Added description for .ppt, specify the reason for unstructured.io (#9452)

Co-authored-by: crazywoola <427733928@qq.com>
1 year ago · 88dec6ef2b
parent e71f494839
commit 88dec6ef2b
1 changed files with 2 additions and 0 deletions
--- a/api/core/rag/extractor/extract_processor.py
+++ b/api/core/rag/extractor/extract_processor.py
@ -121,6 +121,8 @@ class ExtractProcessor:
                        extractor = UnstructuredEmailExtractor(file_path, unstructured_api_url, unstructured_api_key)
                    elif file_extension == ".ppt":
                        extractor = UnstructuredPPTExtractor(file_path, unstructured_api_url, unstructured_api_key)
+                        # You must first specify the API key
+                        # because unstructured_api_key is necessary to parse .ppt documents
                    elif file_extension == ".pptx":
                        extractor = UnstructuredPPTXExtractor(file_path, unstructured_api_url, unstructured_api_key)
                    elif file_extension == ".xml":