refactor: Update VectaraVectorStoreComponent to handle embedding input and add documents to vector store

src/backend/base/langflow/components/vectorstores/Vectara.py

@@ -1,30 +1,45 @@
-from typing import List
+from typing import List, TYPE_CHECKING
 
-from langchain_community.embeddings import FakeEmbeddings
 from langchain_community.vectorstores import Vectara
+from loguru import logger
 
 from langflow.base.vectorstores.model import LCVectorStoreComponent
 from langflow.helpers.data import docs_to_data
-from langflow.io import IntInput, StrInput, SecretStrInput, DataInput, MultilineInput
+from langflow.io import HandleInput, IntInput, Output, SecretStrInput, StrInput, TextInput
 from langflow.schema import Data
 
+if TYPE_CHECKING:
+    from langchain_community.vectorstores import Vectara
 
 class VectaraVectorStoreComponent(LCVectorStoreComponent):
-    display_name = "Vectara"
+    """
-    description = "Vectara Vector Store with search capabilities"
+    Vectara Vector Store with search capabilities
-    documentation = "https://python.langchain.com/v0.2/docs/integrations/vectorstores/vectara/"
+    """
+
+    display_name: str = "Vectara"
+    description: str = "Vectara Vector Store with search capabilities"
+    documentation = "https://python.langchain.com/docs/modules/data_connection/vectorstores/integrations/vectara"
     icon = "Vectara"
 
     inputs = [
         StrInput(name="vectara_customer_id", display_name="Vectara Customer ID", required=True),
         StrInput(name="vectara_corpus_id", display_name="Vectara Corpus ID", required=True),
         SecretStrInput(name="vectara_api_key", display_name="Vectara API Key", required=True),
-        MultilineInput(name="search_query", display_name="Search Query"),
+        HandleInput(
-        DataInput(
+            name="embedding",
+            display_name="Embedding",
+            input_types=["Embeddings"],
+        ),
+        HandleInput(
             name="ingest_data",
-            display_name="Vector Store Inputs",
+            display_name="Ingest Data",
+            input_types=["Document", "Data"],
             is_list=True,
         ),
+        TextInput(
+            name="search_query",
+            display_name="Search Query",
+        ),
         IntInput(
             name="number_of_results",
             display_name="Number of Results",
@@ -34,11 +49,33 @@ class VectaraVectorStoreComponent(LCVectorStoreComponent):
         ),
     ]
 
-    def build_vector_store(self) -> Vectara:
+    def build_vector_store(self) -> "Vectara":
-        return self._build_vectara()
+        """
+        Builds the Vectara object.
+        """
+        try:
+            from langchain_community.vectorstores import Vectara
+        except ImportError:
+            raise ImportError(
+                "Could not import Vectara. Please install it with `pip install langchain-community`."
+            )
 
-    def _build_vectara(self) -> Vectara:
+        vectara = Vectara(
-        source = "Langflow"
+            vectara_customer_id=self.vectara_customer_id,
+            vectara_corpus_id=self.vectara_corpus_id,
+            vectara_api_key=self.vectara_api_key,
+        )
+
+        self._add_documents_to_vector_store(vectara)
+        return vectara
+
+    def _add_documents_to_vector_store(self, vector_store: "Vectara") -> None:
+        """
+        Adds documents to the Vector Store.
+        """
+        if not self.ingest_data:
+            self.status = "No documents to add to Vectara"
+            return
 
         documents = []
         for _input in self.ingest_data or []:
@@ -48,24 +85,15 @@ class VectaraVectorStoreComponent(LCVectorStoreComponent):
                 documents.append(_input)
 
         if documents:
-            return Vectara.from_documents(
+            logger.debug(f"Adding {len(documents)} documents to Vectara.")
-                documents=documents,
+            vector_store.add_documents(documents)
-                embedding=FakeEmbeddings(size=768),
+            self.status = f"Added {len(documents)} documents to Vectara"
-                vectara_customer_id=self.vectara_customer_id,
+        else:
-                vectara_corpus_id=self.vectara_corpus_id,
+            logger.debug("No documents to add to Vectara.")
-                vectara_api_key=self.vectara_api_key,
+            self.status = "No valid documents to add to Vectara"
-                source=source,
-            )
-
-        return Vectara(
-            vectara_customer_id=self.vectara_customer_id,
-            vectara_corpus_id=self.vectara_corpus_id,
-            vectara_api_key=self.vectara_api_key,
-            source=source,
-        )
 
     def search_documents(self) -> List[Data]:
-        vector_store = self._build_vectara()
+        vector_store = self.build_vector_store()
 
         if self.search_query and isinstance(self.search_query, str) and self.search_query.strip():
             docs = vector_store.similarity_search(
@@ -74,7 +102,8 @@ class VectaraVectorStoreComponent(LCVectorStoreComponent):
             )
 
             data = docs_to_data(docs)
-            self.status = data
+            self.status = f"Found {len(data)} results for the query: {self.search_query}"
             return data
         else:
+            self.status = "No search query provided"
             return []