Sentence Transformers Aliasing (#3541)

The sentence transformers was a dup of the HF one. 

This is a breaking change (model_name vs. model) for anyone using
`SentenceTransformerEmbeddings(model="some/nondefault/model")`, but
since it was landed only this week it seems better to do this now rather
than doing a wrapper.

docs/modules/models/text_embedding/examples/sentence_transformers.ipynb

@@ -8,12 +8,14 @@
    "source": [
     "# Sentence Transformers Embeddings\n",
     "\n",
-    "Let's generate embeddings using the [SentenceTransformers](https://www.sbert.net/) integration. SentenceTransformers is a python package that can generate text and image embeddings, originating from [Sentence-BERT](https://arxiv.org/abs/1908.10084)"
+    "[SentenceTransformers](https://www.sbert.net/) embeddings are called using the `HuggingFaceEmbeddings` integration. We have also added an alias for `SentenceTransformerEmbeddings` for users who are more familiar with directly using that package.\n",
+    "\n",
+    "SentenceTransformers is a python package that can generate text and image embeddings, originating from [Sentence-BERT](https://arxiv.org/abs/1908.10084)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 1,
    "id": "06c9f47d",
    "metadata": {},
    "outputs": [
@@ -21,10 +23,9 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\n",
-      "To disable this warning, you can either:\n",
-      "\t- Avoid using `tokenizers` before the fork if possible\n",
-      "\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\n"
+      "\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.0.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m23.1.1\u001b[0m\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n"
      ]
     }
    ],
@@ -34,27 +35,28 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 2,
    "id": "861521a9",
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.embeddings import SentenceTransformerEmbeddings "
+    "from langchain.embeddings import HuggingFaceEmbeddings, SentenceTransformerEmbeddings "
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": null,
    "id": "ff9be586",
    "metadata": {},
    "outputs": [],
    "source": [
-    "embeddings = SentenceTransformerEmbeddings(model=\"all-MiniLM-L6-v2\")"
+    "embeddings = HuggingFaceEmbeddings(model_name=\"all-MiniLM-L6-v2\")\n",
+    "# Equivalent to SentenceTransformerEmbeddings(model_name=\"all-MiniLM-L6-v2\")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 4,
    "id": "d0a98ae9",
    "metadata": {},
    "outputs": [],
@@ -64,7 +66,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 5,
    "id": "5d6c682b",
    "metadata": {},
    "outputs": [],
@@ -74,7 +76,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 6,
    "id": "bb5e74c0",
    "metadata": {},
    "outputs": [],
@@ -107,7 +109,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.2"
+   "version": "3.8.16"
   },
   "vscode": {
    "interpreter": {

langchain/embeddings/sentence_transformer.py

@@ -1,63 +1,4 @@
 """Wrapper around sentence transformer embedding models."""
-from typing import Any, Dict, List, Optional
+from langchain.embeddings.huggingface import HuggingFaceEmbeddings
 
-from pydantic import BaseModel, Extra, Field, root_validator
-
-from langchain.embeddings.base import Embeddings
-
-
-class SentenceTransformerEmbeddings(BaseModel, Embeddings):
-    embedding_function: Any  #: :meta private:
-
-    model: Optional[str] = Field("all-MiniLM-L6-v2", alias="model")
-    """Transformer model to use."""
-
-    class Config:
-        """Configuration for this pydantic object."""
-
-        extra = Extra.forbid
-
-    @root_validator()
-    def validate_environment(cls, values: Dict) -> Dict:
-        """Validate that sentence_transformers library is installed."""
-        model = values["model"]
-
-        try:
-            from sentence_transformers import SentenceTransformer
-
-            values["embedding_function"] = SentenceTransformer(model)
-        except ImportError:
-            raise ModuleNotFoundError(
-                "Could not import sentence_transformers library. "
-                "Please install the sentence_transformers library to "
-                "use this embedding model: pip install sentence_transformers"
-            )
-        except Exception:
-            raise NameError(f"Could not load SentenceTransformer model {model}.")
-
-        return values
-
-    def embed_documents(self, texts: List[str]) -> List[List[float]]:
-        """Embed a list of documents using the SentenceTransformer model.
-
-        Args:
-            texts: The list of texts to embed.
-
-        Returns:
-            List of embeddings, one for each text.
-        """
-        embeddings = self.embedding_function.encode(
-            texts, convert_to_numpy=True
-        ).tolist()
-        return [list(map(float, e)) for e in embeddings]
-
-    def embed_query(self, text: str) -> List[float]:
-        """Embed a query using the SentenceTransformer model.
-
-        Args:
-            text: The text to embed.
-
-        Returns:
-            Embedding for the text.
-        """
-        return self.embed_documents([text])[0]
+SentenceTransformerEmbeddings = HuggingFaceEmbeddings