markitdown
Convert mọi file (PDF, Word, Excel, PowerPoint, Image, Audio, HTML, CSV, YouTube URL) thành Markdown cho LLM. Tích hợp vào YAMTAM vault để import tài liệu.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-14
- Stars
- ★ 13
- Forks
- 2
01 前言 Front Matter
- name
- markitdown
- triggers
- [ "markitdown", "convert file to markdown", "pdf to markdown", "word to markdown", "import document", "import pdf", "đọc file pdf", "convert tài liệu", "vault import", "đưa file vào vault" ]
- description
- Convert mọi file (PDF, Word, Excel, PowerPoint, Image, Audio, HTML, CSV, YouTube URL) thành Markdown cho LLM. Tích hợp vào YAMTAM vault để import tài liệu.
03 SKILL.md 正文
markitdown — File → Markdown Converter
Source: github.com/microsoft/markitdown
Version: 0.1.6 (installed)
License: MIT · Built by Microsoft AutoGen team
Supported formats
| Format | Notes |
|---|---|
| Text extraction | |
| Word (.docx) | Full structure |
| PowerPoint (.pptx) | Slides → Markdown |
| Excel (.xlsx) | Tables |
| Image | EXIF + OCR (với LLM) |
| Audio | Transcription |
| HTML | Clean text |
| CSV / JSON / XML | Structured |
| YouTube URL | Transcript tự động |
| EPub | Chapters |
Basic usage
from markitdown import MarkItDown
md = MarkItDown()
# Convert file
result = md.convert("document.pdf")
print(result.text_content)
# Convert URL
result = md.convert("https://example.com")
# Convert YouTube → transcript
result = md.convert("https://youtube.com/watch?v=xxx")
CLI
markitdown document.pdf > output.md
markitdown document.pdf -o output.md
markitdown https://example.com -o page.md
Tích hợp YAMTAM vault
# Import PDF vào vault
python3 tools/vault-import.py document.pdf
# Import thư mục
python3 tools/vault-import.py --dir ./docs/ --ext pdf,docx
# Import + ghi vào knowledge base
python3 tools/vault-import.py report.pdf --tag bao-cao --lang vi
Với LLM (AI-powered OCR cho ảnh scan)
import anthropic
from markitdown import MarkItDown
client = anthropic.Anthropic()
md = MarkItDown(llm_client=client, llm_model="claude-haiku-4-5-20251001")
result = md.convert("scan_bai_thi.jpg")
print(result.text_content)
Khi nào dùng trong YAMTAM
- Import sách giáo khoa tiếng Việt (PDF) → vault search
- Convert báo cáo Word/Excel → context cho Claude
- Đọc slide PowerPoint → summary tự động
- Transcribe YouTube tiếng Việt → text searchable
- Parse CSV lớn → Markdown table cho LLM
- Đọc tài liệu JNMT (Word, PDF) → AI context
04 同仓库更多 Skills
openai--sentry--sentry
Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require `SENTRY_AUTH_TOKEN`.
ito-basket-compare
Compare Itô prediction-market baskets against a user's knowledge base, portfolio notes, financial context, watchlist, or research thesis. Use for read-only basket comparison and gap analysis without investment advice or live trading.
implementing-network-traffic-baselining
Build network traffic baselines from NetFlow/IPFIX data using Python pandas for statistical analysis, z-score anomaly detection, and hourly/daily traffic pattern profiling
detecting-evasion-techniques-in-endpoint-logs
Detects defense evasion techniques used by adversaries in endpoint logs including log tampering, timestomping, process injection, and security tool disabling. Use when investigating suspicious endpoint behavior, building detection rules for evasion tactics, or conducting threat hunting for stealthy adversary activity. Activates for requests involving evasion detection, defense evasion analysis, log tampering detection, or MITRE ATT&CK TA0005.
implementing-microsegmentation-with-guardicore
Implementing microsegmentation using Akamai Guardicore Segmentation to map application dependencies, create granular network policies, visualize east-west traffic flows, and enforce least-privilege communication between workloads across data centers and cloud.
ramdisk-tmpfs-patterns
暂无简介