Merge pull request #108 from CatchTheTornado/feature/107-model-not-required

Author: pkarw

text_extract_api/extract/tasks.py

@@ -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,
 ):
     """
@@ -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)

text_extract_api/main.py

@@ -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'),
@@ -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")
@@ -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")