFaceEmbeddings()"
+    "model_name = \"sentence-transformers/all-mpnet-base-v2\"\n",
+    "embeddings = HuggingFaceEmbeddings(model_name=model_name)"
    ]
   },
   {

docs/docs/integrations/vectorstores/surrealdb.ipynb

@@ -92,7 +92,8 @@
     "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
     "docs = text_splitter.split_documents(documents)\n",
     "\n",
-    "embeddings = HuggingFaceEmbeddings()"
+    "model_name = \"sentence-transformers/all-mpnet-base-v2\"\n",
+    "embeddings = HuggingFaceEmbeddings(model_name=model_name)"
    ]
   },
   {

docs/docs/integrations/vectorstores/tiledb.ipynb

@@ -51,7 +51,8 @@
     "raw_documents = TextLoader(\"../../how_to/state_of_the_union.txt\").load()\n",
     "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
     "documents = text_splitter.split_documents(raw_documents)\n",
-    "embeddings = HuggingFaceEmbeddings()\n",
+    "model_name = \"sentence-transformers/all-mpnet-base-v2\"\n",
+    "embeddings = HuggingFaceEmbeddings(model_name=model_name)\n",
     "db = TileDB.from_documents(\n",
     "    documents, embeddings, index_uri=\"/tmp/tiledb_index\", index_type=\"FLAT\"\n",
     ")"

docs/docs/integrations/vectorstores/vald.ipynb

@@ -50,7 +50,8 @@
     "raw_documents = TextLoader(\"state_of_the_union.txt\").load()\n",
     "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
     "documents = text_splitter.split_documents(raw_documents)\n",
-    "embeddings = HuggingFaceEmbeddings()\n",
+    "model_name = \"sentence-transformers/all-mpnet-base-v2\"\n",
+    "embeddings = HuggingFaceEmbeddings(model_name=model_name)\n",
     "db = Vald.from_documents(documents, embeddings, host=\"localhost\", port=8080)"
    ]
   },
@@ -197,7 +198,8 @@
     "raw_documents = TextLoader(\"state_of_the_union.txt\").load()\n",
     "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
     "documents = text_splitter.split_documents(raw_documents)\n",
-    "embeddings = HuggingFaceEmbeddings()\n",
+    "model_name = \"sentence-transformers/all-mpnet-base-v2\"\n",
+    "embeddings = HuggingFaceEmbeddings(model_name=model_name)\n",
     "\n",
     "db = Vald.from_documents(\n",
     "    documents,\n",

docs/docs/integrations/vectorstores/vdms.ipynb

@@ -200,7 +200,8 @@
     "\n",
     "\n",
     "# create the open-source embedding function\n",
-    "embedding = HuggingFaceEmbeddings()\n",
+    "model_name = \"sentence-transformers/all-mpnet-base-v2\"\n",
+    "embedding = HuggingFaceEmbeddings(model_name=model_name)\n",
     "print(\n",
     "    f\"# Embedding Dimensions: {len(embedding.embed_query('This is a test document.'))}\"\n",
     ")"

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 (
+from typing import Any, Dict, Iterable, List, Optional, Tuple
-    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",

templates/self-query-qdrant/README.md

@@ -92,9 +92,10 @@ from langchain.chains.query_constructor.schema import AttributeInfo
 
 from self_query_qdrant.chain import create_chain
 
+model_name = "sentence-transformers/all-mpnet-base-v2"
 chain = create_chain(
     llm=Cohere(),
-    embeddings=HuggingFaceEmbeddings(),
+    embeddings=HuggingFaceEmbeddings(model_name=model_name),
     document_contents="Descriptions of cats, along with their names and breeds.",
     metadata_field_info=[
         AttributeInfo(name="name", description="Name of the cat", type="string"),
@@ -112,8 +113,9 @@ from langchain_community.embeddings import HuggingFaceEmbeddings
 
 from self_query_qdrant.chain import initialize
 
+model_name = "sentence-transformers/all-mpnet-base-v2"
 initialize(
-    embeddings=HuggingFaceEmbeddings(),
+    embeddings=HuggingFaceEmbeddings(model_name=model_name),
     collection_name="cats",
     documents=[
         Document(