Data and documents
Ask questions of your data, text to SQL, BI and forecasting; read PDFs and scans, extract text and tables.
mineru leads with 80, ahead of docling (77) and RAGFlow (74).22 projects ranked by score. Updated from public GitHub data.
On this page: Data analysis (5), Documents and OCR (17).
In Best of Vibe Coding
2 projects, ranked by score.
| Rank | Project | Score |
|---|---|---|
| 1 | rag-postgres-openai-pythonRAG over Postgres table rows with hybrid search and SQL filters | 49 out of 100 |
| 2 | natural-language-postgresNext.js text-to-SQL over Postgres with auto-picked charts | 28 out of 100 |
In Best of Open-Source AI
20 projects, ranked by score.
| Rank | Project | Score |
|---|---|---|
| 1 | mineruDocument parser that converts PDFs, images and Office files to Markdown and JSON | 80 out of 100 |
| 2 | doclingPython library and CLI that converts PDFs, Office files and more into structured text | 77 out of 100 |
| 3 | RAGFlowRAG engine with deep document parsing, template chunking and agentic retrieval | 74 out of 100 |
| #4 | timesfmPretrained time-series foundation model for zero-shot forecasting from Google Research | 74 out of 100 |
| #5 | markitdownPython tool that converts PDF, Office, HTML and audio files to Markdown for LLMs | 71 out of 100 |
| #6 | pageindexVectorless RAG that builds a tree index of a PDF and lets an LLM search it | 66 out of 100 |
| #7 | pdfmathtranslateTranslates scientific PDFs while keeping formulas, figures and layout intact | 61 out of 100 |
| #8 | rag-anythingPython library for RAG over PDFs, Office files, images, tables and equations | 60 out of 100 |
| #9 | paperless-gptLLM-based OCR, titles, tags and document linking for paperless-ngx | 59 out of 100 |
| #10 | unstructuredPython library that parses PDFs, Office files and HTML into typed elements | 57 out of 100 |
| #11 | paddleocrOCR and document parsing toolkit that outputs Markdown and JSON from PDFs and images | 56 out of 100 |
| #12 | markerConverts PDFs, Office files and images to markdown, JSON, HTML or chunks | 55 out of 100 |
| #13 | opendataloader-pdfPDF parser that outputs Markdown, JSON with bounding boxes, and Tagged PDF | 54 out of 100 |
| #14 | unlimited-ocrOCR model that parses long documents and multi-page PDFs in one pass | 54 out of 100 |
| #15 | Docling ServeDocling document conversion as an HTTP API with playground UI | 53 out of 100 |
| #16 | DB-GPTAgentic data assistant that writes SQL and code over your databases | 52 out of 100 |
| #17 | MorphikMultimodal retrieval engine for visually rich PDFs, images and video | 46 out of 100 |
| #18 | Paperless-AIAuto-tags Paperless-ngx documents and adds RAG chat over the archive | 33 out of 100 |
| #19 | pandas-aiPython library for asking natural-language questions about DataFrames | 24 out of 100 |
| #20 | easyocrPython OCR library for text detection and recognition in 80+ languages | 22 out of 100 |
A project's field comes from its own description: what it is made for. All fields.