refactor: Update URLComponent to include text_key in Data objects

src/backend/base/langflow/components/data/URL.py

@@ -62,6 +62,6 @@ class URLComponent(Component):
         urls = [self.ensure_url(url.strip()) for url in self.urls if url.strip()]
         loader = WebBaseLoader(web_paths=urls, encoding="utf-8")
         docs = loader.load()
-        data = [Data(text_key="text", content=doc.page_content, **doc.metadata) for doc in docs]
+        data = [Data(text=doc.page_content, **doc.metadata) for doc in docs]
         self.status = data
         return data

src/backend/base/langflow/components/experimental/SplitText.py

@@ -67,21 +67,21 @@ class SplitTextComponent(Component):
         buffer = ""
 
         for row in data:
-            text = row.data.get(text_key, "")
+            parent = row.data.get(text_key, "")
-            chunks = text.split(separator)
+            chunks = parent.split(separator)
 
             for chunk in chunks:
                 buffer += chunk
                 while len(buffer) >= max_chunk_size:
-                    results.append(Data(data={"parent": text, "text": buffer[:max_chunk_size]}))
+                    results.append(Data(data={"parent": parent, "text": buffer[:max_chunk_size]}))
                     buffer = buffer[max_chunk_size:]
                 if len(buffer) >= min_chunk_size:
-                    results.append(Data(data={"parent": text, "text": buffer}))
+                    results.append(Data(data={"parent": parent, "text": buffer}))
                     buffer = ""
 
         # Handle any remaining text that may not meet the min_chunk_size requirement
         if buffer:
-            results.append(Data(data={"parent": text, "text": buffer}))
+            results.append(Data(parent=parent, text=buffer))
 
         self.status = results
         return results

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

@@ -7,7 +7,7 @@ from loguru import logger
 
 from langflow.base.vectorstores.utils import chroma_collection_to_data
 from langflow.components.vectorstores.base.model import LCVectorStoreComponent
-from langflow.inputs import BoolInput, DropdownInput, HandleInput, IntInput, StrInput
+from langflow.inputs import BoolInput, DropdownInput, HandleInput, IntInput, StrInput, MessageInput, DataInput
 from langflow.schema import Data
 
 if TYPE_CHECKING:
@@ -39,12 +39,15 @@ class ChromaVectorStoreComponent(LCVectorStoreComponent):
             display_name="Code",
             advanced=True,
         ),
-        StrInput(
+        MessageInput(
-            name="vector_store_inputs",
+            name="search_query",
-            display_name="Vector Store Inputs",
+            display_name="Search Query",
-            input_types=["Document", "Data"],
             is_list=True,
         ),
+        DataInput(
+            name="ingest_data",
+            display_name="Ingest Data",
+        ),
         HandleInput(name="embedding", display_name="Embedding", input_types=["Embeddings"]),
         StrInput(
             name="chroma_server_cors_allow_origins",
@@ -77,27 +80,19 @@ class ChromaVectorStoreComponent(LCVectorStoreComponent):
             advanced=True,
             info="If false, will not add documents that are already in the Vector Store.",
         ),
-        BoolInput(
-            name="add_to_vector_store",
-            display_name="Add to Vector Store",
-            info="If true, the Vector Store Inputs will be added to the Vector Store.",
-        ),
-        StrInput(
-            name="search_input",
-            display_name="Search Input",
-        ),
         DropdownInput(
             name="search_type",
             display_name="Search Type",
             options=["Similarity", "MMR"],
             value="Similarity",
+            advanced=True
         ),
         IntInput(
             name="number_of_results",
             display_name="Number of Results",
             info="Number of results to return.",
             advanced=True,
-            value=4,
+            value=10,
         ),
         IntInput(
             name="limit",
@@ -144,9 +139,6 @@ class ChromaVectorStoreComponent(LCVectorStoreComponent):
             collection_name=self.collection_name,
         )
 
-        if self.add_to_vector_store:
-            self._add_documents_to_vector_store(chroma)
-
         self.status = chroma_collection_to_data(chroma.get(self.limit))
         return chroma
 
@@ -154,6 +146,10 @@ class ChromaVectorStoreComponent(LCVectorStoreComponent):
         """
         Adds documents to the Vector Store.
         """
+        if not self.ingest_data:
+            self.status = ""
+            return
+
         if self.allow_duplicates:
             stored_data = []
         else:
@@ -164,7 +160,7 @@ class ChromaVectorStoreComponent(LCVectorStoreComponent):
                 _stored_documents_without_id.append(value)
 
         documents = []
-        for _input in self.vector_store_inputs or []:
+        for _input in self.ingest_data or []:
             if isinstance(_input, Data):
                 if _input not in _stored_documents_without_id:
                     documents.append(_input.to_lc_document())
@@ -181,16 +177,23 @@ class ChromaVectorStoreComponent(LCVectorStoreComponent):
         """
         Search for documents in the Chroma vector store.
         """
-        if not self.search_input:
+        if not self.search_query.text:
+            self.status = ""
             return
 
-        vector_store = self._build_chroma()
+        vector_store = self.build_vector_store()
 
-        logger.debug(f"Search input: {self.search_input}")
+        logger.debug(f"Search input: {self.search_query}")
         logger.debug(f"Search type: {self.search_type}")
         logger.debug(f"Number of results: {self.number_of_results}")
 
+        if isinstance(self.search_query, list):
+            if len(self.search_query) > 1:
+                raise ValueError("Input value must be a single-item list.")
+            else:
+                self.search_query = self.search_query[0]
+
         search_results = self.search_with_vector_store(
-            self.input_value, self.search_type, vector_store, k=self.number_of_results
+            self.search_query.text, self.search_type, vector_store, k=self.number_of_results
         )
         return search_results

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

@@ -1,25 +1,19 @@
 from typing import List, Union
 
 from langchain_core.documents import Document
-from langchain_core.retrievers import BaseRetriever
-from langchain_core.vectorstores import VectorStore
 
 from langflow.custom import Component
 from langflow.field_typing import Text
 from langflow.helpers.data import docs_to_data
 from langflow.schema import Data
 from langflow.template import Output
+from langflow.field_typing import BaseRetriever, VectorStore
 
 
 class LCVectorStoreComponent(Component):
     outputs = [
         Output(
-            display_name="Vector Store",
+            display_name="Retriever",
-            name="vector_store",
-            method="build_vector_store",
-        ),
-        Output(
-            display_name="Base Retriever",
             name="base_retriever",
             method="build_base_retriever",
         ),

src/backend/base/langflow/inputs/__init__.py

@@ -1,5 +1,6 @@
 from .inputs import (
     BoolInput,
+    DataInput,
     DictInput,
     DropdownInput,
     FileInput,
@@ -16,18 +17,19 @@ from .inputs import (
 )
 
 __all__ = [
+    "BoolInput",
+    "DataInput",
+    "DictInput",
+    "DropdownInput",
+    "FileInput",
+    "FloatInput",
+    "HandleInput",
+    "IntInput",
+    "MessageInput",
+    "MultilineInput",
+    "NestedDictInput",
+    "PromptInput",
     "SecretStrInput",
     "StrInput",
-    "PromptInput",
-    "MultilineInput",
-    "HandleInput",
     "TextInput",
-    "BoolInput",
-    "DropdownInput",
-    "FloatInput",
-    "IntInput",
-    "DictInput",
-    "MessageInput",
-    "NestedDictInput",
-    "FileInput",
 ]

src/backend/base/langflow/inputs/inputs.py

@@ -23,9 +23,8 @@ class HandleInput(BaseInputMixin, ListableInputMixin):
     field_type: Optional[SerializableFieldTypes] = FieldTypes.OTHER
 
 
-# class DataInput(HandleInput):
+class DataInput(HandleInput):
-#     input_types: list[str] = ["Data"]
+    input_types: list[str] = ["Data"]
-# ! Let's add this?
 
 
 class PromptInput(BaseInputMixin, ListableInputMixin):
@@ -136,7 +135,7 @@ class FileInput(BaseInputMixin, ListableInputMixin, FileMixin):
 
 InputTypes = Union[
     BoolInput,
-    # DataInput, # ! Let's add this
+    DataInput,
     DictInput,
     DropdownInput,
     FileInput,