feat: add Google embedding support & update setup (#550) bump:patch

libs/kotaemon/kotaemon/embeddings/__init__.py

@@ -4,6 +4,7 @@ from .fastembed import FastEmbedEmbeddings
 from .langchain_based import (
     LCAzureOpenAIEmbeddings,
     LCCohereEmbeddings,
+    LCGoogleEmbeddings,
     LCHuggingFaceEmbeddings,
     LCOpenAIEmbeddings,
 )
@@ -18,6 +19,7 @@ __all__ = [
     "LCAzureOpenAIEmbeddings",
     "LCCohereEmbeddings",
     "LCHuggingFaceEmbeddings",
+    "LCGoogleEmbeddings",
     "OpenAIEmbeddings",
     "AzureOpenAIEmbeddings",
     "FastEmbedEmbeddings",

libs/kotaemon/kotaemon/embeddings/langchain_based.py

@@ -219,3 +219,38 @@ class LCHuggingFaceEmbeddings(LCEmbeddingMixin, BaseEmbeddings):
             from langchain.embeddings import HuggingFaceBgeEmbeddings
 
         return HuggingFaceBgeEmbeddings
+
+
+class LCGoogleEmbeddings(LCEmbeddingMixin, BaseEmbeddings):
+    """Wrapper around Langchain's Google GenAI embedding, focusing on key parameters"""
+
+    google_api_key: str = Param(
+        help="API key (https://aistudio.google.com/app/apikey)",
+        default=None,
+        required=True,
+    )
+    model: str = Param(
+        help="Model name to use (https://ai.google.dev/gemini-api/docs/models/gemini#text-embedding-and-embedding)",  # noqa
+        default="models/text-embedding-004",
+        required=True,
+    )
+
+    def __init__(
+        self,
+        model: str = "models/text-embedding-004",
+        google_api_key: Optional[str] = None,
+        **params,
+    ):
+        super().__init__(
+            model=model,
+            google_api_key=google_api_key,
+            **params,
+        )
+
+    def _get_lc_class(self):
+        try:
+            from langchain_google_genai import GoogleGenerativeAIEmbeddings
+        except ImportError:
+            raise ImportError("Please install langchain-google-genai")
+
+        return GoogleGenerativeAIEmbeddings