community[minor]: Add Clova Embeddings for LangChain Community (#21890)

- [ ] **PR title**: "Add Naver ClovaX embedding to LangChain community"
- HyperClovaX is a large language model developed by
[Naver](https://clova-x.naver.com/welcome).
It's a powerful and purpose-trained LLM.

- You can visit the embedding service provided by
[ClovaX](https://www.ncloud.com/product/aiService/clovaStudio)

- You may get CLOVA_EMB_API_KEY, CLOVA_EMB_APIGW_API_KEY,
CLOVA_EMB_APP_ID From
https://www.ncloud.com/product/aiService/clovaStudio

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>

docs/docs/integrations/text_embedding/clova.ipynb

@@ -0,0 +1,86 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Clova Embeddings\n",
+    "[Clova](https://api.ncloud-docs.com/docs/ai-naver-clovastudio-summary) offers an embeddings service\n",
+    "\n",
+    "This example goes over how to use LangChain to interact with Clova inference for text embedding.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"CLOVA_EMB_API_KEY\"] = \"\"\n",
+    "os.environ[\"CLOVA_EMB_APIGW_API_KEY\"] = \"\"\n",
+    "os.environ[\"CLOVA_EMB_APP_ID\"] = \"\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.embeddings import ClovaEmbeddings"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "embeddings = ClovaEmbeddings()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query_text = \"This is a test query.\"\n",
+    "query_result = embeddings.embed_query(query_text)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "document_text = [\"This is a test doc1.\", \"This is a test doc2.\"]\n",
+    "document_result = embeddings.embed_documents([document_text])"
+   ]
+  }
+ ],
+ "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": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

libs/community/langchain_community/embeddings/__init__.py

@@ -43,6 +43,9 @@ if TYPE_CHECKING:
     from langchain_community.embeddings.clarifai import (
         ClarifaiEmbeddings,
     )
+    from langchain_community.embeddings.clova import (
+        ClovaEmbeddings,
+    )
     from langchain_community.embeddings.cohere import (
         CohereEmbeddings,
     )
@@ -232,6 +235,7 @@ __all__ = [
     "BedrockEmbeddings",
     "BookendEmbeddings",
     "ClarifaiEmbeddings",
+    "ClovaEmbeddings",
     "CohereEmbeddings",
     "DashScopeEmbeddings",
     "DatabricksEmbeddings",
@@ -309,6 +313,7 @@ _module_lookup = {
     "BedrockEmbeddings": "langchain_community.embeddings.bedrock",
     "BookendEmbeddings": "langchain_community.embeddings.bookend",
     "ClarifaiEmbeddings": "langchain_community.embeddings.clarifai",
+    "ClovaEmbeddings": "langchain_community.embeddings.clova",
     "CohereEmbeddings": "langchain_community.embeddings.cohere",
     "DashScopeEmbeddings": "langchain_community.embeddings.dashscope",
     "DatabricksEmbeddings": "langchain_community.embeddings.databricks",

libs/community/langchain_community/embeddings/clova.py

@@ -0,0 +1,134 @@
+from __future__ import annotations
+
+from typing import Dict, List, Optional, cast
+
+import requests
+from langchain_core.embeddings import Embeddings
+from langchain_core.pydantic_v1 import BaseModel, Extra, SecretStr, root_validator
+from langchain_core.utils import convert_to_secret_str, get_from_dict_or_env
+
+
+class ClovaEmbeddings(BaseModel, Embeddings):
+    """
+    Clova's embedding service.
+
+    To use this service,
+
+    you should have the following environment variables
+    set with your API tokens and application ID,
+    or pass them as named parameters to the constructor:
+
+    - ``CLOVA_EMB_API_KEY``: API key for accessing Clova's embedding service.
+    - ``CLOVA_EMB_APIGW_API_KEY``: API gateway key for enhanced security.
+    - ``CLOVA_EMB_APP_ID``: Application ID for identifying your application.
+
+    Example:
+        .. code-block:: python
+
+            from langchain_community.embeddings import ClovaEmbeddings
+            embeddings = ClovaEmbeddings(
+                clova_emb_api_key='your_clova_emb_api_key',
+                clova_emb_apigw_api_key='your_clova_emb_apigw_api_key',
+                app_id='your_app_id'
+            )
+
+            query_text = "This is a test query."
+            query_result = embeddings.embed_query(query_text)
+
+            document_text = "This is a test document."
+            document_result = embeddings.embed_documents([document_text])
+
+    """
+
+    endpoint_url: str = (
+        "https://clovastudio.apigw.ntruss.com/testapp/v1/api-tools/embedding"
+    )
+    """Endpoint URL to use."""
+    model: str = "clir-emb-dolphin"
+    """Embedding model name to use."""
+    clova_emb_api_key: Optional[SecretStr] = None
+    """API key for accessing Clova's embedding service."""
+    clova_emb_apigw_api_key: Optional[SecretStr] = None
+    """API gateway key for enhanced security."""
+    app_id: Optional[SecretStr] = None
+    """Application ID for identifying your application."""
+
+    class Config:
+        extra = Extra.forbid
+
+    @root_validator(pre=True, allow_reuse=True)
+    def validate_environment(cls, values: Dict) -> Dict:
+        """Validate api key exists in environment."""
+        values["clova_emb_api_key"] = convert_to_secret_str(
+            get_from_dict_or_env(values, "clova_emb_api_key", "CLOVA_EMB_API_KEY")
+        )
+        values["clova_emb_apigw_api_key"] = convert_to_secret_str(
+            get_from_dict_or_env(
+                values, "clova_emb_apigw_api_key", "CLOVA_EMB_APIGW_API_KEY"
+            )
+        )
+        values["app_id"] = convert_to_secret_str(
+            get_from_dict_or_env(values, "app_id", "CLOVA_EMB_APP_ID")
+        )
+        return values
+
+    def embed_documents(self, texts: List[str]) -> List[List[float]]:
+        """
+        Embed a list of texts and return their embeddings.
+
+        Args:
+            texts: The list of texts to embed.
+
+        Returns:
+            List of embeddings, one for each text.
+        """
+        embeddings = []
+        for text in texts:
+            embeddings.append(self._embed_text(text))
+        return embeddings
+
+    def embed_query(self, text: str) -> List[float]:
+        """
+        Embed a single query text and return its embedding.
+
+        Args:
+            text: The text to embed.
+
+        Returns:
+            Embeddings for the text.
+        """
+        return self._embed_text(text)
+
+    def _embed_text(self, text: str) -> List[float]:
+        """
+        Internal method to call the embedding API and handle the response.
+        """
+        payload = {"text": text}
+
+        # HTTP headers for authorization
+        headers = {
+            "X-NCP-CLOVASTUDIO-API-KEY": cast(
+                SecretStr, self.clova_emb_api_key
+            ).get_secret_value(),
+            "X-NCP-APIGW-API-KEY": cast(
+                SecretStr, self.clova_emb_apigw_api_key
+            ).get_secret_value(),
+            "Content-Type": "application/json",
+        }
+
+        # send request
+        app_id = cast(SecretStr, self.app_id).get_secret_value()
+        response = requests.post(
+            f"{self.endpoint_url}/{self.model}/{app_id}",
+            headers=headers,
+            json=payload,
+        )
+
+        # check for errors
+        if response.status_code == 200:
+            response_data = response.json()
+            if "result" in response_data and "embedding" in response_data["result"]:
+                return response_data["result"]["embedding"]
+        raise ValueError(
+            f"API request failed with status {response.status_code}: {response.text}"
+        )

libs/community/tests/unit_tests/embeddings/test_imports.py

@@ -1,6 +1,7 @@
 from langchain_community.embeddings import __all__, _module_lookup
 
 EXPECTED_ALL = [
+    "ClovaEmbeddings",
     "OpenAIEmbeddings",
     "AnyscaleEmbeddings",
     "AzureOpenAIEmbeddings",