docs: huggingface package (#21645)

cookbook/sql_db_qa.mdx

@@ -647,7 +647,7 @@ Sometimes you may not have the luxury of using OpenAI or other service-hosted la
 import logging
 import torch
 from transformers import AutoTokenizer, GPT2TokenizerFast, pipeline, AutoModelForSeq2SeqLM, AutoModelForCausalLM
-from langchain_community.llms import HuggingFacePipeline
+from langchain_huggingface import HuggingFacePipeline
 
 # Note: This model requires a large GPU, e.g. an 80GB A100. See documentation for other ways to run private non-OpenAI models.
 model_id = "google/flan-ul2"
@@ -992,7 +992,7 @@ Now that you have some examples (with manually corrected output SQL), you can do
 ```python
 from langchain.prompts import FewShotPromptTemplate, PromptTemplate
 from langchain.chains.sql_database.prompt import _sqlite_prompt, PROMPT_SUFFIX
-from langchain_community.embeddings.huggingface import HuggingFaceEmbeddings
+from langchain_huggingface import HuggingFaceEmbeddings
 from langchain.prompts.example_selector.semantic_similarity import SemanticSimilarityExampleSelector
 from langchain_community.vectorstores import Chroma
 

docs/docs/how_to/long_context_reorder.ipynb

@@ -21,7 +21,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet  sentence-transformers langchain-chroma langchain langchain-openai > /dev/null"
+    "%pip install --upgrade --quiet  sentence-transformers langchain-chroma langchain langchain-openai langchain-huggingface > /dev/null"
    ]
   },
   {
@@ -57,7 +57,7 @@
     "from langchain_community.document_transformers import (\n",
     "    LongContextReorder,\n",
     ")\n",
-    "from langchain_community.embeddings import HuggingFaceEmbeddings\n",
+    "from langchain_huggingface import HuggingFaceEmbeddings\n",
     "from langchain_openai import OpenAI\n",
     "\n",
     "# Get embeddings.\n",

docs/docs/integrations/chat/huggingface.ipynb

@@ -24,7 +24,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet  text-generation transformers google-search-results numexpr langchainhub sentencepiece jinja2"
+    "%pip install --upgrade --quiet  langchain-huggingface text-generation transformers google-search-results numexpr langchainhub sentencepiece jinja2"
    ]
   },
   {
@@ -47,7 +47,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_huggingface.llms import HuggingFaceEndpoint\n",
+    "from langchain_huggingface import HuggingFaceEndpoint\n",
     "\n",
     "llm = HuggingFaceEndpoint(\n",
     "    repo_id=\"meta-llama/Meta-Llama-3-70B-Instruct\",\n",
@@ -92,7 +92,7 @@
     "    HumanMessage,\n",
     "    SystemMessage,\n",
     ")\n",
-    "from langchain_huggingface.chat_models import ChatHuggingFace\n",
+    "from langchain_huggingface import ChatHuggingFace\n",
     "\n",
     "messages = [\n",
     "    SystemMessage(content=\"You're a helpful assistant\"),\n",

docs/docs/integrations/document_transformers/cross_encoder_reranker.ipynb

@@ -67,8 +67,8 @@
    "outputs": [],
    "source": [
     "from langchain.document_loaders import TextLoader\n",
-    "from langchain_community.embeddings import HuggingFaceEmbeddings\n",
     "from langchain_community.vectorstores import FAISS\n",
+    "from langchain_huggingface import HuggingFaceEmbeddings\n",
     "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
     "\n",
     "documents = TextLoader(\"../../how_to/state_of_the_union.txt\").load()\n",

docs/docs/integrations/llms/huggingface_endpoint.ipynb

@@ -20,7 +20,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_huggingface.llms import HuggingFaceEndpoint"
+    "from langchain_huggingface import HuggingFaceEndpoint"
    ]
   },
   {
@@ -83,7 +83,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_huggingface.llms import HuggingFaceEndpoint"
+    "from langchain_huggingface import HuggingFaceEndpoint"
    ]
   },
   {
@@ -193,7 +193,7 @@
    "outputs": [],
    "source": [
     "from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
-    "from langchain_huggingface.llms import HuggingFaceEndpoint\n",
+    "from langchain_huggingface import HuggingFaceEndpoint\n",
     "\n",
     "llm = HuggingFaceEndpoint(\n",
     "    endpoint_url=f\"{your_endpoint_url}\",\n",

docs/docs/integrations/llms/jsonformer_experimental.ipynb

@@ -152,7 +152,7 @@
     }
    ],
    "source": [
-    "from langchain_community.llms import HuggingFacePipeline\n",
+    "from langchain_huggingface import HuggingFacePipeline\n",
     "from transformers import pipeline\n",
     "\n",
     "hf_model = pipeline(\n",

docs/docs/integrations/llms/lmformatenforcer_experimental.ipynb

@@ -25,7 +25,7 @@
    },
    "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet  lm-format-enforcer > /dev/null"
+    "%pip install --upgrade --quiet  lm-format-enforcer langchain-huggingface > /dev/null"
    ]
   },
   {
@@ -193,7 +193,7 @@
     }
    ],
    "source": [
-    "from langchain_community.llms import HuggingFacePipeline\n",
+    "from langchain_huggingface import HuggingFacePipeline\n",
     "from transformers import pipeline\n",
     "\n",
     "hf_model = pipeline(\n",

docs/docs/integrations/llms/mlx_pipelines.ipynb

@@ -78,7 +78,6 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_community.llms.huggingface_pipeline import HuggingFacePipeline\n",
     "from mlx_lm import load\n",
     "\n",
     "model, tokenizer = load(\"mlx-community/quantized-gemma-2b-it\")\n",

docs/docs/integrations/llms/openvino.ipynb

@@ -55,7 +55,7 @@
    },
    "outputs": [],
    "source": [
-    "from langchain_community.llms.huggingface_pipeline import HuggingFacePipeline\n",
+    "from langchain_huggingface import HuggingFacePipeline\n",
     "\n",
     "ov_config = {\"PERFORMANCE_HINT\": \"LATENCY\", \"NUM_STREAMS\": \"1\", \"CACHE_DIR\": \"\"}\n",
     "\n",

docs/docs/integrations/llms/rellm_experimental.ipynb

@@ -24,7 +24,7 @@
    },
    "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet  rellm > /dev/null"
+    "%pip install --upgrade --quiet  rellm langchain-huggingface > /dev/null"
    ]
   },
   {
@@ -92,7 +92,7 @@
     }
    ],
    "source": [
-    "from langchain_community.llms import HuggingFacePipeline\n",
+    "from langchain_huggingface import HuggingFacePipeline\n",
     "from transformers import pipeline\n",
     "\n",
     "hf_model = pipeline(\n",

docs/docs/integrations/llms/weight_only_quantization.ipynb

@@ -85,7 +85,6 @@
    "outputs": [],
    "source": [
     "from intel_extension_for_transformers.transformers import AutoModelForSeq2SeqLM\n",
-    "from langchain_community.llms.huggingface_pipeline import HuggingFacePipeline\n",
     "from transformers import AutoTokenizer, pipeline\n",
     "\n",
     "model_id = \"google/flan-t5-large\"\n",

docs/docs/integrations/platforms/huggingface.mdx

@@ -2,22 +2,24 @@
 
 All functionality related to the [Hugging Face Platform](https://huggingface.co/).
 
+## Installation
+
+Most of the Hugging Face integrations are available in the `langchain-huggingface` package.
+
+```bash
+pip install langchain-huggingface
+```
+
 ## Chat models
 
 ### Models from Hugging Face
 
 We can use the `Hugging Face` LLM classes or directly use the `ChatHuggingFace` class.
 
-We need to install several python packages.
-
-```bash
-pip install huggingface_hub
-pip install transformers
-```
 See a [usage example](/docs/integrations/chat/huggingface).
 
 ```python
-from langchain_community.chat_models.huggingface import ChatHuggingFace
+from langchain_huggingface import ChatHuggingFace
 ```
 
 ## LLMs
@@ -26,60 +28,23 @@ from langchain_community.chat_models.huggingface import ChatHuggingFace
 
 Hugging Face models can be run locally through the `HuggingFacePipeline` class.
 
-We need to install `transformers` python package.
-
-```bash
-pip install transformers
-```
-
 See a [usage example](/docs/integrations/llms/huggingface_pipelines).
 
 ```python
-from langchain_community.llms.huggingface_pipeline import HuggingFacePipeline
+from langchain_huggingface import HuggingFacePipeline
 ```
 
-To use the OpenVINO backend in local pipeline wrapper, please install the optimum library and set HuggingFacePipeline's backend as `openvino`:
-
-```bash
-pip install --upgrade-strategy eager "optimum[openvino,nncf]"
-```
-
-See a [usage example](/docs/integrations/llms/huggingface_pipelines)
-
-To export your model to the OpenVINO IR format with the CLI:
-
-```bash
-optimum-cli export openvino --model gpt2 ov_model
-```
-
-To apply [weight-only quantization](https://github.com/huggingface/optimum-intel?tab=readme-ov-file#export) when exporting your model.
-
-
 ## Embedding Models
 
-### Hugging Face Hub
+### HuggingFaceEmbeddings
-
->The [Hugging Face Hub](https://huggingface.co/docs/hub/index) is a platform 
-> with over 350k models, 75k datasets, and 150k demo apps (Spaces), all open source 
-> and publicly available, in an online platform where people can easily 
-> collaborate and build ML together. The Hub works as a central place where anyone 
-> can explore, experiment, collaborate, and build technology with Machine Learning.
-
-We need to install the `sentence_transformers` python package.
-
-```bash
-pip install sentence_transformers
-```
-
-
-#### HuggingFaceEmbeddings
 
 See a [usage example](/docs/integrations/text_embedding/huggingfacehub).
 
 ```python
-from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_huggingface import HuggingFaceEmbeddings
 ```
-#### HuggingFaceInstructEmbeddings
+
+### HuggingFaceInstructEmbeddings
 
 See a [usage example](/docs/integrations/text_embedding/instruct_embeddings).
 
@@ -87,7 +52,7 @@ See a [usage example](/docs/integrations/text_embedding/instruct_embeddings).
 from langchain_community.embeddings import HuggingFaceInstructEmbeddings
 ```
 
-#### HuggingFaceBgeEmbeddings
+### 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 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.

docs/docs/integrations/providers/snowflake.mdx

@@ -17,7 +17,7 @@ pip install langchain-community sentence-transformers
 ```
 
 ```python
-from langchain_community.text_embeddings import HuggingFaceEmbeddings
+from langchain_huggingface import HuggingFaceEmbeddings
 
 model = HuggingFaceEmbeddings(model_name="snowflake/arctic-embed-l")
 ```

docs/docs/integrations/providers/vdms.mdx

@@ -41,7 +41,7 @@ docs = text_splitter.split_documents(documents)
 
 from langchain_community.vectorstores import VDMS
 from langchain_community.vectorstores.vdms import VDMS_Client
-from langchain_community.embeddings.huggingface import HuggingFaceEmbeddings
+from langchain_huggingface import HuggingFaceEmbeddings
 
 client = VDMS_Client("localhost", 55555)
 vectorstore = VDMS.from_documents(

docs/docs/integrations/retrievers/merger_retriever.ipynb

@@ -33,7 +33,7 @@
     "    EmbeddingsClusteringFilter,\n",
     "    EmbeddingsRedundantFilter,\n",
     ")\n",
-    "from langchain_community.embeddings import HuggingFaceEmbeddings\n",
+    "from langchain_huggingface import HuggingFaceEmbeddings\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
     "# Get 3 diff embeddings.\n",

docs/docs/integrations/text_embedding/sentence_transformers.ipynb

@@ -41,7 +41,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_community.embeddings import HuggingFaceEmbeddings"
+    "from langchain_huggingface import HuggingFaceEmbeddings"
    ]
   },
   {

docs/docs/integrations/vectorstores/annoy.ipynb

@@ -52,8 +52,8 @@
    },
    "outputs": [],
    "source": [
-    "from langchain_community.embeddings import HuggingFaceEmbeddings\n",
     "from langchain_community.vectorstores import Annoy\n",
+    "from langchain_huggingface import HuggingFaceEmbeddings\n",
     "\n",
     "embeddings_func = HuggingFaceEmbeddings()"
    ]

docs/docs/integrations/vectorstores/faiss.ipynb

@@ -328,7 +328,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_community.embeddings.huggingface import HuggingFaceEmbeddings\n",
+    "from langchain_huggingface import HuggingFaceEmbeddings\n",
     "\n",
     "pkl = db.serialize_to_bytes()  # serializes the faiss\n",
     "embeddings = HuggingFaceEmbeddings(model_name=\"all-MiniLM-L6-v2\")\n",

docs/docs/integrations/vectorstores/faiss_async.ipynb

@@ -158,7 +158,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_community.embeddings.huggingface import HuggingFaceEmbeddings\n",
+    "from langchain_huggingface import HuggingFaceEmbeddings\n",
     "\n",
     "pkl = db.serialize_to_bytes()  # serializes the faiss index\n",
     "embeddings = HuggingFaceEmbeddings(model_name=\"all-MiniLM-L6-v2\")\n",

docs/docs/integrations/vectorstores/oracle.ipynb

@@ -91,11 +91,11 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_community.embeddings import HuggingFaceEmbeddings\n",
     "from langchain_community.vectorstores import oraclevs\n",
     "from langchain_community.vectorstores.oraclevs import OracleVS\n",
     "from langchain_community.vectorstores.utils import DistanceStrategy\n",
-    "from langchain_core.documents import Document"
+    "from langchain_core.documents import Document\n",
+    "from langchain_huggingface import HuggingFaceEmbeddings"
    ]
   },
   {

docs/docs/integrations/vectorstores/scann.ipynb

@@ -60,8 +60,8 @@
    ],
    "source": [
     "from langchain_community.document_loaders import TextLoader\n",
-    "from langchain_community.embeddings import HuggingFaceEmbeddings\n",
     "from langchain_community.vectorstores import ScaNN\n",
+    "from langchain_huggingface import HuggingFaceEmbeddings\n",
     "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "loader = TextLoader(\"state_of_the_union.txt\")\n",

docs/docs/integrations/vectorstores/semadb.ipynb

@@ -41,7 +41,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_community.embeddings import HuggingFaceEmbeddings\n",
+    "from langchain_huggingface import HuggingFaceEmbeddings\n",
     "\n",
     "embeddings = HuggingFaceEmbeddings()"
    ]

docs/docs/integrations/vectorstores/surrealdb.ipynb

@@ -74,8 +74,8 @@
    "outputs": [],
    "source": [
     "from langchain_community.document_loaders import TextLoader\n",
-    "from langchain_community.embeddings import HuggingFaceEmbeddings\n",
     "from langchain_community.vectorstores import SurrealDBStore\n",
+    "from langchain_huggingface import HuggingFaceEmbeddings\n",
     "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },

docs/docs/integrations/vectorstores/tiledb.ipynb

@@ -44,8 +44,8 @@
    "outputs": [],
    "source": [
     "from langchain_community.document_loaders import TextLoader\n",
-    "from langchain_community.embeddings import HuggingFaceEmbeddings\n",
     "from langchain_community.vectorstores import TileDB\n",
+    "from langchain_huggingface import HuggingFaceEmbeddings\n",
     "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "raw_documents = TextLoader(\"../../how_to/state_of_the_union.txt\").load()\n",

docs/docs/integrations/vectorstores/vald.ipynb

@@ -43,8 +43,8 @@
    "outputs": [],
    "source": [
     "from langchain_community.document_loaders import TextLoader\n",
-    "from langchain_community.embeddings import HuggingFaceEmbeddings\n",
     "from langchain_community.vectorstores import Vald\n",
+    "from langchain_huggingface import HuggingFaceEmbeddings\n",
     "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "raw_documents = TextLoader(\"state_of_the_union.txt\").load()\n",
@@ -190,8 +190,8 @@
    "outputs": [],
    "source": [
     "from langchain_community.document_loaders import TextLoader\n",
-    "from langchain_community.embeddings import HuggingFaceEmbeddings\n",
     "from langchain_community.vectorstores import Vald\n",
+    "from langchain_huggingface import HuggingFaceEmbeddings\n",
     "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "raw_documents = TextLoader(\"state_of_the_union.txt\").load()\n",

docs/docs/integrations/vectorstores/vdms.ipynb

@@ -92,9 +92,9 @@
     "import time\n",
     "\n",
     "from langchain_community.document_loaders.text import TextLoader\n",
-    "from langchain_community.embeddings.huggingface import HuggingFaceEmbeddings\n",
     "from langchain_community.vectorstores import VDMS\n",
     "from langchain_community.vectorstores.vdms import VDMS_Client\n",
+    "from langchain_huggingface import HuggingFaceEmbeddings\n",
     "from langchain_text_splitters.character import CharacterTextSplitter\n",
     "\n",
     "time.sleep(2)\n",

docs/docs/integrations/vectorstores/vearch.ipynb

@@ -53,8 +53,8 @@
    ],
    "source": [
     "from langchain_community.document_loaders import TextLoader\n",
-    "from langchain_community.embeddings.huggingface import HuggingFaceEmbeddings\n",
     "from langchain_community.vectorstores.vearch import Vearch\n",
+    "from langchain_huggingface import HuggingFaceEmbeddings\n",
     "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
     "from transformers import AutoModel, AutoTokenizer\n",
     "\n",

libs/partners/huggingface/langchain_huggingface/embeddings/huggingface_endpoint.py

@@ -19,7 +19,7 @@ class HuggingFaceEndpointEmbeddings(BaseModel, Embeddings):
     Example:
         .. code-block:: python
 
-            from langchain_community.embeddings import HuggingFaceEndpointEmbeddings
+            from langchain_huggingface import HuggingFaceEndpointEmbeddings
             model = "sentence-transformers/all-mpnet-base-v2"
             hf = HuggingFaceEndpointEmbeddings(
                 model=model,