Austin/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2024-11-16 11:42:29 +08:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

fix the ssrf of docx file extractor external images

Browse Source
This commit is contained in:
jyong 2024-11-04 15:31:20 +08:00
parent c135ec4b08
commit 517bbc281a
2 changed files with 15 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
api/core/helper/ssrf_proxy.py
View File

@ -31,24 +31,25 @@ def make_request(method, url, max_retries=SSRF_DEFAULT_MAX_RETRIES, **kwargs):
allow_redirects = kwargs.pop("allow_redirects")
if "follow_redirects" not in kwargs:
kwargs["follow_redirects"] = allow_redirects
stream = kwargs.pop("stream", False)
retries = 0
while retries <= max_retries:
try:
if SSRF_PROXY_ALL_URL:
with httpx.Client(proxy=SSRF_PROXY_ALL_URL) as client:
response = client.request(method=method, url=url, **kwargs)
elif proxy_mounts:
with httpx.Client(mounts=proxy_mounts) as client:
response = client.request(method=method, url=url, **kwargs)
else:
with httpx.Client() as client:
response = client.request(method=method, url=url, **kwargs)
client_args = {"proxy": SSRF_PROXY_ALL_URL} if SSRF_PROXY_ALL_URL else {}
if proxy_mounts:
client_args["mounts"] = proxy_mounts
if response.status_code not in STATUS_FORCELIST:
return response
else:
logging.warning(f"Received status code {response.status_code} for URL {url} which is in the force list")
with httpx.Client(**client_args) as client:
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"
)
except httpx.RequestError as e:
logging.warning(f"Request to URL {url} failed on attempt {retries + 1}: {e}")

1
api/core/rag/extractor/word_extractor.py
View File

@ -81,7 +81,6 @@ class WordExtractor(BaseExtractor):
os.makedirs(image_folder, exist_ok=True)
image_count = 0
image_map = {}
for rel in doc.part.rels.values():
if "image" in rel.target_ref:
image_count += 1