Dossier Lab

C 61 completed
Ai Ml
web_app / typescript · small
201
Files
19,212
LOC
4
Frameworks
8
Languages

Pipeline State

completed
Run ID
#365265
Phase
done
Progress
1%
Started
Finished
2026-04-13 01:31:02
LLM tokens
0

Pipeline Metadata

Stage
Cataloged
Decision
proceed
Novelty
75.07
Framework unique
Isolation
Last stage change
2026-05-10 03:35:34
Deduplication group #65671
Member of a group with 1 similar repo(s) — this repo is canonical view group →
Top concepts (2)
Project DescriptionWeb Frontend
All rows above produced by Repobility · https://repobility.com

AI Prompt

Create a personal intelligence tool called Dossier Lab using Next.js 16, TypeScript, and Tailwind CSS. The core functionality should allow users to ingest various content types like URLs, PDFs, YouTube videos, and Markdown files. It needs a hybrid search capability combining semantic vector search (using OpenAI embeddings) and PostgreSQL full-text search. Implement a Q&A feature that streams answers with source-level citations and supports chat history persistence. Additionally, include an Evaluation Dashboard to track metrics like retrieval accuracy and groundedness, and support multi-provider LLMs like OpenAI and Anthropic. Use Prisma for ORM and PostgreSQL with pgvector for the database.
typescript next.js react postgresql prisma ai llm search web-app openai anthropic full-text-search
Generated by gemma4:latest

Catalog Information

Dossier Lab is a personal intelligence tool that transforms your reading into a searchable knowledge base.

Description

Dossier Lab captures articles, documents, and text, allowing you to search semantically, ask questions, and get source-grounded answers with citations. It supports content capture from various sources, hybrid search using semantic vector search and metadata-aware full-text search, Q&A with citations, and evaluation dashboard for tracking retrieval accuracy.

الوصف

يعد دوسير لاب أداة ذكاء شخصية تحول قرائتك إلى قاعدة المعرفة قابلة للبحث. يمكنك التقاط المقالات والوثائق والنصوص، ثم البحث بشكل منطقي، أسأل الأسئلة، وحصل على الإجابات المبنية على المصادر مع المراجع.

Novelty

9/10

Tags

knowledge-base semantic-search question-answering citation-management evaluation-dashboard

Technologies

anthropic jest next-auth nextjs openai prisma react recharts shadcn-ui tailwind

Claude Models

claude-opus-4.6 claude-sonnet-4.6 claude-haiku-4.5

Quality Score

C
60.6/100
Structure
60
Code Quality
77
Documentation
49
Testing
30
Practices
66
Security
75
Dependencies
60

Strengths

  • Code linting configured (eslint)

Weaknesses

  • No LICENSE file \u2014 legal ambiguity for contributors
  • No CI/CD configuration \u2014 manual testing and deployment
  • 1484 duplicate lines detected \u2014 consider DRY refactoring
  • 2 'god files' with >500 LOC need decomposition

Recommendations

  • Add a test suite \u2014 start with critical path integration tests
  • Set up CI/CD (GitHub Actions recommended) to automate testing and deployment
  • Add a LICENSE file (MIT recommended for open source)

Security & Health

12.1h
Tech Debt (B)
A
OWASP (100%)
PASS
Quality Gate
A
Risk (2)
Repobility analyzer · published findings · https://repobility.com
Unknown
License
8.5%
Duplication
Full Security Report AI Fix Prompts SARIF SBOM

Languages

typescript
66.4%
html
19.0%
markdown
9.9%
css
2.8%
sql
0.9%
json
0.6%
javascript
0.3%
toml
0.0%

Frameworks

React Next.js Jest Prisma

Concepts (2)

Open data · scored by Repobility · https://repobility.com
CategoryNameDescriptionConfidence
Repobility · code-quality intelligence platform · https://repobility.com
auto_descriptionProject DescriptionA personal intelligence tool that transforms your reading into a searchable, synthesizable knowledge base. Capture articles, documents, and text, then search semantically, ask questions, and get source-grounded answers with citations.80%
auto_categoryWeb Frontendweb-frontend70%

Quality Timeline

1 quality score recorded.

View File Metrics

Embed Badge

Add to your README:

![Quality](https://repos.aljefra.com/badge/89439.svg)
Quality BadgeSecurity Badge
Export Quality CSVDownload SBOMExport Findings CSV