diff --git a/common/data_source/confluence_connector.py b/common/data_source/confluence_connector.py
index 58a7d2f82b..abe55b5b27 100644
--- a/common/data_source/confluence_connector.py
+++ b/common/data_source/confluence_connector.py
@@ -920,7 +920,7 @@ def extract_text_from_confluence_html(
         confluence_client (Confluence): Confluence client
         fetched_titles (set[str]): The titles of the pages that have already been fetched
     Returns:
-        str: loaded and formated Confluence page
+        str: loaded and formatted Confluence page
     """
     body = confluence_object["body"]
     object_html = body.get("storage", body.get("view", {})).get("value")
diff --git a/deepdoc/README.md b/deepdoc/README.md
index db70e30d80..b8bd15e307 100644
--- a/deepdoc/README.md
+++ b/deepdoc/README.md
@@ -98,7 +98,7 @@ We use vision information to resolve problems as human being.
      ```bash
         python deepdoc/vision/t_recognizer.py --inputs=path_to_images_or_pdfs --threshold=0.2 --mode=tsr --output_dir=path_to_store_result
      ```
-    The inputs could be directory to images or PDF, or a image or PDF. 
+    The inputs could be directory to images or PDF, or an image or PDF. 
     You can look into the folder 'path_to_store_result' where has both images and html pages which demonstrate the detection results as following:
     <div align="center" style="margin-top:20px;margin-bottom:20px;">
     <img src="https://github.com/infiniflow/ragflow/assets/12318111/cb24e81b-f2ba-49f3-ac09-883d75606f4c" width="1000"/>
diff --git a/deepdoc/parser/pdf_parser.py b/deepdoc/parser/pdf_parser.py
index 6717a887ae..ad63ded035 100644
--- a/deepdoc/parser/pdf_parser.py
+++ b/deepdoc/parser/pdf_parser.py
@@ -708,7 +708,7 @@ class RAGFlowPdfParser:
     def __ocr(self, pagenum, img, chars, ZM=3, device_id: int | None = None):
         start = timer()
         bxs = self.ocr.detect(np.array(img), device_id)
-        logging.info(f"__ocr detecting boxes of a image cost ({timer() - start}s)")
+        logging.info(f"__ocr detecting boxes of an image cost ({timer() - start}s)")
 
         start = timer()
         if not bxs:
diff --git a/deepdoc/vision/table_structure_recognizer.py b/deepdoc/vision/table_structure_recognizer.py
index 0cd762576c..e0892c2d72 100644
--- a/deepdoc/vision/table_structure_recognizer.py
+++ b/deepdoc/vision/table_structure_recognizer.py
@@ -394,7 +394,7 @@ class TableStructureRecognizer(Recognizer):
 
     @staticmethod
     def __desc_table(cap, hdr_rowno, tbl, is_english):
-        # get text of every colomn in header row to become header text
+        # get text of every column in header row to become header text
         clmno = len(tbl[0])
         rowno = len(tbl)
         headers = {}
diff --git a/rag/prompts/assign_toc_levels.md b/rag/prompts/assign_toc_levels.md
index d35dee7791..ce80c22622 100644
--- a/rag/prompts/assign_toc_levels.md
+++ b/rag/prompts/assign_toc_levels.md
@@ -1,4 +1,4 @@
-You are given a JSON array of TOC(tabel of content) items. Each item has at least {"title": string} and may include an existing title hierarchical level.
+You are given a JSON array of TOC(table of contents) items. Each item has at least {"title": string} and may include an existing title hierarchical level.
 
 Task
 - For each item, assign a depth label using Arabic numerals only: top-level = 1, second-level = 2, third-level = 3, etc.