| Name | docsumm-ai JSON |
| Version |
0.1.0
JSON |
| download |
| home_page | None |
| Summary | Audience-aware document summarizer for PDF/DOCX/TXT — optimized for context retention, not token count. |
| upload_time | 2025-10-06 16:41:18 |
| maintainer | None |
| docs_url | None |
| author | Rohit Rajdev |
| requires_python | >=3.9 |
| license | MIT |
| keywords |
ai
llm
documents
docx
pdf
summarization
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# docsumm-ai
**One-line, opinionated document summarizer for PDFs, Word, or text — optimized for context retention, not token count.**
---
## Why docsumm-ai?
Summarizing long documents shouldn’t mean losing meaning.
Most tools today **truncate context** just to fit into token limits — resulting in shallow, inaccurate summaries.
`docsumm-ai` was built to fix that.
We designed it for **researchers, analysts, and AI developers** who care about both **fidelity and efficiency**.
It automatically adapts to document structure, ensuring retention of key insights from text, Word, or PDFs — in a single line.
---
## What Makes It Different
✅ **One-line summarize()** — clean summaries with context retention
✅ **Handles PDFs, DOCX, TXT** — no format left behind
✅ **Context-aware chunking** — semantic segmentation, not blind splitting
✅ **Adaptive compression** — keeps the right level of detail per section
✅ **CLI + Python API** — works both in scripts and terminal
✅ **Transparent JSON + Markdown output** — reproducible and human-readable
---
## Installation
```bash
pip install docsumm-ai
## Quickstart
1. Summarize a text file
from docsumm_ai import summarize
summary = summarize("annual_report.txt", mode="concise")
print(summary)
2. Summarize a PDF (CLI)
docsumm summarize my_report.pdf --mode detailed --out summary.md
## Output Example
Input:
“The study explores the correlation between urban growth and environmental impact across 32 global cities…”
Output:
“Analyzes 32 cities showing urban expansion drives higher emissions; highlights need for adaptive policies.”
---
## License
MIT License © 2025 Rohit Rajdev
Open for community collaboration and research integration.
🌐 Links
🔗 GitHub: https://github.com/RohitRajdev/docsumm-ai
✉️ Contact: rohitrajdev.com
🧠 Related project: dataprep-ai
Raw data
{
"_id": null,
"home_page": null,
"name": "docsumm-ai",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.9",
"maintainer_email": null,
"keywords": "AI, LLM, documents, docx, pdf, summarization",
"author": "Rohit Rajdev",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/8c/07/083b5528828e941f8a382d26860c329fb838f1f6a921485813f54cb82fcb/docsumm_ai-0.1.0.tar.gz",
"platform": null,
"description": "# docsumm-ai \n**One-line, opinionated document summarizer for PDFs, Word, or text \u2014 optimized for context retention, not token count.**\n\n\n\n\n\n\n---\n\n## Why docsumm-ai?\n\nSummarizing long documents shouldn\u2019t mean losing meaning. \nMost tools today **truncate context** just to fit into token limits \u2014 resulting in shallow, inaccurate summaries.\n\n`docsumm-ai` was built to fix that.\n\nWe designed it for **researchers, analysts, and AI developers** who care about both **fidelity and efficiency**. \nIt automatically adapts to document structure, ensuring retention of key insights from text, Word, or PDFs \u2014 in a single line.\n\n---\n\n## What Makes It Different\n\n\u2705 **One-line summarize()** \u2014 clean summaries with context retention \n\u2705 **Handles PDFs, DOCX, TXT** \u2014 no format left behind \n\u2705 **Context-aware chunking** \u2014 semantic segmentation, not blind splitting \n\u2705 **Adaptive compression** \u2014 keeps the right level of detail per section \n\u2705 **CLI + Python API** \u2014 works both in scripts and terminal \n\u2705 **Transparent JSON + Markdown output** \u2014 reproducible and human-readable \n\n---\n\n## Installation\n\n```bash\npip install docsumm-ai\n\n## Quickstart\n1. Summarize a text file\nfrom docsumm_ai import summarize\n\nsummary = summarize(\"annual_report.txt\", mode=\"concise\")\nprint(summary)\n\n2. Summarize a PDF (CLI)\ndocsumm summarize my_report.pdf --mode detailed --out summary.md\n\n## Output Example\n\nInput:\n\n\u201cThe study explores the correlation between urban growth and environmental impact across 32 global cities\u2026\u201d\n\nOutput:\n\n\u201cAnalyzes 32 cities showing urban expansion drives higher emissions; highlights need for adaptive policies.\u201d\n\n---\n\n## License\n\nMIT License \u00a9 2025 Rohit Rajdev\nOpen for community collaboration and research integration.\n\n\ud83c\udf10 Links\n\n\ud83d\udd17 GitHub: https://github.com/RohitRajdev/docsumm-ai\n\n\u2709\ufe0f Contact: rohitrajdev.com\n\n\ud83e\udde0 Related project: dataprep-ai\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Audience-aware document summarizer for PDF/DOCX/TXT \u2014 optimized for context retention, not token count.",
"version": "0.1.0",
"project_urls": null,
"split_keywords": [
"ai",
" llm",
" documents",
" docx",
" pdf",
" summarization"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "ba281401f16c35a1d9a7cce7341a123a0e30eab7956b52f76e543c50cef32497",
"md5": "74169186513f608c14722f462be282de",
"sha256": "5469de08b76e652ec9b5ee26e05f8589bfd4379e0ef5d738ae39c59ff0feeaaa"
},
"downloads": -1,
"filename": "docsumm_ai-0.1.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "74169186513f608c14722f462be282de",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.9",
"size": 5287,
"upload_time": "2025-10-06T16:41:17",
"upload_time_iso_8601": "2025-10-06T16:41:17.330654Z",
"url": "https://files.pythonhosted.org/packages/ba/28/1401f16c35a1d9a7cce7341a123a0e30eab7956b52f76e543c50cef32497/docsumm_ai-0.1.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "8c07083b5528828e941f8a382d26860c329fb838f1f6a921485813f54cb82fcb",
"md5": "57188e5ce8de5d05e3c7ea7345186c29",
"sha256": "f6c05439695b95057bfd77df176c2398be234d9ef396b7d2b805154e07557104"
},
"downloads": -1,
"filename": "docsumm_ai-0.1.0.tar.gz",
"has_sig": false,
"md5_digest": "57188e5ce8de5d05e3c7ea7345186c29",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.9",
"size": 6539,
"upload_time": "2025-10-06T16:41:18",
"upload_time_iso_8601": "2025-10-06T16:41:18.539074Z",
"url": "https://files.pythonhosted.org/packages/8c/07/083b5528828e941f8a382d26860c329fb838f1f6a921485813f54cb82fcb/docsumm_ai-0.1.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-10-06 16:41:18",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "docsumm-ai"
}
