mirror of
https://github.com/semantica-agi/semantica.git
synced 2026-08-30 04:40:16 +00:00
KaifAhmad1andClaude Sonnet 4.6
946a1089c8
- Migrate from mint.json to docs.json (Mintlify v4) - Theme: maple, emerald green + near-black dark / cream light palette (#059669 primary, #0A0A0A dark bg, #FAF7F0 light bg) - Typography: Lexend headings, Inter body - 5-tab navigation: Documentation, Quick Start, API Reference, Cookbook, FAQ - Homepage: removed badge stickers, redundant h2, added blockquote tagline, full 27-module reference table with semantica.mcp_server added - quickstart.md: CodeGroup per pipeline step, pattern vs LLM options, AccordionGroup for patterns and troubleshooting - faq.md: full AccordionGroup structure across 5 sections - reference/explorer.md: NEW — FastAPI explorer, Ontology Hub, Distance Intelligence, CLI reference, REST API endpoints - reference/mcp_server.md: NEW — MCP stdio server, 12 tools with I/O examples, 3 resources, Claude Desktop/VS Code/Windsurf/Cline config - docs.json: explorer added to Output group, mcp_server to Utilities group - Chat, feedback (thumbs/suggest/raise), OG/Twitter metadata, search topbar - All reference pages reformatted with Mintlify JSX components Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
134 lines
3.0 KiB
Markdown
134 lines
3.0 KiB
Markdown
---
|
|
title: "Parse Module"
|
|
description: "Document parsing and text extraction — DocumentParser for standard formats and DoclingParser for complex layouts."
|
|
icon: "file-lines"
|
|
---
|
|
|
|
> Universal data parser supporting documents, web content, structured data, emails, code, and media.
|
|
|
|
---
|
|
|
|
## DocumentParser
|
|
|
|
Standard parser for clean, machine-readable documents.
|
|
|
|
```python
|
|
from semantica.parse import DocumentParser
|
|
|
|
parser = DocumentParser()
|
|
parsed = parser.parse("data/report.pdf")
|
|
|
|
print(parsed.text) # full clean text
|
|
print(parsed.metadata) # title, author, date, page_count, etc.
|
|
print(parsed.sections) # document structure
|
|
```
|
|
|
|
Supported formats: PDF, DOCX, HTML, TXT, JSON, CSV, PPTX, XLSX.
|
|
|
|
---
|
|
|
|
## DoclingParser
|
|
|
|
Advanced parser for complex layouts using the Docling backend.
|
|
|
|
```bash
|
|
pip install "semantica[docling]"
|
|
```
|
|
|
|
```python
|
|
from semantica.parse import DoclingParser
|
|
|
|
parser = DoclingParser(
|
|
extract_tables=True, # structured table extraction
|
|
extract_images=True, # image OCR
|
|
output_format="markdown", # "markdown" | "html" | "json"
|
|
)
|
|
|
|
parsed = parser.parse("data/annual_report.pdf")
|
|
|
|
print(parsed.text) # full clean text
|
|
print(parsed.tables) # structured table data
|
|
print(parsed.sections) # document structure
|
|
```
|
|
|
|
Use DoclingParser for: multi-column PDFs, tables with merged cells, PPTX slides, XLSX spreadsheets, images with OCR, and scanned documents.
|
|
|
|
---
|
|
|
|
## OCR Support
|
|
|
|
```python
|
|
parser = DoclingParser(
|
|
ocr=True,
|
|
ocr_language=["en"],
|
|
extract_tables=True,
|
|
)
|
|
|
|
parsed = parser.parse("data/scanned_contract.pdf")
|
|
```
|
|
|
|
---
|
|
|
|
## Parsed Document Object
|
|
|
|
```python
|
|
@dataclass
|
|
class ParsedDocument:
|
|
text: str
|
|
sections: List[Section]
|
|
tables: List[TableData]
|
|
metadata: DocumentMetadata
|
|
source_id: str
|
|
|
|
@dataclass
|
|
class DocumentMetadata:
|
|
title: Optional[str]
|
|
author: Optional[str]
|
|
created_date: Optional[datetime]
|
|
page_count: int
|
|
language: Optional[str]
|
|
has_tables: bool
|
|
has_images: bool
|
|
word_count: int
|
|
format: str # "pdf" | "docx" | "pptx" | ...
|
|
```
|
|
|
|
---
|
|
|
|
## Integration with FileIngestor
|
|
|
|
```python
|
|
from semantica.ingest import FileIngestor
|
|
from semantica.parse import DoclingParser
|
|
|
|
ingestor = FileIngestor()
|
|
parser = DoclingParser(extract_tables=True)
|
|
|
|
sources = ingestor.ingest("data/reports/")
|
|
for source in sources:
|
|
parsed = parser.parse(source)
|
|
```
|
|
|
|
<Note>
|
|
Docling is an optional dependency. If `docling` is not installed, `DoclingParser` raises an `ImportError` with installation instructions. Standard `DocumentParser` is used as the fallback.
|
|
</Note>
|
|
|
|
---
|
|
|
|
## See Also
|
|
|
|
<CardGroup cols={2}>
|
|
<Card title="Ingest" icon="database" href="ingest">
|
|
Load files before parsing.
|
|
</Card>
|
|
<Card title="Split" icon="scissors" href="split">
|
|
Chunk parsed text for embedding.
|
|
</Card>
|
|
<Card title="Docling Integration" icon="file-pdf" href="../integrations/docling">
|
|
Full Docling integration guide.
|
|
</Card>
|
|
<Card title="Semantic Extract" icon="magnifying-glass" href="semantic_extract">
|
|
Extract entities from parsed text.
|
|
</Card>
|
|
</CardGroup>
|