Fix disallowed_special parameter and refactor CharacterTextSplitterComponent (#1410)

This pull request fixes the disallowed_special parameter in the OpenAIEmbeddingsComponent and refactors the CharacterTextSplitterComponent to use typing and update the return value. It also updates the ChromaComponent configuration and bumps the version to 0.6.7a1 in pyproject.toml.

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "langflow"
-version = "0.6.6"
+version = "0.6.7a1"
 description = "A Python package with a built-in web application"
 authors = ["Logspace <contact@logspace.ai>"]
 maintainers = [

src/backend/langflow/components/embeddings/OpenAIEmbeddings.py

@@ -95,12 +95,15 @@ class OpenAIEmbeddingsComponent(CustomComponent):
         tikToken_enable: bool = True,
         tiktoken_model_name: Optional[str] = None,
     ) -> Union[OpenAIEmbeddings, Callable]:
+        # This is to avoid errors with Vector Stores (e.g Chroma)
+        if disallowed_special == ["all"]:
+            disallowed_special = "all"
         return OpenAIEmbeddings(
             tiktoken_enabled=tikToken_enable,
             default_headers=default_headers,
             default_query=default_query,
             allowed_special=set(allowed_special),
-            disallowed_special=set(disallowed_special),
+            disallowed_special="all",
             chunk_size=chunk_size,
             client=client,
             deployment=deployment,

src/backend/langflow/components/textsplitters/CharacterTextSplitter.py

@@ -1,7 +1,8 @@
-from langflow import CustomComponent
+from typing import List
+
 from langchain.text_splitter import CharacterTextSplitter
 from langchain_core.documents.base import Document
-from typing import List
+from langflow import CustomComponent
 
 
 class CharacterTextSplitterComponent(CustomComponent):
@@ -23,8 +24,10 @@ class CharacterTextSplitterComponent(CustomComponent):
         chunk_size: int = 1000,
         separator: str = "\n",
     ) -> List[Document]:
-        return CharacterTextSplitter(
+        docs = CharacterTextSplitter(
             chunk_overlap=chunk_overlap,
             chunk_size=chunk_size,
             separator=separator,
         ).split_documents(documents)
+        self.status = docs
+        return docs

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

@@ -29,7 +29,7 @@ class ChromaComponent(CustomComponent):
             "collection_name": {"display_name": "Collection Name", "value": "langflow"},
             "persist": {"display_name": "Persist"},
             "persist_directory": {"display_name": "Persist Directory"},
-            "code": {"show": False, "display_name": "Code"},
+            "code": {"advanced": True, "display_name": "Code"},
             "documents": {"display_name": "Documents", "is_list": True},
             "embedding": {"display_name": "Embedding"},
             "chroma_server_cors_allow_origins": {