Spaces:
Running
Running
| import subprocess | |
| import os | |
| mermaid_code = """ | |
| graph TD | |
| %% Styling | |
| classDef default fill:#1A1A1A,stroke:#444,stroke-width:2px,color:#FFF,rx:8px,ry:8px,font-family:arial; | |
| classDef mobile fill:#003366,stroke:#0055AA,stroke-width:2px,color:#FFF; | |
| classDef preproc fill:#333333,stroke:#555,stroke-width:2px,color:#FFF; | |
| classDef model fill:#4B0082,stroke:#8A2BE2,stroke-width:2px,color:#FFF; | |
| classDef condition fill:#2B2B2B,stroke:#F4A460,stroke-width:2px,color:#FFF,shape:rhombus; | |
| classDef external fill:#004d00,stroke:#009900,stroke-width:2px,color:#FFF; | |
| classDef final fill:#660000,stroke:#CC0000,stroke-width:2px,color:#FFF; | |
| %% Nodes | |
| UserApp[📱 Mobile App]:::mobile | |
| ImgUpload[🖼️ Image]:::preproc | |
| Question[⌨️ Question Text]:::preproc | |
| PIL[🐍 PIL Preprocessing<br/>RGB conversion]:::preproc | |
| CLIP[👁️ OpenAI CLIP ViT-B/32<br/>Image Features 512-dim]:::model | |
| GPT2[🤗 DistilGPT-2<br/>Tokenized Question]:::model | |
| Route1{Question<br/>spatial?}:::condition | |
| Spatial[📐 Spatial VQA Model<br/>8-head attention]:::model | |
| Base[🧠 Base VQA Model<br/>General VQA]:::model | |
| Decoder[🤗 GPT-2 Decoder<br/>vocab decode]:::model | |
| NeuralAns[💬 Neural Answer]:::final | |
| Route2{Knowledge<br/>question?}:::condition | |
| ObjDet[👁️ CLIP Object Detector<br/>Top-3 objects]:::model | |
| Wikidata[🌍 Wikidata SPARQL<br/>P31, P186, P366]:::external | |
| GroqV[⚡ Groq Llama-3.3<br/>Verbalizer]:::external | |
| KGAns[🧩 KG Enhancement]:::final | |
| FastAPI[🚀 FastAPI]:::preproc | |
| GroqA[⚡ Groq Llama-3.3<br/>Accessibility]:::external | |
| Audio[🔊 2-sentence description]:::final | |
| %% Edges | |
| UserApp -- "Image uploaded" --> ImgUpload | |
| UserApp -- "Question typed" --> Question | |
| ImgUpload --> PIL | |
| PIL --> CLIP | |
| Question --> GPT2 | |
| CLIP & GPT2 --> Route1 | |
| Route1 -- "YES" --> Spatial | |
| Route1 -- "NO" --> Base | |
| Spatial & Base -- "Beam search (width=5)" --> Decoder | |
| Decoder --> NeuralAns | |
| CLIP -- "Anchor similarity" --> Route2 | |
| Route2 -- "YES" --> ObjDet | |
| ObjDet -- "Detected objects" --> Wikidata | |
| Wikidata -- "Structured facts" --> GroqV | |
| GroqV --> KGAns | |
| FastAPI -- "Narration request" --> GroqA | |
| GroqA --> Audio | |
| NeuralAns & KGAns & Audio -- "JSON output" --> FastAPI | |
| FastAPI --> UserApp | |
| """ | |
| file_path = r"C:\Users\rdeva\Downloads\vqa_coes\architecture_draft.mmd" | |
| with open(file_path, "w", encoding="utf-8") as f: | |
| f.write(mermaid_code) | |
| print(f"Mermaid file saved to {file_path}") | |
| # Note: In a real environment, we would use mermaid-cli (mmdc) to convert this to SVG/PNG. | |
| # Since it might not be installed globally, we will just provide the mermaid file and | |
| # instructions, or generate an HTML wrapper that renders it in browser. | |
| html_path = r"C:\Users\rdeva\Downloads\vqa_coes\architecture_draft.html" | |
| html_content = f""" | |
| <!DOCTYPE html> | |
| <html> | |
| <head> | |
| <title>VQA Architecture Draft</title> | |
| <script type="module"> | |
| import mermaid from 'https://cdn.jsdelivr.net/npm/mermaid@10/dist/mermaid.esm.min.mjs'; | |
| mermaid.initialize({{ startOnLoad: true, theme: 'dark', flowchart: {{ curve: 'basis' }} }}); | |
| </script> | |
| <style> | |
| body {{ background-color: #0D1117; color: white; font-family: sans-serif; display: flex; justify-content: center; padding: 20px; }} | |
| .mermaid {{ background-color: #161B22; padding: 20px; border-radius: 10px; box-shadow: 0 4px 8px rgba(0,0,0,0.5); }} | |
| </style> | |
| </head> | |
| <body> | |
| <div class="mermaid"> | |
| {mermaid_code} | |
| </div> | |
| </body> | |
| </html> | |
| """ | |
| with open(html_path, "w", encoding="utf-8") as f: | |
| f.write(html_content) | |
| print(f"HTML viewer saved to {html_path}") | |