diff --git a/README.md b/README.md index bacc741..1d58913 100644 --- a/README.md +++ b/README.md @@ -1,64 +1,67 @@ # trans-video -Public landing page for a video transcription, AI summary, and mind-map workflow. +Public landing page for an AI media and knowledge automation workflow. -This repository is intentionally lightweight. The active service code remains private while deployment credentials, sample media, user content, internal paths, and operational configuration are being removed from publishable materials. +This repository is intentionally lightweight. It explains the public-safe +architecture for turning media and knowledge sources into structured review +material while the active implementation and operational material remain +private. -## What The Project Does +## Portfolio Entry -The project line covers a pipeline for turning long-form video into structured review material: +- Public case-study overview: -| Stage | Purpose | -|---|---| -| Source ingestion | Accept local video files or video-platform source material after authorization | -| Audio extraction | Prepare audio for speech recognition | -| Transcription | Run Whisper-class speech transcription and segment alignment | -| AI summary | Generate structured summaries, topic sections, and action notes | -| Mind map output | Render summary structure as Markmap-style interactive mind maps | -| Service orchestration | Coordinate API, background jobs, queue/cache, and model calls | - -The private implementation currently maps to a FastAPI/Celery/Redis style service with GPU transcription and LLM-assisted summarization. - -## Repository Status +## What The Project Shows -This public repository is a project pointer, not the active source workspace. +The project line covers a reusable AI tool-product workflow: -| Repository | Visibility | Role | -|---|---:|---| -| `trans-video` | PUBLIC | Public landing page and sanitized project description | -| `trans-video-api` | PRIVATE | Current service extraction/API workspace | -| `02-trans_video` | PRIVATE | Legacy workspace kept as historical reference | +| Stage | Purpose | +|---|---| +| Ingestion | Accept publishable media or knowledge sources | +| Extraction | Prepare audio, text, or source material for processing | +| AI structuring | Generate summaries, topic sections, and action notes | +| Mind-map output | Render the structured result as an interactive map | +| Document sync | Move reviewed material into a reusable knowledge base | +| Orchestration | Coordinate API, background jobs, status tracking, and retries | + +## Architecture + +```mermaid +flowchart LR + A[Input source] --> B[Ingestion] + B --> C[Extraction] + C --> D[AI structuring] + D --> E[Summary and mind-map output] + E --> F[Document sync] + F --> G[Review and reuse] + G --> D +``` ## Interview / Portfolio Positioning Use this project as an AI tool-product example: -- backend workflow design for long-running media tasks, -- queue-based processing around CPU/GPU-heavy steps, +- backend workflow design for long-running media and knowledge tasks, +- queue-oriented processing around CPU/GPU-heavy steps, - transcription-to-summary-to-mind-map product flow, -- prompt/output structuring for readable study material, -- public/private boundary management for user media and deployment data. +- structured output design for readable study material, +- public/private boundary management for user content and deployment details. It is a support project rather than the main robotics project line. ## Public Boundary -This repository should not contain: +This repository is a public landing page and sanitized case-study pointer. It +does not publish the active service workspace, private source material, +credentials, deployment settings, internal infrastructure, operational traces, +or full task outputs. -- API keys, cookies, tokens, service credentials, or model-provider secrets, -- private media, user uploads, customer data, or copyrighted source samples, -- internal hostnames, deployment IPs, queue credentials, or storage paths, -- private prompt logs or production transcripts. - -Any future demo should use synthetic or explicitly publishable sample media. +Future demos should use synthetic or explicitly publishable sample material. ## Next Public Artifacts Planned public materials: -1. sanitized architecture diagram, -2. sample input/output using publishable media, -3. short case-study README or NotionNext article, -4. screenshot of the generated mind-map output. - -Until those are available, this repository should be treated as a clean public pointer to the project line. +1. synthetic sample input/output, +2. screenshot of a generated mind-map output, +3. short public-safe case-study notes linked from the portfolio overview.