From 7756489950481b17d403f7a8ae4026c55cef24ef Mon Sep 17 00:00:00 2001
From: lujingxuansc <lujingxuansc@bytedance.com>
Date: Thu, 14 Dec 2023 11:17:28 +0800
Subject: [PATCH 01/13] feat: integrate bytedance volcano embedding

---
 .../text_embedding/bytedance_volcano.ipynb    | 123 +++++++++++++++++
 .../embeddings/__init__.py                    |   2 +
 .../embeddings/bytedance_volcano.py           | 127 ++++++++++++++++++
 .../embeddings/test_volcano.py                |  19 +++
 .../unit_tests/embeddings/test_imports.py     |   1 +
 .../langchain/embeddings/__init__.py          |   2 +
 .../langchain/embeddings/bytedance_volcano.py |   5 +
 .../unit_tests/embeddings/test_imports.py     |   1 +
 8 files changed, 280 insertions(+)
 create mode 100644 docs/docs/integrations/text_embedding/bytedance_volcano.ipynb
 create mode 100644 libs/community/langchain_community/embeddings/bytedance_volcano.py
 create mode 100644 libs/community/tests/integration_tests/embeddings/test_volcano.py
 create mode 100644 libs/langchain/langchain/embeddings/bytedance_volcano.py

diff --git a/docs/docs/integrations/text_embedding/bytedance_volcano.ipynb b/docs/docs/integrations/text_embedding/bytedance_volcano.ipynb
new file mode 100644
index 0000000000000..0370a934be75f
--- /dev/null
+++ b/docs/docs/integrations/text_embedding/bytedance_volcano.ipynb
@@ -0,0 +1,123 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "outputs": [
+    {
+     "ename": "SyntaxError",
+     "evalue": "invalid syntax (3044863648.py, line 3)",
+     "output_type": "error",
+     "traceback": [
+      "\u001B[0;36m  Cell \u001B[0;32mIn[5], line 3\u001B[0;36m\u001B[0m\n\u001B[0;31m    This notebook provides you with a guide on how to load the Volcano Embedding class.\u001B[0m\n\u001B[0m         ^\u001B[0m\n\u001B[0;31mSyntaxError\u001B[0m\u001B[0;31m:\u001B[0m invalid syntax\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Bytedance Volcano\n",
+    "\n",
+    "This notebook provides you with a guide on how to load the Volcano Embedding class.\n",
+    "\n",
+    "\n",
+    "## API Initialization\n",
+    "\n",
+    "To use the LLM services based on [Bytedance Volcano](https://www.volcengine.com/docs/82379/1099455), you have to initialize these parameters:\n",
+    "\n",
+    "You could either choose to init the AK,SK in environment variables or init params:\n",
+    "\n",
+    "```base\n",
+    "export VOLC_ACCESSKEY=XXX\n",
+    "export VOLC_SECRETKEY=XXX\n",
+    "```"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2023-12-14T03:05:29.859376Z",
+     "start_time": "2023-12-14T03:05:29.853288Z"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "ExecuteTime": {
+     "start_time": "2023-12-14T03:05:29.857798Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "\"\"\"For basic init and call\"\"\"\n",
+    "import os\n",
+    "\n",
+    "from langchain.embeddings import VolcanoEmbeddings\n",
+    "\n",
+    "os.environ[\"VOLC_ACCESSKEY\"] = \"\"\n",
+    "os.environ[\"VOLC_SECRETKEY\"] = \"==\"\n",
+    "\n",
+    "embed = VolcanoEmbeddings(\n",
+    "    # volcano_ak='xxx',\n",
+    "    # volcano_sk='xxx'\n",
+    ")\n",
+    "\n",
+    "print(\"embed_documents result:\")\n",
+    "res1 = embed.embed_documents([\"foo\", \"bar\"])\n",
+    "for r in res1:\n",
+    "    print(\"\", r[:8])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "ExecuteTime": {
+     "start_time": "2023-12-14T03:05:29.859276Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "print(\"embed_query result:\")\n",
+    "res2 = embed.embed_query(\"foo\")\n",
+    "print(\"\", r[:8])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "ExecuteTime": {
+     "start_time": "2023-12-14T03:05:29.860282Z"
+    }
+   },
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.18"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "6fa70026b407ae751a5c9e6bd7f7d482379da8ad616f98512780b705c84ee157"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/libs/community/langchain_community/embeddings/__init__.py b/libs/community/langchain_community/embeddings/__init__.py
index ce9cfc7aa0b76..71f1aeee69179 100644
--- a/libs/community/langchain_community/embeddings/__init__.py
+++ b/libs/community/langchain_community/embeddings/__init__.py
@@ -78,6 +78,7 @@
 from langchain_community.embeddings.spacy_embeddings import SpacyEmbeddings
 from langchain_community.embeddings.tensorflow_hub import TensorflowHubEmbeddings
 from langchain_community.embeddings.vertexai import VertexAIEmbeddings
+from langchain_community.embeddings.bytedance_volcano import VolcanoEmbeddings
 from langchain_community.embeddings.voyageai import VoyageEmbeddings
 from langchain_community.embeddings.xinference import XinferenceEmbeddings
 
@@ -136,6 +137,7 @@
     "JohnSnowLabsEmbeddings",
     "VoyageEmbeddings",
     "BookendEmbeddings",
+    "VolcanoEmbeddings",
 ]
 
 
diff --git a/libs/community/langchain_community/embeddings/bytedance_volcano.py b/libs/community/langchain_community/embeddings/bytedance_volcano.py
new file mode 100644
index 0000000000000..cd0d7b96d515e
--- /dev/null
+++ b/libs/community/langchain_community/embeddings/bytedance_volcano.py
@@ -0,0 +1,127 @@
+from __future__ import annotations
+
+import logging
+from typing import Any, Dict, List, Optional
+
+from langchain_core.embeddings import Embeddings
+from langchain_core.pydantic_v1 import BaseModel, root_validator
+
+from langchain.utils import get_from_dict_or_env
+
+logger = logging.getLogger(__name__)
+
+
+class VolcanoEmbeddings(BaseModel, Embeddings):
+    """`Bytedance Volcano Embeddings` embedding models."""
+
+    volcano_ak: Optional[str] = None
+    """volcano access key
+    learn more from: https://www.volcengine.com/docs/6459/76491#ak-sk"""
+
+    volcano_sk: Optional[str] = None
+    """volcano secret key
+    learn more from: https://www.volcengine.com/docs/6459/76491#ak-sk"""
+
+    host: str = 'maas-api.ml-platform-cn-beijing.volces.com'
+    """host
+    learn more from https://www.volcengine.com/docs/82379/1174746"""
+    region: str = "cn-beijing"
+    """region
+    learn more from https://www.volcengine.com/docs/82379/1174746"""
+
+    model: str = "bge-large-zh"
+    """Model name
+    you could get from https://www.volcengine.com/docs/82379/1174746
+    for now, we support bge_large_zh
+    """
+
+    version: str = "1.0"
+    """ model version """
+
+    chunk_size: int = 100
+    """Chunk size when multiple texts are input"""
+
+    client: Any
+    """volcano client"""
+
+    @root_validator()
+    def validate_environment(cls, values: Dict) -> Dict:
+        """
+        Validate whether volcano_ak and volcano_sk in the environment variables or
+        configuration file are available or not.
+
+        init volcano embedding client with `ak`, `sk`, `host`, `region`
+
+        Args:
+
+            values: a dictionary containing configuration information, must include the
+            fields of volcano_ak and volcano_sk
+        Returns:
+
+            a dictionary containing configuration information. If volcano_ak and
+            volcano_sk are not provided in the environment variables or configuration
+            file,the original values will be returned; otherwise, values containing
+            volcano_ak and volcano_sk will be returned.
+        Raises:
+
+            ValueError: volcengine package not found, please install it with `pip install
+            volcengine`
+        """
+        values["volcano_ak"] = get_from_dict_or_env(
+            values,
+            "volcano_ak",
+            "VOLC_ACCESSKEY",
+        )
+        values["volcano_sk"] = get_from_dict_or_env(
+            values,
+            "volcano_sk",
+            "VOLC_SECRETKEY",
+        )
+
+        try:
+            from volcengine.maas import MaasService, MaasException
+            client = MaasService(values["host"], values["region"])
+            client.set_ak(values["volcano_ak"])
+            client.set_sk(values["volcano_sk"])
+            values["client"] = client
+        except ImportError:
+            raise ImportError(
+                "volcengine package not found, please install it with "
+                "`pip install volcengine`"
+            )
+        return values
+
+    def embed_query(self, text: str) -> List[float]:
+        return self.embed_documents([text])[0]
+
+    def embed_documents(self, texts: List[str]) -> List[List[float]]:
+        """
+        Embeds a list of text documents using the AutoVOT algorithm.
+
+        Args:
+            texts (List[str]): A list of text documents to embed.
+
+        Returns:
+            List[List[float]]: A list of embeddings for each document in the input list.
+                            Each embedding is represented as a list of float values.
+        """
+        text_in_chunks = [
+            texts[i: i + self.chunk_size]
+            for i in range(0, len(texts), self.chunk_size)
+        ]
+        lst = []
+        for chunk in text_in_chunks:
+            req = {
+                "model": {
+                    "name": self.model,
+                    "version": self.version,
+                },
+                "input": chunk,
+            }
+            try:
+                from volcengine.maas import MaasException
+                resp = self.client.embeddings(req)
+                lst.extend([res["embedding"] for res in resp["data"]])
+            except MaasException as err:
+                raise ValueError(f"Error: {err!r}")
+        return lst
diff --git a/libs/community/tests/integration_tests/embeddings/test_volcano.py b/libs/community/tests/integration_tests/embeddings/test_volcano.py
new file mode 100644
index 0000000000000..3e4411d597a5f
--- /dev/null
+++ b/libs/community/tests/integration_tests/embeddings/test_volcano.py
@@ -0,0 +1,19 @@
+"""Test Bytedance Vocalno Embedding."""
+from langchain_community.embeddings import VolcanoEmbeddings
+
+
+def test_modelscope_embedding_documents() -> None:
+    """Test modelscope embeddings for documents."""
+    documents = ["foo", "bar"]
+    embedding = VolcanoEmbeddings()
+    output = embedding.embed_documents(documents)
+    assert len(output) == 2
+    assert len(output[0]) == 1024
+
+
+def test_modelscope_embedding_query() -> None:
+    """Test modelscope embeddings for query."""
+    document = "foo bar"
+    embedding = VolcanoEmbeddings()
+    output = embedding.embed_query(document)
+    assert len(output) == 1024
diff --git a/libs/community/tests/unit_tests/embeddings/test_imports.py b/libs/community/tests/unit_tests/embeddings/test_imports.py
index d33d98e493b26..4c6e7a7ce355d 100644
--- a/libs/community/tests/unit_tests/embeddings/test_imports.py
+++ b/libs/community/tests/unit_tests/embeddings/test_imports.py
@@ -53,6 +53,7 @@
     "JohnSnowLabsEmbeddings",
     "VoyageEmbeddings",
     "BookendEmbeddings",
+    "VolcanoEmbeddings"
 ]
 
 
diff --git a/libs/langchain/langchain/embeddings/__init__.py b/libs/langchain/langchain/embeddings/__init__.py
index 3710a6e1969fa..3dc72cc1d88cd 100644
--- a/libs/langchain/langchain/embeddings/__init__.py
+++ b/libs/langchain/langchain/embeddings/__init__.py
@@ -70,6 +70,7 @@
 from langchain.embeddings.spacy_embeddings import SpacyEmbeddings
 from langchain.embeddings.tensorflow_hub import TensorflowHubEmbeddings
 from langchain.embeddings.vertexai import VertexAIEmbeddings
+from langchain.embeddings.bytedance_volcano import VolcanoEmbeddings
 from langchain.embeddings.voyageai import VoyageEmbeddings
 from langchain.embeddings.xinference import XinferenceEmbeddings
 
@@ -129,6 +130,7 @@
     "JohnSnowLabsEmbeddings",
     "VoyageEmbeddings",
     "BookendEmbeddings",
+    "VolcanoEmbeddings",
 ]
 
 
diff --git a/libs/langchain/langchain/embeddings/bytedance_volcano.py b/libs/langchain/langchain/embeddings/bytedance_volcano.py
new file mode 100644
index 0000000000000..5b8592466d049
--- /dev/null
+++ b/libs/langchain/langchain/embeddings/bytedance_volcano.py
@@ -0,0 +1,5 @@
+from langchain_community.embeddings.bytedance_volcano import (
+    VolcanoEmbeddings,
+)
+
+__all__ = ["VolcanoEmbeddings"]
diff --git a/libs/langchain/tests/unit_tests/embeddings/test_imports.py b/libs/langchain/tests/unit_tests/embeddings/test_imports.py
index 8fe5df0994a50..5bd96f6b29eda 100644
--- a/libs/langchain/tests/unit_tests/embeddings/test_imports.py
+++ b/libs/langchain/tests/unit_tests/embeddings/test_imports.py
@@ -54,6 +54,7 @@
     "JohnSnowLabsEmbeddings",
     "VoyageEmbeddings",
     "BookendEmbeddings",
+    "VolcanoEmbeddings"
 ]
 
 

From 3cc606f8a711d38da698105107e297d64bba8f1b Mon Sep 17 00:00:00 2001
From: lujingxuansc <lujingxuansc@bytedance.com>
Date: Thu, 14 Dec 2023 11:21:34 +0800
Subject: [PATCH 02/13] format

---
 libs/langchain/langchain/embeddings/__init__.py            | 2 +-
 libs/langchain/tests/unit_tests/embeddings/test_imports.py | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/libs/langchain/langchain/embeddings/__init__.py b/libs/langchain/langchain/embeddings/__init__.py
index 3dc72cc1d88cd..4fbc849bd40c7 100644
--- a/libs/langchain/langchain/embeddings/__init__.py
+++ b/libs/langchain/langchain/embeddings/__init__.py
@@ -23,6 +23,7 @@
 from langchain.embeddings.baidu_qianfan_endpoint import QianfanEmbeddingsEndpoint
 from langchain.embeddings.bedrock import BedrockEmbeddings
 from langchain.embeddings.bookend import BookendEmbeddings
+from langchain.embeddings.bytedance_volcano import VolcanoEmbeddings
 from langchain.embeddings.cache import CacheBackedEmbeddings
 from langchain.embeddings.clarifai import ClarifaiEmbeddings
 from langchain.embeddings.cohere import CohereEmbeddings
@@ -70,7 +71,6 @@
 from langchain.embeddings.spacy_embeddings import SpacyEmbeddings
 from langchain.embeddings.tensorflow_hub import TensorflowHubEmbeddings
 from langchain.embeddings.vertexai import VertexAIEmbeddings
-from langchain.embeddings.bytedance_volcano import VolcanoEmbeddings
 from langchain.embeddings.voyageai import VoyageEmbeddings
 from langchain.embeddings.xinference import XinferenceEmbeddings
 
diff --git a/libs/langchain/tests/unit_tests/embeddings/test_imports.py b/libs/langchain/tests/unit_tests/embeddings/test_imports.py
index 5bd96f6b29eda..ac89763907eef 100644
--- a/libs/langchain/tests/unit_tests/embeddings/test_imports.py
+++ b/libs/langchain/tests/unit_tests/embeddings/test_imports.py
@@ -54,7 +54,7 @@
     "JohnSnowLabsEmbeddings",
     "VoyageEmbeddings",
     "BookendEmbeddings",
-    "VolcanoEmbeddings"
+    "VolcanoEmbeddings",
 ]
 
 

From cb88740ff902622101e040682feb084d0169dcad Mon Sep 17 00:00:00 2001
From: lujingxuansc <lujingxuansc@bytedance.com>
Date: Thu, 14 Dec 2023 11:53:47 +0800
Subject: [PATCH 03/13] fix jupyter

---
 .../text_embedding/bytedance_volcano.ipynb    | 19 ++-----------------
 1 file changed, 2 insertions(+), 17 deletions(-)

diff --git a/docs/docs/integrations/text_embedding/bytedance_volcano.ipynb b/docs/docs/integrations/text_embedding/bytedance_volcano.ipynb
index 0370a934be75f..bbb3f919e01a9 100644
--- a/docs/docs/integrations/text_embedding/bytedance_volcano.ipynb
+++ b/docs/docs/integrations/text_embedding/bytedance_volcano.ipynb
@@ -1,18 +1,7 @@
 {
  "cells": [
   {
-   "cell_type": "code",
-   "execution_count": 5,
-   "outputs": [
-    {
-     "ename": "SyntaxError",
-     "evalue": "invalid syntax (3044863648.py, line 3)",
-     "output_type": "error",
-     "traceback": [
-      "\u001B[0;36m  Cell \u001B[0;32mIn[5], line 3\u001B[0;36m\u001B[0m\n\u001B[0;31m    This notebook provides you with a guide on how to load the Volcano Embedding class.\u001B[0m\n\u001B[0m         ^\u001B[0m\n\u001B[0;31mSyntaxError\u001B[0m\u001B[0;31m:\u001B[0m invalid syntax\n"
-     ]
-    }
-   ],
+   "cell_type": "raw",
    "source": [
     "# Bytedance Volcano\n",
     "\n",
@@ -31,11 +20,7 @@
     "```"
    ],
    "metadata": {
-    "collapsed": false,
-    "ExecuteTime": {
-     "end_time": "2023-12-14T03:05:29.859376Z",
-     "start_time": "2023-12-14T03:05:29.853288Z"
-    }
+    "collapsed": false
    }
   },
   {

From 2dd743551897a691ddc4bb0ae6342c49ea3a780c Mon Sep 17 00:00:00 2001
From: lujingxuansc <lujingxuansc@bytedance.com>
Date: Thu, 14 Dec 2023 11:57:35 +0800
Subject: [PATCH 04/13] fix import

---
 .../langchain_community/embeddings/bytedance_volcano.py        | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/libs/community/langchain_community/embeddings/bytedance_volcano.py b/libs/community/langchain_community/embeddings/bytedance_volcano.py
index cd0d7b96d515e..59726ee847382 100644
--- a/libs/community/langchain_community/embeddings/bytedance_volcano.py
+++ b/libs/community/langchain_community/embeddings/bytedance_volcano.py
@@ -5,8 +5,7 @@
 
 from langchain_core.embeddings import Embeddings
 from langchain_core.pydantic_v1 import BaseModel, root_validator
-
-from langchain.utils import get_from_dict_or_env
+from langchain_core.utils import get_from_dict_or_env
 
 logger = logging.getLogger(__name__)
 

From d149c33d24ad19ca8fa87fb2ffdb96e3cf682f1c Mon Sep 17 00:00:00 2001
From: lujingxuansc <lujingxuansc@bytedance.com>
Date: Thu, 14 Dec 2023 12:01:26 +0800
Subject: [PATCH 05/13] delete no used import

---
 .../langchain_community/embeddings/bytedance_volcano.py         | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/libs/community/langchain_community/embeddings/bytedance_volcano.py b/libs/community/langchain_community/embeddings/bytedance_volcano.py
index 59726ee847382..eb267c64d342d 100644
--- a/libs/community/langchain_community/embeddings/bytedance_volcano.py
+++ b/libs/community/langchain_community/embeddings/bytedance_volcano.py
@@ -78,7 +78,7 @@ def validate_environment(cls, values: Dict) -> Dict:
         )
 
         try:
-            from volcengine.maas import MaasService, MaasException
+            from volcengine.maas import MaasService
             client = MaasService(values["host"], values["region"])
             client.set_ak(values["volcano_ak"])
             client.set_sk(values["volcano_sk"])

From 16cbeeec3e29c6113d28c7797ec23dd08420de26 Mon Sep 17 00:00:00 2001
From: lujingxuansc <lujingxuansc@bytedance.com>
Date: Thu, 14 Dec 2023 12:07:09 +0800
Subject: [PATCH 06/13] fix line too long

---
 .../langchain_community/embeddings/bytedance_volcano.py       | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/libs/community/langchain_community/embeddings/bytedance_volcano.py b/libs/community/langchain_community/embeddings/bytedance_volcano.py
index eb267c64d342d..1f3f26e0c4471 100644
--- a/libs/community/langchain_community/embeddings/bytedance_volcano.py
+++ b/libs/community/langchain_community/embeddings/bytedance_volcano.py
@@ -63,8 +63,8 @@ def validate_environment(cls, values: Dict) -> Dict:
             volcano_ak and volcano_sk will be returned.
         Raises:
 
-            ValueError: volcengine package not found, please install it with `pip install
-            volcengine`
+            ValueError: volcengine package not found, please install it with
+            `pip install volcengine`
         """
         values["volcano_ak"] = get_from_dict_or_env(
             values,

From 0ad53cf03f568e290e064d5e3cb294a09378c66a Mon Sep 17 00:00:00 2001
From: lujingxuansc <lujingxuansc@bytedance.com>
Date: Thu, 14 Dec 2023 12:11:42 +0800
Subject: [PATCH 07/13] format

---
 libs/community/langchain_community/embeddings/__init__.py   | 2 +-
 .../langchain_community/embeddings/bytedance_volcano.py     | 6 ++++--
 libs/community/tests/unit_tests/embeddings/test_imports.py  | 2 +-
 3 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/libs/community/langchain_community/embeddings/__init__.py b/libs/community/langchain_community/embeddings/__init__.py
index 71f1aeee69179..f8c34f4b48353 100644
--- a/libs/community/langchain_community/embeddings/__init__.py
+++ b/libs/community/langchain_community/embeddings/__init__.py
@@ -25,6 +25,7 @@
 )
 from langchain_community.embeddings.bedrock import BedrockEmbeddings
 from langchain_community.embeddings.bookend import BookendEmbeddings
+from langchain_community.embeddings.bytedance_volcano import VolcanoEmbeddings
 from langchain_community.embeddings.clarifai import ClarifaiEmbeddings
 from langchain_community.embeddings.cohere import CohereEmbeddings
 from langchain_community.embeddings.dashscope import DashScopeEmbeddings
@@ -78,7 +79,6 @@
 from langchain_community.embeddings.spacy_embeddings import SpacyEmbeddings
 from langchain_community.embeddings.tensorflow_hub import TensorflowHubEmbeddings
 from langchain_community.embeddings.vertexai import VertexAIEmbeddings
-from langchain_community.embeddings.bytedance_volcano import VolcanoEmbeddings
 from langchain_community.embeddings.voyageai import VoyageEmbeddings
 from langchain_community.embeddings.xinference import XinferenceEmbeddings
 
diff --git a/libs/community/langchain_community/embeddings/bytedance_volcano.py b/libs/community/langchain_community/embeddings/bytedance_volcano.py
index 1f3f26e0c4471..5cb43e6f54589 100644
--- a/libs/community/langchain_community/embeddings/bytedance_volcano.py
+++ b/libs/community/langchain_community/embeddings/bytedance_volcano.py
@@ -21,7 +21,7 @@ class VolcanoEmbeddings(BaseModel, Embeddings):
     """volcano secret key
     learn more from: https://www.volcengine.com/docs/6459/76491#ak-sk"""
 
-    host: str = 'maas-api.ml-platform-cn-beijing.volces.com'
+    host: str = "maas-api.ml-platform-cn-beijing.volces.com"
     """host
     learn more from https://www.volcengine.com/docs/82379/1174746"""
     region: str = "cn-beijing"
@@ -79,6 +79,7 @@ def validate_environment(cls, values: Dict) -> Dict:
 
         try:
             from volcengine.maas import MaasService
+
             client = MaasService(values["host"], values["region"])
             client.set_ak(values["volcano_ak"])
             client.set_sk(values["volcano_sk"])
@@ -105,7 +106,7 @@ def embed_documents(self, texts: List[str]) -> List[List[float]]:
                             Each embedding is represented as a list of float values.
         """
         text_in_chunks = [
-            texts[i: i + self.chunk_size]
+            texts[i : i + self.chunk_size]
             for i in range(0, len(texts), self.chunk_size)
         ]
         lst = []
@@ -119,6 +120,7 @@ def embed_documents(self, texts: List[str]) -> List[List[float]]:
             }
             try:
                 from volcengine.maas import MaasException
+
                 resp = self.client.embeddings(req)
                 lst.extend([res["embedding"] for res in resp["data"]])
             except MaasException as err:
diff --git a/libs/community/tests/unit_tests/embeddings/test_imports.py b/libs/community/tests/unit_tests/embeddings/test_imports.py
index 4c6e7a7ce355d..cd91e675da5be 100644
--- a/libs/community/tests/unit_tests/embeddings/test_imports.py
+++ b/libs/community/tests/unit_tests/embeddings/test_imports.py
@@ -53,7 +53,7 @@
     "JohnSnowLabsEmbeddings",
     "VoyageEmbeddings",
     "BookendEmbeddings",
-    "VolcanoEmbeddings"
+    "VolcanoEmbeddings",
 ]
 
 

From a0874638e5afa49affc8790099b7d2f2c064cc86 Mon Sep 17 00:00:00 2001
From: lujingxuansc <lujingxuansc@bytedance.com>
Date: Mon, 18 Dec 2023 10:35:48 +0800
Subject: [PATCH 08/13] delete from langchain package

---
 .../tests/integration_tests/embeddings/test_volcano.py    | 8 ++++----
 libs/langchain/langchain/embeddings/__init__.py           | 2 --
 libs/langchain/langchain/embeddings/bytedance_volcano.py  | 5 -----
 .../langchain/tests/unit_tests/embeddings/test_imports.py | 1 -
 4 files changed, 4 insertions(+), 12 deletions(-)
 delete mode 100644 libs/langchain/langchain/embeddings/bytedance_volcano.py

diff --git a/libs/community/tests/integration_tests/embeddings/test_volcano.py b/libs/community/tests/integration_tests/embeddings/test_volcano.py
index 3e4411d597a5f..2916ff12b7242 100644
--- a/libs/community/tests/integration_tests/embeddings/test_volcano.py
+++ b/libs/community/tests/integration_tests/embeddings/test_volcano.py
@@ -2,8 +2,8 @@
 from langchain_community.embeddings import VolcanoEmbeddings
 
 
-def test_modelscope_embedding_documents() -> None:
-    """Test modelscope embeddings for documents."""
+def test_embedding_documents() -> None:
+    """Test embeddings for documents."""
     documents = ["foo", "bar"]
     embedding = VolcanoEmbeddings()
     output = embedding.embed_documents(documents)
@@ -11,8 +11,8 @@ def test_modelscope_embedding_documents() -> None:
     assert len(output[0]) == 1024
 
 
-def test_modelscope_embedding_query() -> None:
-    """Test modelscope embeddings for query."""
+def test_embedding_query() -> None:
+    """Test embeddings for query."""
     document = "foo bar"
     embedding = VolcanoEmbeddings()
     output = embedding.embed_query(document)
diff --git a/libs/langchain/langchain/embeddings/__init__.py b/libs/langchain/langchain/embeddings/__init__.py
index 4fbc849bd40c7..3710a6e1969fa 100644
--- a/libs/langchain/langchain/embeddings/__init__.py
+++ b/libs/langchain/langchain/embeddings/__init__.py
@@ -23,7 +23,6 @@
 from langchain.embeddings.baidu_qianfan_endpoint import QianfanEmbeddingsEndpoint
 from langchain.embeddings.bedrock import BedrockEmbeddings
 from langchain.embeddings.bookend import BookendEmbeddings
-from langchain.embeddings.bytedance_volcano import VolcanoEmbeddings
 from langchain.embeddings.cache import CacheBackedEmbeddings
 from langchain.embeddings.clarifai import ClarifaiEmbeddings
 from langchain.embeddings.cohere import CohereEmbeddings
@@ -130,7 +129,6 @@
     "JohnSnowLabsEmbeddings",
     "VoyageEmbeddings",
     "BookendEmbeddings",
-    "VolcanoEmbeddings",
 ]
 
 
diff --git a/libs/langchain/langchain/embeddings/bytedance_volcano.py b/libs/langchain/langchain/embeddings/bytedance_volcano.py
deleted file mode 100644
index 5b8592466d049..0000000000000
--- a/libs/langchain/langchain/embeddings/bytedance_volcano.py
+++ /dev/null
@@ -1,5 +0,0 @@
-from langchain_community.embeddings.bytedance_volcano import (
-    VolcanoEmbeddings,
-)
-
-__all__ = ["VolcanoEmbeddings"]
diff --git a/libs/langchain/tests/unit_tests/embeddings/test_imports.py b/libs/langchain/tests/unit_tests/embeddings/test_imports.py
index ac89763907eef..8fe5df0994a50 100644
--- a/libs/langchain/tests/unit_tests/embeddings/test_imports.py
+++ b/libs/langchain/tests/unit_tests/embeddings/test_imports.py
@@ -54,7 +54,6 @@
     "JohnSnowLabsEmbeddings",
     "VoyageEmbeddings",
     "BookendEmbeddings",
-    "VolcanoEmbeddings",
 ]
 
 

From acc3e51115699f5749f5058e8b87f852bf3ad631 Mon Sep 17 00:00:00 2001
From: lujingxuansc <lujingxuansc@bytedance.com>
Date: Mon, 18 Dec 2023 10:58:04 +0800
Subject: [PATCH 09/13] fix name

---
 ...tedance_volcano.ipynb => volcengine.ipynb} | 19 +++++++++++--------
 .../embeddings/__init__.py                    |  2 +-
 .../{bytedance_volcano.py => volcengine.py}   |  2 +-
 3 files changed, 13 insertions(+), 10 deletions(-)
 rename docs/docs/integrations/text_embedding/{bytedance_volcano.ipynb => volcengine.ipynb} (86%)
 rename libs/community/langchain_community/embeddings/{bytedance_volcano.py => volcengine.py} (98%)

diff --git a/docs/docs/integrations/text_embedding/bytedance_volcano.ipynb b/docs/docs/integrations/text_embedding/volcengine.ipynb
similarity index 86%
rename from docs/docs/integrations/text_embedding/bytedance_volcano.ipynb
rename to docs/docs/integrations/text_embedding/volcengine.ipynb
index bbb3f919e01a9..d3a5fa6c2c03c 100644
--- a/docs/docs/integrations/text_embedding/bytedance_volcano.ipynb
+++ b/docs/docs/integrations/text_embedding/volcengine.ipynb
@@ -1,16 +1,22 @@
 {
  "cells": [
   {
-   "cell_type": "raw",
+   "cell_type": "markdown",
+   "metadata": {
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
    "source": [
-    "# Bytedance Volcano\n",
+    "# Volc Engine\n",
     "\n",
     "This notebook provides you with a guide on how to load the Volcano Embedding class.\n",
     "\n",
     "\n",
     "## API Initialization\n",
     "\n",
-    "To use the LLM services based on [Bytedance Volcano](https://www.volcengine.com/docs/82379/1099455), you have to initialize these parameters:\n",
+    "To use the LLM services based on [VolcEngine](https://www.volcengine.com/docs/82379/1099455), you have to initialize these parameters:\n",
     "\n",
     "You could either choose to init the AK,SK in environment variables or init params:\n",
     "\n",
@@ -18,10 +24,7 @@
     "export VOLC_ACCESSKEY=XXX\n",
     "export VOLC_SECRETKEY=XXX\n",
     "```"
-   ],
-   "metadata": {
-    "collapsed": false
-   }
+   ]
   },
   {
    "cell_type": "code",
@@ -39,7 +42,7 @@
     "from langchain.embeddings import VolcanoEmbeddings\n",
     "\n",
     "os.environ[\"VOLC_ACCESSKEY\"] = \"\"\n",
-    "os.environ[\"VOLC_SECRETKEY\"] = \"==\"\n",
+    "os.environ[\"VOLC_SECRETKEY\"] = \"\"\n",
     "\n",
     "embed = VolcanoEmbeddings(\n",
     "    # volcano_ak='xxx',\n",
diff --git a/libs/community/langchain_community/embeddings/__init__.py b/libs/community/langchain_community/embeddings/__init__.py
index f8c34f4b48353..75c70d1740617 100644
--- a/libs/community/langchain_community/embeddings/__init__.py
+++ b/libs/community/langchain_community/embeddings/__init__.py
@@ -25,7 +25,7 @@
 )
 from langchain_community.embeddings.bedrock import BedrockEmbeddings
 from langchain_community.embeddings.bookend import BookendEmbeddings
-from langchain_community.embeddings.bytedance_volcano import VolcanoEmbeddings
+from langchain_community.embeddings.volcengine import VolcanoEmbeddings
 from langchain_community.embeddings.clarifai import ClarifaiEmbeddings
 from langchain_community.embeddings.cohere import CohereEmbeddings
 from langchain_community.embeddings.dashscope import DashScopeEmbeddings
diff --git a/libs/community/langchain_community/embeddings/bytedance_volcano.py b/libs/community/langchain_community/embeddings/volcengine.py
similarity index 98%
rename from libs/community/langchain_community/embeddings/bytedance_volcano.py
rename to libs/community/langchain_community/embeddings/volcengine.py
index 5cb43e6f54589..300df91de03da 100644
--- a/libs/community/langchain_community/embeddings/bytedance_volcano.py
+++ b/libs/community/langchain_community/embeddings/volcengine.py
@@ -11,7 +11,7 @@
 
 
 class VolcanoEmbeddings(BaseModel, Embeddings):
-    """`Bytedance Volcano Embeddings` embedding models."""
+    """`Volcengine Embeddings` embedding models."""
 
     volcano_ak: Optional[str] = None
     """volcano access key

From 69f97a7402e71a2d0b54d9e60b3ad7ae693bff51 Mon Sep 17 00:00:00 2001
From: lujingxuansc <lujingxuansc@bytedance.com>
Date: Mon, 18 Dec 2023 14:01:19 +0800
Subject: [PATCH 10/13] update doc

---
 .../text_embedding/volcengine.ipynb           | 33 +++++++++++++++----
 1 file changed, 26 insertions(+), 7 deletions(-)

diff --git a/docs/docs/integrations/text_embedding/volcengine.ipynb b/docs/docs/integrations/text_embedding/volcengine.ipynb
index d3a5fa6c2c03c..f406ac1d40946 100644
--- a/docs/docs/integrations/text_embedding/volcengine.ipynb
+++ b/docs/docs/integrations/text_embedding/volcengine.ipynb
@@ -28,25 +28,35 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {
     "ExecuteTime": {
      "start_time": "2023-12-14T03:05:29.857798Z"
     }
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "embed_documents result:\n",
+      " [0.02929673343896866, -0.009310632012784481, -0.060323506593704224, 0.0031018739100545645, -0.002218986628577113, -0.0023125179577618837, -0.04864659160375595, -2.062115163425915e-05]\n",
+      " [0.01987231895327568, -0.026041055098176003, -0.08395249396562576, 0.020043574273586273, -0.028862033039331436, 0.004629664588719606, -0.023107370361685753, -0.0342753604054451]\n"
+     ]
+    }
+   ],
    "source": [
     "\"\"\"For basic init and call\"\"\"\n",
     "import os\n",
     "\n",
-    "from langchain.embeddings import VolcanoEmbeddings\n",
+    "from langchain_community.embeddings import VolcanoEmbeddings\n",
     "\n",
     "os.environ[\"VOLC_ACCESSKEY\"] = \"\"\n",
     "os.environ[\"VOLC_SECRETKEY\"] = \"\"\n",
     "\n",
     "embed = VolcanoEmbeddings(\n",
-    "    # volcano_ak='xxx',\n",
-    "    # volcano_sk='xxx'\n",
+    "    volcano_ak='',\n",
+    "    volcano_sk=''\n",
     ")\n",
     "\n",
     "print(\"embed_documents result:\")\n",
@@ -57,13 +67,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "metadata": {
     "ExecuteTime": {
      "start_time": "2023-12-14T03:05:29.859276Z"
     }
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "embed_query result:\n",
+      " [0.01987231895327568, -0.026041055098176003, -0.08395249396562576, 0.020043574273586273, -0.028862033039331436, 0.004629664588719606, -0.023107370361685753, -0.0342753604054451]\n"
+     ]
+    }
+   ],
    "source": [
     "print(\"embed_query result:\")\n",
     "res2 = embed.embed_query(\"foo\")\n",

From 70c7e766afeb066bf38b3be8ecf39476de1e0da3 Mon Sep 17 00:00:00 2001
From: lujingxuansc <lujingxuansc@bytedance.com>
Date: Mon, 18 Dec 2023 14:06:40 +0800
Subject: [PATCH 11/13] format

---
 libs/community/langchain_community/embeddings/__init__.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/libs/community/langchain_community/embeddings/__init__.py b/libs/community/langchain_community/embeddings/__init__.py
index 75c70d1740617..3ae7e8ac4f4e7 100644
--- a/libs/community/langchain_community/embeddings/__init__.py
+++ b/libs/community/langchain_community/embeddings/__init__.py
@@ -25,7 +25,6 @@
 )
 from langchain_community.embeddings.bedrock import BedrockEmbeddings
 from langchain_community.embeddings.bookend import BookendEmbeddings
-from langchain_community.embeddings.volcengine import VolcanoEmbeddings
 from langchain_community.embeddings.clarifai import ClarifaiEmbeddings
 from langchain_community.embeddings.cohere import CohereEmbeddings
 from langchain_community.embeddings.dashscope import DashScopeEmbeddings
@@ -79,6 +78,7 @@
 from langchain_community.embeddings.spacy_embeddings import SpacyEmbeddings
 from langchain_community.embeddings.tensorflow_hub import TensorflowHubEmbeddings
 from langchain_community.embeddings.vertexai import VertexAIEmbeddings
+from langchain_community.embeddings.volcengine import VolcanoEmbeddings
 from langchain_community.embeddings.voyageai import VoyageEmbeddings
 from langchain_community.embeddings.xinference import XinferenceEmbeddings
 

From 642280101a6daa78ada9c4dce3f6a41a0c8ede9d Mon Sep 17 00:00:00 2001
From: lujingxuansc <lujingxuansc@bytedance.com>
Date: Mon, 18 Dec 2023 14:10:31 +0800
Subject: [PATCH 12/13] format

---
 .../docs/integrations/text_embedding/volcengine.ipynb | 11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

diff --git a/docs/docs/integrations/text_embedding/volcengine.ipynb b/docs/docs/integrations/text_embedding/volcengine.ipynb
index f406ac1d40946..c32bfb53aeecb 100644
--- a/docs/docs/integrations/text_embedding/volcengine.ipynb
+++ b/docs/docs/integrations/text_embedding/volcengine.ipynb
@@ -3,10 +3,7 @@
   {
    "cell_type": "markdown",
    "metadata": {
-    "collapsed": false,
-    "jupyter": {
-     "outputs_hidden": false
-    }
+    "collapsed": false
    },
    "source": [
     "# Volc Engine\n",
@@ -54,11 +51,7 @@
     "os.environ[\"VOLC_ACCESSKEY\"] = \"\"\n",
     "os.environ[\"VOLC_SECRETKEY\"] = \"\"\n",
     "\n",
-    "embed = VolcanoEmbeddings(\n",
-    "    volcano_ak='',\n",
-    "    volcano_sk=''\n",
-    ")\n",
-    "\n",
+    "embed = VolcanoEmbeddings(volcano_ak=\"\", volcano_sk=\"\")\n",
     "print(\"embed_documents result:\")\n",
     "res1 = embed.embed_documents([\"foo\", \"bar\"])\n",
     "for r in res1:\n",

From eea5d7f7816d63882571ec859c2d87191244190f Mon Sep 17 00:00:00 2001
From: lujingxuansc <lujingxuansc@bytedance.com>
Date: Thu, 21 Dec 2023 19:33:22 +0800
Subject: [PATCH 13/13] fix err

---
 libs/community/langchain_community/embeddings/volcengine.py   | 4 ++--
 .../tests/integration_tests/embeddings/test_volcano.py        | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/libs/community/langchain_community/embeddings/volcengine.py b/libs/community/langchain_community/embeddings/volcengine.py
index 300df91de03da..98ac729b96807 100644
--- a/libs/community/langchain_community/embeddings/volcengine.py
+++ b/libs/community/langchain_community/embeddings/volcengine.py
@@ -123,6 +123,6 @@ def embed_documents(self, texts: List[str]) -> List[List[float]]:
 
                 resp = self.client.embeddings(req)
                 lst.extend([res["embedding"] for res in resp["data"]])
-            except MaasException as err:
-                raise ValueError(f"Error: {err!r}")
+            except MaasException as e:
+                raise ValueError(f"embed by volcengine Error: {e}")
         return lst
diff --git a/libs/community/tests/integration_tests/embeddings/test_volcano.py b/libs/community/tests/integration_tests/embeddings/test_volcano.py
index 2916ff12b7242..7ef7ac33fa46b 100644
--- a/libs/community/tests/integration_tests/embeddings/test_volcano.py
+++ b/libs/community/tests/integration_tests/embeddings/test_volcano.py
@@ -1,4 +1,4 @@
-"""Test Bytedance Vocalno Embedding."""
+"""Test Bytedance Volcano Embedding."""
 from langchain_community.embeddings import VolcanoEmbeddings