mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-26 20:14:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

not do amateur hour stuff

Browse Source 
Signed-off-by: Vinay Damodaran <vrdn@hey.com>
This commit is contained in:
Vinay Damodaran 2025-05-07 21:42:16 -07:00
parent 45c5a9445a
commit 8186bdcd4c
3 changed files with 8 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docling/datamodel/pipeline_options.py
View File

@ -225,6 +225,7 @@ class PictureDescriptionApiOptions(PictureDescriptionBaseOptions):
headers: Dict[str, str] = {} headers: Dict[str, str] = {}
params: Dict[str, Any] = {} params: Dict[str, Any] = {}
timeout: float = 20 timeout: float = 20
concurrency: int = 1
prompt: str = "Describe this image in a few sentences." prompt: str = "Describe this image in a few sentences."
provenance: str = "" provenance: str = ""
@ -295,6 +296,7 @@ class ApiVlmOptions(BaseVlmOptions):
params: Dict[str, Any] = {} params: Dict[str, Any] = {}
scale: float = 2.0 scale: float = 2.0
timeout: float = 60 timeout: float = 60
concurrency: int = 1
response_format: ResponseFormat response_format: ResponseFormat

8
docling/models/api_vlm_model.py
View File

@ -28,6 +28,7 @@ class ApiVlmModel(BasePageModel):
) )
self.timeout = self.vlm_options.timeout self.timeout = self.vlm_options.timeout
self.concurrency = self.vlm_options.concurrency
self.prompt_content = ( self.prompt_content = (
f"This is a page from a document.\n{self.vlm_options.prompt}" f"This is a page from a document.\n{self.vlm_options.prompt}"
) )
@ -37,10 +38,7 @@ class ApiVlmModel(BasePageModel):
} }
def __call__( def __call__(
self, self, conv_res: ConversionResult, page_batch: Iterable[Page]
conv_res: ConversionResult,
page_batch: Iterable[Page],
concurrency: int = 1,
) -> Iterable[Page]: ) -> Iterable[Page]:
def _vlm_request(page): def _vlm_request(page):
assert page._backend is not None assert page._backend is not None
@ -69,5 +67,5 @@ class ApiVlmModel(BasePageModel):
return page return page
with ThreadPoolExecutor(max_workers=concurrency) as executor: with ThreadPoolExecutor(max_workers=self.concurrency) as executor:
yield from executor.map(_vlm_request, page_batch) yield from executor.map(_vlm_request, page_batch)

7
docling/models/picture_description_api_model.py
View File

@ -38,6 +38,7 @@ class PictureDescriptionApiModel(PictureDescriptionBaseModel):
accelerator_options=accelerator_options, accelerator_options=accelerator_options,
) )
self.options: PictureDescriptionApiOptions self.options: PictureDescriptionApiOptions
self.concurrency = self.options.concurrency
if self.enabled: if self.enabled:
if not enable_remote_services: if not enable_remote_services:
@ -46,9 +47,7 @@ class PictureDescriptionApiModel(PictureDescriptionBaseModel):
"pipeline_options.enable_remote_services=True." "pipeline_options.enable_remote_services=True."
) )
def _annotate_images( def _annotate_images(self, images: Iterable[Image.Image]) -> Iterable[str]:
self, images: Iterable[Image.Image], concurrency: int = 1
) -> Iterable[str]:
# Note: technically we could make a batch request here, # Note: technically we could make a batch request here,
# but not all APIs will allow for it. For example, vllm won't allow more than 1. # but not all APIs will allow for it. For example, vllm won't allow more than 1.
def _api_request(image): def _api_request(image):
@ -61,5 +60,5 @@ class PictureDescriptionApiModel(PictureDescriptionBaseModel):
**self.options.params, **self.options.params,
) )
with ThreadPoolExecutor(max_workers=concurrency) as executor: with ThreadPoolExecutor(max_workers=self.concurrency) as executor:
yield from executor.map(_api_request, images) yield from executor.map(_api_request, images)