PDF to markdown using vision LLMs — tables, layouts, and structure preserved
-
Updated
Feb 21, 2026 - Python
#
vision-llm
Here are 22 public repositories matching this topic...
Convert scanned PDFs into searchable text locally using Vision LLMs (olmOCR). 100% private, offline, and free. Features a modern Web UI & CLI.
python ocr web-ui document-processing fastapi privacy-focused searchable-pdf no-api-key pdf-ocr local-llm offline-ai surya-ocr olmocr vision-llm
-
Updated
Dec 23, 2025 - Python
Powerful PDF data extraction library powered by AI vision models. Transform PDFs into structured, validated data using TypeScript, Zod, and AI providers like Scaleway and Ollama.
-
Updated
Sep 14, 2025 - TypeScript
PyMidscene - Midscene.js 的 Python SDK 实现 | AI 驱动的自然语言 UI 自动化，告别选择器，用中文描述即可操作。与官方缓存格式完全兼容。
python automation ai natural-language ui-testing browser-automation rpa playwright vision-llm midscene
-
Updated
Feb 9, 2026 - Python
AI Video Editor Pipeline with Vision LLM Models
python workflow optimized video-editor integrated youtube-upload davinci-resolve llm llamacpp llama-cpp end-to-end-workflow vision-llm ai-video-editor llm-vision llm-video-editor
-
Updated
Feb 15, 2026 - Python
AI-powered OCR for Diablo II: Resurrected - batch-extract item tooltips from screenshots using Vision LLMs (OpenAI, Groq, OpenRouter, LM Studio/Ollama). No Tesseract or EasyOCR needed.
python ocr ai computer-vision gaming pytorch openai diablo2 item-tracking item-tracker d2r groq loot-tracker diablo2resurrected openrouter ollama lmstudio loot-tracking vision-llm tooltip-ocr
-
Updated
Sep 3, 2025 - Python
A feature-rich desktop GUI for Ollama with Vision, RAG, and JSON support.
desktop-app python gui vision thinking code-execution rag ai-tools llm net8 local-ai ollama vision-llm
-
Updated
Feb 21, 2026 - Visual Basic .NET
A Python‑based incident detection engine that analyzes video feeds for motion, detects objects, and uses large language models (LLMs) to generate semantic descriptions of incidents. Designed for extensibility with custom detectors and processors.
-
Updated
Feb 8, 2026 - TypeScript
Free OCR powered by LLMs using OpenRouter — extract text from images with no API costs. Works with image URLs and Base64 inputs using free vision-capable models.
python ocr computer-vision image-processing text-extraction image-to-text api-integration llm free-ai openrouter ai-ocr free-ocr vision-llm
-
Updated
Dec 11, 2025 - Python
Multimodal AI-powered medical assistant with LLMs, speech, and image understanding.
-
Updated
Apr 18, 2025 - Jupyter Notebook
Free, offline OCR using local LLMs with Ollama. Convert images to text with vision-enabled models running entirely on your machine — no cloud, no API costs, full privacy.
python ocr computer-vision image-processing text-extraction image-to-text llm local-llm ollama ai-ocr offline-ocr free-ocr llm-ocr vision-llm
-
Updated
Dec 11, 2025 - Python
🖼️ Extract text from images locally using Ollama's LLMs—100% free, offline, and private. No API keys or cloud costs necessary.
python computer-vision offline image-processing embeddings plants openai ocr-recognition document-processing multimodal ml-engineering ai-engineering llm generative-ai local-llm ollama mistral-7b ai-ocr vision-llm
-
Updated
Feb 25, 2026 - Python
AI-powered tool that extracts structured data from bank statement images using LLaMA Vision and displays it in clean JSON and table formats. Built with Streamlit and pandas for fast, accurate financial document parsing.
-
Updated
Oct 27, 2025 - Python
A FastAPI-based backend service that extracts structured information from academic marksheets (images or PDFs) using OCR and an LLM, and returns a normalized JSON response with confidence scores.
docker ocr computer-vision json-api reactjs image-processing document-processing ai-api fastapi huggingface pdf-processing easyocr document-ai llm multimodal-ai google-gemini-api vision-llm marksheet-extraction
-
Updated
Jan 24, 2026 - Python
🤖 A Discord bot that scrapes daily tech comics (XKCD, MonkeyUser, Turnoff.us) and uses Vision LLMs (Llama-4 via Groq) to explain the jokes.
-
Updated
Dec 14, 2025 - Python
🤖 Automate UI interactions with ease using the PyMidscene Python SDK, leveraging Midscene.js for AI-driven, natural language commands.
python automation ai natural-language ui-testing browser-automation rpa playwright vision-llm midscene
-
Updated
Feb 25, 2026 - Python
Multi-engine image generation filter for Open WebUI. Features automated prompt enhancement, multi-language support, and real-time Vision QC scoring. Supports A1111, ComfyUI, and OpenAI backends with integrated performance telemetry.
python prompt-engineering stable-diffusion comfyui image-generation-ai open-webui vision-llm open-webui-functions
-
Updated
Feb 15, 2026 - Python
python nlp docker-compose web-ui embeddings feature-extraction privacy-focused searchable-pdf geometric-transformations no-api-key llm ollama llimage olmocr vision-llm
-
Updated
Feb 25, 2026 - Python
This repository focuses on customizing the Qwen2.5-Vision model for specific tasks. It provides step-by-step guidance, scripts, and best practices for fine-tuning the model on custom datasets. Ideal for developers and researchers, it ensures optimal performance and accuracy tailored to unique use cases.
transformer fine-tuning vision-transformer llm vision-language-model llm-training qwen qwen2-5 vision-llm
-
Updated
Apr 22, 2025 - Jupyter Notebook
Automated data extraction from PDF receipts to Excel using Vision LLM (tested with Qwen3-VL and olmOCR 2).
-
Updated
Feb 10, 2026 - Python
Improve this page
Add a description, image, and links to the vision-llm topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the vision-llm topic, visit your repo's landing page and select "manage topics."