From a03e21018a7fa1a99d2a38e6019c5f1338c4cf43 Mon Sep 17 00:00:00 2001
From: Gabriel Luiz Freitas Almeida <gabriel@langflow.org>
Date: Thu, 26 Jun 2025 13:34:35 -0300
Subject: [PATCH] refactor(chunk_documents): move optional imports inside
 method with error handling (#8750)

fix: handle ImportError for optional chunkers and tokenizers in ChunkDoclingDocumentComponent
---
 .../docling/chunk_docling_document.py         | 28 +++++++++++++++++--
 1 file changed, 25 insertions(+), 3 deletions(-)

diff --git a/src/backend/base/langflow/components/docling/chunk_docling_document.py b/src/backend/base/langflow/components/docling/chunk_docling_document.py
index ae920021e..1ffadc35d 100644
--- a/src/backend/base/langflow/components/docling/chunk_docling_document.py
+++ b/src/backend/base/langflow/components/docling/chunk_docling_document.py
@@ -3,9 +3,6 @@ import json
 import tiktoken
 from docling_core.transforms.chunker import BaseChunker, DocMeta
 from docling_core.transforms.chunker.hierarchical_chunker import HierarchicalChunker
-from docling_core.transforms.chunker.hybrid_chunker import HybridChunker
-from docling_core.transforms.chunker.tokenizer.huggingface import HuggingFaceTokenizer
-from docling_core.transforms.chunker.tokenizer.openai import OpenAITokenizer
 
 from langflow.base.data.docling_utils import extract_docling_documents
 from langflow.custom import Component
@@ -122,13 +119,38 @@ class ChunkDoclingDocumentComponent(Component):
 
         chunker: BaseChunker
         if self.chunker == "HybridChunker":
+            try:
+                from docling_core.transforms.chunker.hybrid_chunker import HybridChunker
+            except ImportError as e:
+                msg = (
+                    "HybridChunker is not installed. Please install it with `uv pip install docling-core[chunking] "
+                    "or `uv pip install transformers`"
+                )
+                raise ImportError(msg) from e
             max_tokens: int | None = self.max_tokens if self.max_tokens else None
             if self.provider == "Hugging Face":
+                try:
+                    from docling_core.transforms.chunker.tokenizer.huggingface import HuggingFaceTokenizer
+                except ImportError as e:
+                    msg = (
+                        "HuggingFaceTokenizer is not installed."
+                        " Please install it with `uv pip install docling-core[chunking]`"
+                    )
+                    raise ImportError(msg) from e
                 tokenizer = HuggingFaceTokenizer.from_pretrained(
                     model_name=self.hf_model_name,
                     max_tokens=max_tokens,
                 )
             elif self.provider == "OpenAI":
+                try:
+                    from docling_core.transforms.chunker.tokenizer.openai import OpenAITokenizer
+                except ImportError as e:
+                    msg = (
+                        "OpenAITokenizer is not installed."
+                        " Please install it with `uv pip install docling-core[chunking]`"
+                        " or `uv pip install transformers`"
+                    )
+                    raise ImportError(msg) from e
                 if max_tokens is None:
                     max_tokens = 128 * 1024  # context window length required for OpenAI tokenizers
                 tokenizer = OpenAITokenizer(