fix(word_extractor): Fix type error and remove stream in ssrf_proxy (#…

…11241) Signed-off-by: -LAN- <laipz8200@outlook.com>
langgenius · Dec 2, 2024 · 9601102 · 9601102
1 parent 56c2d1c
commit 9601102
Show file tree

Hide file tree

Showing 2 changed files with 1 addition and 3 deletions.
diff --git a/api/core/helper/ssrf_proxy.py b/api/core/helper/ssrf_proxy.py
@@ -53,8 +53,6 @@ def make_request(method, url, max_retries=SSRF_DEFAULT_MAX_RETRIES, **kwargs):
                     response = client.request(method=method, url=url, **kwargs)
 
             if response.status_code not in STATUS_FORCELIST:
-                if stream:
-                    return response.iter_bytes()
                 return response
             else:
                 logging.warning(f"Received status code {response.status_code} for URL {url} which is in the force list")

diff --git a/api/core/rag/extractor/word_extractor.py b/api/core/rag/extractor/word_extractor.py
@@ -86,7 +86,7 @@ def _extract_images_from_docx(self, doc, image_folder):
                 image_count += 1
                 if rel.is_external:
                     url = rel.reltype
-                    response = ssrf_proxy.get(url, stream=True)
+                    response = ssrf_proxy.get(url)
                     if response.status_code == 200:
                         image_ext = mimetypes.guess_extension(response.headers["Content-Type"])
                         file_uuid = str(uuid.uuid4())