diff --git a/docs/docs/integrations/chat/huggingface.ipynb b/docs/docs/integrations/chat/huggingface.ipynb
index 6bdb04870ef..f203d29f685 100644
--- a/docs/docs/integrations/chat/huggingface.ipynb
+++ b/docs/docs/integrations/chat/huggingface.ipynb
@@ -58,6 +58,62 @@
     ")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### `HuggingFacePipeline`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_huggingface import HuggingFacePipeline\n",
+    "\n",
+    "llm = HuggingFacePipeline.from_model_id(\n",
+    "    model_id=\"HuggingFaceH4/zephyr-7b-beta\",\n",
+    "    task=\"text-generation\",\n",
+    "    pipeline_kwargs=dict(\n",
+    "        max_new_tokens=512,\n",
+    "        do_sample=False,\n",
+    "        repetition_penalty=1.03,\n",
+    "    ),\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "To run a quantized version, you might specify a `bitsandbytes` quantization config as follows:\n",
+    "\n",
+    "```python\n",
+    "from transformers import BitsAndBytesConfig\n",
+    "\n",
+    "quantization_config = BitsAndBytesConfig(\n",
+    "    load_in_4bit=True,\n",
+    "    bnb_4bit_quant_type=\"nf4\",\n",
+    "    bnb_4bit_compute_dtype=\"float16\",\n",
+    "    bnb_4bit_use_double_quant=True\n",
+    ")\n",
+    "```\n",
+    "\n",
+    "and pass it to the `HuggingFacePipeline` as a part of its `model_kwargs`:\n",
+    "\n",
+    "```python\n",
+    "pipeline = HuggingFacePipeline(\n",
+    "    ...\n",
+    "\n",
+    "    model_kwargs={\"quantization_config\": quantization_config},\n",
+    "    \n",
+    "    ...\n",
+    ")\n",
+    "```"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
diff --git a/libs/partners/huggingface/langchain_huggingface/chat_models/huggingface.py b/libs/partners/huggingface/langchain_huggingface/chat_models/huggingface.py
index 8cbb274477e..9b3564d5302 100644
--- a/libs/partners/huggingface/langchain_huggingface/chat_models/huggingface.py
+++ b/libs/partners/huggingface/langchain_huggingface/chat_models/huggingface.py
@@ -35,6 +35,7 @@ from langchain_core.tools import BaseTool
 from langchain_core.utils.function_calling import convert_to_openai_tool
 
 from langchain_huggingface.llms.huggingface_endpoint import HuggingFaceEndpoint
+from langchain_huggingface.llms.huggingface_pipeline import HuggingFacePipeline
 
 DEFAULT_SYSTEM_PROMPT = """You are a helpful, respectful, and honest assistant."""
 
@@ -135,6 +136,10 @@ def _is_huggingface_endpoint(llm: Any) -> bool:
     return isinstance(llm, HuggingFaceEndpoint)
 
 
+def _is_huggingface_pipeline(llm: Any) -> bool:
+    return isinstance(llm, HuggingFacePipeline)
+
+
 class ChatHuggingFace(BaseChatModel):
     """
     Wrapper for using Hugging Face LLM's as ChatModels.
@@ -150,8 +155,8 @@ class ChatHuggingFace(BaseChatModel):
     """
 
     llm: Any
-    """LLM, must be of type HuggingFaceTextGenInference, HuggingFaceEndpoint, or 
-        HuggingFaceHub."""
+    """LLM, must be of type HuggingFaceTextGenInference, HuggingFaceEndpoint,
+        HuggingFaceHub, or HuggingFacePipeline."""
     system_message: SystemMessage = SystemMessage(content=DEFAULT_SYSTEM_PROMPT)
     tokenizer: Any = None
     model_id: Optional[str] = None
@@ -175,10 +180,12 @@ class ChatHuggingFace(BaseChatModel):
             not _is_huggingface_hub(values["llm"])
             and not _is_huggingface_textgen_inference(values["llm"])
             and not _is_huggingface_endpoint(values["llm"])
+            and not _is_huggingface_pipeline(values["llm"])
         ):
             raise TypeError(
                 "Expected llm to be one of HuggingFaceTextGenInference, "
-                f"HuggingFaceEndpoint, HuggingFaceHub, received {type(values['llm'])}"
+                "HuggingFaceEndpoint, HuggingFaceHub, HuggingFacePipeline "
+                f"received {type(values['llm'])}"
             )
         return values
 
@@ -293,6 +300,9 @@ class ChatHuggingFace(BaseChatModel):
             return
         elif _is_huggingface_textgen_inference(self.llm):
             endpoint_url: Optional[str] = self.llm.inference_server_url
+        elif _is_huggingface_pipeline(self.llm):
+            self.model_id = self.llm.model_id
+            return
         else:
             endpoint_url = self.llm.endpoint_url