mljourney

Extracting text from images with a language model means using a vision-capable LLM as an OCR engine — passing an image to the model and asking it to return the text it contains. For many use cases this works better than traditional OCR: it handles handwriting, low-quality scans, unusual fonts, mixed languages, and complex layouts … Read more

Speech-to-text models have diversified rapidly since Whisper’s release. In 2026, practitioners choosing a local STT model face a genuine selection problem: there are fast models and accurate models and streaming models and multilingual models, and the best choice depends on the specific deployment scenario. This guide cuts through the options with a task-first framework — … Read more

Video understanding with local LLMs means running a multimodal model on your own hardware to analyse, describe, or answer questions about video content — without sending frames to a cloud API. The capability became practical for local deployment in 2025 as models like LLaVA-NeXT-Video, InternVL2-Video, and Qwen2-VL made video understanding available in open-weight form. Local … Read more

Analysing charts with a vision LLM means asking a multimodal model to read, interpret, and reason about visual data — bar charts, line graphs, scatter plots, pie charts, heatmaps — without converting them to numbers first. The use case is practical and common: extracting values from a chart image in a PDF report, comparing trends … Read more

Multimodal RAG extends retrieval-augmented generation beyond text to include images, charts, figures, and tables embedded in documents. A standard text RAG pipeline loses everything visual — diagrams in technical manuals, charts in financial reports, figures in research papers — because it can only index and retrieve text. Multimodal RAG preserves these visual elements and makes … Read more

Whisper set the standard for open-source speech recognition when OpenAI released it in 2022. It remains the most widely deployed local speech-to-text model in 2026, but it is no longer uncontested — several alternatives have emerged that outperform it in specific scenarios: faster inference (Faster-Whisper, Parakeet), better real-time streaming (Silero, streaming Whisper variants), improved accuracy … Read more

Audio language models are multimodal AI systems that process audio natively — they can transcribe speech, understand spoken language, respond to audio queries, identify speakers, detect music, and even generate speech — without converting audio to text first as an intermediate step. The category expanded rapidly in 2024–2026 as native audio understanding moved from a … Read more

InternVL2 and LLaVA are two of the most widely benchmarked open-source vision-language models, but they represent different design philosophies and perform differently across task categories. LLaVA (Large Language and Vision Assistant) established the blueprint for efficient multimodal models through its simple visual instruction tuning approach. InternVL2 is a more recent series from Shanghai AI Lab … Read more

OpenAI’s Assistants API and custom agent frameworks represent two fundamentally different approaches to building AI agent applications. The Assistants API gives you a managed, hosted agent infrastructure with built-in tools, persistent threads, and file handling — you configure rather than build. Custom agents give you full architectural control at the cost of building and maintaining … Read more

Smolagents is Hugging Face’s minimal agent framework, released in early 2025. The name captures the design philosophy: small agents, small codebase, small API surface. Where frameworks like Agno and LangGraph add features and abstractions, Smolagents deliberately removes them — the entire core is a few hundred lines of Python that anyone can read and understand … Read more