YogeLiu/doc_processer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: optimize the format convert

Browse Source
This commit is contained in:
liuyuanchuang
2026-02-04 12:00:06 +08:00
parent 10dbd59161
commit 526c1f3a0d
7 changed files with 571 additions and 187 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
app/schemas/image.py
View File

@@ -40,11 +40,21 @@ class ImageOCRRequest(BaseModel):
class ImageOCRResponse(BaseModel):
"""Response body for image OCR endpoint."""
latex: str = Field("", description="LaTeX representation of the content")
latex: str = Field("", description="LaTeX representation of the content (empty if mixed content)")
markdown: str = Field("", description="Markdown representation of the content")
mathml: str = Field("", description="MathML representation (empty if no math detected)")
mathml: str = Field("", description="Standard MathML representation (empty if mixed content)")
mml: str = Field("", description="XML MathML with mml: namespace prefix (empty if mixed content)")
layout_info: LayoutInfo = Field(default_factory=LayoutInfo)
recognition_mode: str = Field(
"", description="Recognition mode used: mixed_recognition or formula_recognition"
)
recognition_mode: str = Field("", description="Recognition mode used: mixed_recognition or formula_recognition")
class LatexToOmmlRequest(BaseModel):
"""Request body for LaTeX to OMML conversion endpoint."""
latex: str = Field(..., description="Pure LaTeX formula (without $ or $$ delimiters)")
class LatexToOmmlResponse(BaseModel):
"""Response body for LaTeX to OMML conversion endpoint."""
omml: str = Field("", description="OMML (Office Math Markup Language) representation")