From 187562fae16af7bf4590a75767400e4bc1418c40 Mon Sep 17 00:00:00 2001 From: Siddarthreddygsr Date: Sat, 19 Jul 2025 15:19:56 +0530 Subject: [PATCH 1/5] fix(issue): Fixing issue #177 Signed-off-by: Siddarthreddygsr --- .../utilities/dalle_image_generator.py | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) diff --git a/libs/community/langchain_community/utilities/dalle_image_generator.py b/libs/community/langchain_community/utilities/dalle_image_generator.py index 71d9df762..9b74a4fa8 100644 --- a/libs/community/langchain_community/utilities/dalle_image_generator.py +++ b/libs/community/langchain_community/utilities/dalle_image_generator.py @@ -62,7 +62,7 @@ class DallEAPIWrapper(BaseModel): """Size of image to generate""" separator: str = "\n" """Separator to use when multiple URLs are returned.""" - quality: Optional[str] = "standard" + quality: Optional[str] = None """Quality of the image that will be generated""" max_retries: int = 2 """Maximum number of retries to make when generating.""" @@ -140,15 +140,16 @@ def validate_environment(self) -> Self: def run(self, query: str) -> str: """Run query through OpenAI and parse result.""" - if is_openai_v1(): - response = self.client.generate( - prompt=query, - n=self.n, - size=self.size, - model=self.model_name, - quality=self.quality, - ) + kwargs = { + "prompt": query, + "n": self.n, + "size": self.size, + "model": self.model_name, + } + if self.quality is not None: + kwargs["quality"] = self.quality + response = self.client.generate(**kwargs) image_urls = self.separator.join([item.url for item in response.data]) else: response = self.client.create( From d7c2e5eb27b34e1f7e33cb0081a05413ceeeb939 Mon Sep 17 00:00:00 2001 From: Siddarthreddygsr Date: Sat, 2 Aug 2025 13:54:46 +0530 Subject: [PATCH 2/5] parsing base url in RecursiveUrlLoader Signed-off-by: Siddarthreddygsr --- .../document_loaders/recursive_url_loader.py | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/libs/community/langchain_community/document_loaders/recursive_url_loader.py b/libs/community/langchain_community/document_loaders/recursive_url_loader.py index 22227d88a..155c46b45 100644 --- a/libs/community/langchain_community/document_loaders/recursive_url_loader.py +++ b/libs/community/langchain_community/document_loaders/recursive_url_loader.py @@ -14,6 +14,7 @@ Union, cast, ) +from urllib.parse import urlparse import aiohttp import requests @@ -372,9 +373,16 @@ def simple_metadata_extractor( self.headers = headers self.check_response_status = check_response_status self.continue_on_failure = continue_on_failure - self.base_url = base_url if base_url is not None else url + self.base_url = base_url if base_url is not None else self._parse_base_url(url) self.proxies = proxies + + def _parse_base_url(self, url) -> str: + if not url.startswith(("http://", "https://")): + url = "https://" + url + parsed_url = urlparse(url) + return f"{parsed_url.scheme}://{parsed_url.netloc}/" + def _get_child_links_recursive( self, url: str, visited: Set[str], *, depth: int = 0 ) -> Iterator[Document]: From a3238db409ab1bcdc964efc4604bcd1ad178f59c Mon Sep 17 00:00:00 2001 From: Siddarthreddygsr Date: Sat, 2 Aug 2025 14:53:27 +0530 Subject: [PATCH 3/5] fixed linting Signed-off-by: Siddarthreddygsr --- .../document_loaders/recursive_url_loader.py | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/libs/community/langchain_community/document_loaders/recursive_url_loader.py b/libs/community/langchain_community/document_loaders/recursive_url_loader.py index 685c389fe..5a9ff4420 100644 --- a/libs/community/langchain_community/document_loaders/recursive_url_loader.py +++ b/libs/community/langchain_community/document_loaders/recursive_url_loader.py @@ -376,7 +376,12 @@ def simple_metadata_extractor( self.base_url = base_url if base_url is not None else self._parse_base_url(url) self.proxies = proxies - def _parse_base_url(self, url) -> str: + def _parse_base_url(self, url: str) -> str: + """Parse the base URL from the given URL. + + Args: + url: The URL to parse. + """ if not url.startswith(("http://", "https://")): url = "https://" + url parsed_url = urlparse(url) From dd26bd71677606f7fe2c8a5f8030b4fc1942d2b8 Mon Sep 17 00:00:00 2001 From: Gurram Siddarth Reddy <73605274+siddarthreddygsr@users.noreply.github.com> Date: Sat, 2 Aug 2025 09:29:51 +0000 Subject: [PATCH 4/5] Update libs/community/langchain_community/document_loaders/recursive_url_loader.py Co-authored-by: graphite-app[bot] <96075541+graphite-app[bot]@users.noreply.github.com> --- .../document_loaders/recursive_url_loader.py | 3 +++ 1 file changed, 3 insertions(+) diff --git a/libs/community/langchain_community/document_loaders/recursive_url_loader.py b/libs/community/langchain_community/document_loaders/recursive_url_loader.py index 5a9ff4420..ed75c2175 100644 --- a/libs/community/langchain_community/document_loaders/recursive_url_loader.py +++ b/libs/community/langchain_community/document_loaders/recursive_url_loader.py @@ -381,6 +381,9 @@ def _parse_base_url(self, url: str) -> str: Args: url: The URL to parse. + + Returns: + The base URL with scheme and netloc only, ending with a slash. """ if not url.startswith(("http://", "https://")): url = "https://" + url From 62fc3f0c2f28de7e5f49fbe167590240d34b19f9 Mon Sep 17 00:00:00 2001 From: Siddarthreddygsr Date: Sat, 2 Aug 2025 15:05:33 +0530 Subject: [PATCH 5/5] fixed make lint Signed-off-by: Siddarthreddygsr --- .../document_loaders/recursive_url_loader.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/libs/community/langchain_community/document_loaders/recursive_url_loader.py b/libs/community/langchain_community/document_loaders/recursive_url_loader.py index ed75c2175..813ef1154 100644 --- a/libs/community/langchain_community/document_loaders/recursive_url_loader.py +++ b/libs/community/langchain_community/document_loaders/recursive_url_loader.py @@ -381,7 +381,7 @@ def _parse_base_url(self, url: str) -> str: Args: url: The URL to parse. - + Returns: The base URL with scheme and netloc only, ending with a slash. """