Skip to content

Feature/107 model not required #108

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Jan 21, 2025
Merged

Feature/107 model not required #108

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
63481b8
#107 api - model set to optional instead of required (llm-based strat…
choinek Jan 20, 2025
1477f15
+ universalize filename
choinek Jan 20, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 5 additions & 5 deletions text_extract_api/extract/tasks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,10 +23,10 @@ def ocr_task(
filename: str,
file_hash: str,
ocr_cache: bool,
prompt: str,
model: str,
language: str,
storage_profile: str,
prompt: Optional[str] = None,
model: Optional[str] = None,
language: Optional[str] = None,
storage_profile: Optional[str] = None,
storage_filename: Optional[str] = None,
):
"""
Expand Down Expand Up @@ -85,7 +85,7 @@ def ocr_task(

if storage_profile:
if not storage_filename:
storage_filename = filename.replace('.pdf', '.md')
storage_filename = filename.replace('.', '_') + '.pdf'

storage_manager = StorageManager(storage_profile)
storage_manager.save(filename, storage_filename, extracted_text)
Expand Down
6 changes: 3 additions & 3 deletions text_extract_api/main.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -78,7 +78,7 @@ async def ocr_endpoint(
async def ocr_upload_endpoint(
strategy: str = Form(...),
prompt: str = Form(None),
model: str = Form(...),
model: str = Form(None),
file: UploadFile = File(...),
ocr_cache: bool = Form(...),
storage_profile: str = Form('default'),
Expand All @@ -104,7 +104,7 @@ class OllamaPullRequest(BaseModel):
class OcrRequest(BaseModel):
strategy: str = Field(..., description="OCR strategy to use")
prompt: Optional[str] = Field(None, description="Prompt for the Ollama model")
model: str = Field(..., description="Model to use for the Ollama endpoint")
model: Optional[str] = Field(None, description="Model to use for the Ollama endpoint")
file: FileField = Field(..., description="Base64 encoded document file")
ocr_cache: bool = Field(..., description="Enable OCR result caching")
storage_profile: Optional[str] = Field('default', description="Storage profile to use")
Expand All @@ -126,7 +126,7 @@ def validate_storage_profile(cls, v):
class OcrFormRequest(BaseModel):
strategy: str = Field(..., description="OCR strategy to use")
prompt: Optional[str] = Field(None, description="Prompt for the Ollama model")
model: str = Field(..., description="Model to use for the Ollama endpoint")
model: Optional[str] = Field(None, description="Model to use for the Ollama endpoint")
ocr_cache: bool = Field(..., description="Enable OCR result caching")
storage_profile: Optional[str] = Field('default', description="Storage profile to use")
storage_filename: Optional[str] = Field(None, description="Storage filename to use")
Expand Down