add text embedder component (#3663)

* add text embedder component

* [autofix.ci] apply automated fixes

* add embedding similarity component

* [autofix.ci] apply automated fixes

* change text embedder output type to data

* ✨ (similarity.spec.ts): Add end-to-end test for checking similarity between embedding texts in the frontend application.

---------

Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: cristhianzl <cristhian.lousa@gmail.com>

src/backend/base/langflow/components/embeddings/EmbeddingSimilarity.py

@@ -0,0 +1,70 @@
+from typing import List
+import numpy as np
+from langflow.custom import Component
+from langflow.io import DataInput, DropdownInput, Output
+from langflow.schema import Data
+
+
+class EmbeddingSimilarityComponent(Component):
+    display_name: str = "Embedding Similarity"
+    description: str = "Compute selected form of similarity between two embedding vectors."
+    icon = "equal"
+
+    inputs = [
+        DataInput(
+            name="embedding_vectors",
+            display_name="Embedding Vectors",
+            info="A list containing exactly two data objects with embedding vectors to compare.",
+            is_list=True,
+        ),
+        DropdownInput(
+            name="similarity_metric",
+            display_name="Similarity Metric",
+            info="Select the similarity metric to use.",
+            options=["Cosine Similarity", "Euclidean Distance", "Manhattan Distance"],
+            value="Cosine Similarity",
+        ),
+    ]
+
+    outputs = [
+        Output(display_name="Similarity Data", name="similarity_data", method="compute_similarity"),
+    ]
+
+    def compute_similarity(self) -> Data:
+        embedding_vectors: List[Data] = self.embedding_vectors
+
+        # Assert that the list contains exactly two Data objects
+        assert len(embedding_vectors) == 2, "Exactly two embedding vectors are required."
+
+        embedding_1 = np.array(embedding_vectors[0].data["embeddings"])
+        embedding_2 = np.array(embedding_vectors[1].data["embeddings"])
+
+        if embedding_1.shape != embedding_2.shape:
+            similarity_score = {"error": "Embeddings must have the same dimensions."}
+        else:
+            similarity_metric = self.similarity_metric
+
+            if similarity_metric == "Cosine Similarity":
+                score = np.dot(embedding_1, embedding_2) / (np.linalg.norm(embedding_1) * np.linalg.norm(embedding_2))
+                similarity_score = {"cosine_similarity": score}
+
+            elif similarity_metric == "Euclidean Distance":
+                score = np.linalg.norm(embedding_1 - embedding_2)
+                similarity_score = {"euclidean_distance": score}
+
+            elif similarity_metric == "Manhattan Distance":
+                score = np.sum(np.abs(embedding_1 - embedding_2))
+                similarity_score = {"manhattan_distance": score}
+
+        # Create a Data object to encapsulate the similarity score and additional information
+        similarity_data = Data(
+            data={
+                "embedding_1": embedding_vectors[0].data["embeddings"],
+                "embedding_2": embedding_vectors[1].data["embeddings"],
+                "similarity_score": similarity_score,
+            },
+            text_key="similarity_score",
+        )
+
+        self.status = similarity_data
+        return similarity_data

src/backend/base/langflow/components/embeddings/GoogleGenerativeAIEmbeddings.py

@@ -19,11 +19,11 @@ import numpy as np
 
 
 class GoogleGenerativeAIEmbeddingsComponent(Component):
-    display_name = "Google GenerativeAI Embeddings"
+    display_name = "Google Generative AI Embeddings"
     description = "Connect to Google's generative AI embeddings service using the GoogleGenerativeAIEmbeddings class, found in the langchain-google-genai package."
     documentation: str = "https://python.langchain.com/v0.2/docs/integrations/text_embedding/google_generative_ai/"
     icon = "Google"
-    name = "Google GenerativeAI Embeddings"
+    name = "Google Generative AI Embeddings"
 
     inputs = [
         SecretStrInput(name="api_key", display_name="API Key"),

src/backend/base/langflow/components/embeddings/TextEmbedder.py

@@ -0,0 +1,51 @@
+from langflow.custom import Component
+from langflow.io import HandleInput, MessageInput, Output
+from langflow.field_typing import Embeddings
+from langflow.schema.message import Message
+from langflow.schema import Data
+
+
+class TextEmbedderComponent(Component):
+    display_name: str = "Text Embedder"
+    description: str = "Generate embeddings for a given message using the specified embedding model."
+    icon = "binary"
+
+    inputs = [
+        HandleInput(
+            name="embedding_model",
+            display_name="Embedding Model",
+            info="The embedding model to use for generating embeddings.",
+            input_types=["Embeddings"],
+        ),
+        MessageInput(
+            name="message",
+            display_name="Message",
+            info="The message to generate embeddings for.",
+        ),
+    ]
+
+    outputs = [
+        Output(display_name="Embedding Data", name="embeddings", method="generate_embeddings"),
+    ]
+
+    def generate_embeddings(self) -> Data:
+        embedding_model: Embeddings = self.embedding_model
+        message: Message = self.message
+
+        # Extract the text content from the message
+        text_content = message.text
+
+        # Generate embeddings using the provided embedding model
+        embeddings = embedding_model.embed_documents([text_content])
+
+        # Assuming the embedding model returns a list of embeddings, we take the first one
+        if embeddings:
+            embedding_vector = embeddings[0]
+        else:
+            embedding_vector = []
+
+        # Create a Data object to encapsulate the results
+        result_data = Data(data={"text": text_content, "embeddings": embedding_vector})
+
+        self.status = {"text": text_content, "embeddings": embedding_vector}
+        return result_data