clossers/didi-lot1-ai
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

LOT 1 - Optimizare script build -Instalare mono comanda

Browse source
This commit is contained in:
Dezvoltari Evotech 2026-06-27 06:42:02 -07:00
parent 5380c3fc63
commit 42ff22bf85
127 changed files with 16163 additions and 532 deletions
Download patch file Download diff file Expand all files Collapse all files

44
ai_platform/README.md
View file

@ -245,13 +245,21 @@ Port allocation follows datacenter schema (5-digit ports):
| Port | Service | Environment |
|------|---------|-------------|
| 11000 | Catalog API | Production |
| 14001 | Qwen3.5-35B-A3B | Production |
| 14011 | LLM API Gateway | Production |
| 11000 | Gateway (nginx, external entry) | Production |
| 11000 | Catalog API (internal, via gateway) | Production |
| 14001 | vLLM Qwen3.5-35B-A3B | Production |
| 14011 | LLM Inference API (router) | Production |
| 14100 | Embeddings API | Production |
| 14200 | Rerank API | Production |
| 51100 | Web API | Development |
| 51300 | Dashboard | Development |
| 54300 | Audio API | Development |
| 54500 | BusterX | Development |
| 54600 | Video API | Development |
| 54400 | Extractors API | Development |
| 54500 | BusterX vLLM | Development |
| 54600 | Video Analysis API | Development |
| 8080 (intern) | SearXNG | Development |
| 8085 | Forensic Features API | Other |
| 8090 | didi_brain API | Other |
**Guidelines:**
- Use 1xxxx for production services
@ -377,11 +385,19 @@ Reviewers will check for:
| Module | Port | Description | Status |
|--------|------|-------------|--------|
| [catalog-api](modules/catalog-api/) | 11000 | Service catalog & discovery gateway | Active |
| [llm-inference](modules/llm-inference/) | 14011 | Unified LLM inference with multiple backends | Active |
| [audio](modules/audio/) | 54300 | Speech-to-text (Whisper) | Active |
| [video-analysis](modules/video-analysis/) | 54600 | Deepfake detection & semantic video analysis | Active |
| [gateway](modules/gateway/) | 11000 | nginx reverse proxy — single external entry point | Active |
| [catalog-api](modules/catalog-api/) | 11000 | Service catalog & discovery aggregator (internal) | Active |
| [llm-inference](modules/llm-inference/) | 14011 | Unified LLM inference (Qwen3.5-35B-A3B) with multiple backends | Active |
| [embeddings](modules/embeddings/) | 14100 | OpenAI-compatible embeddings (BAAI/bge-m3) | Active |
| [rerank](modules/rerank/) | 14200 | Document reranking (BAAI/bge-reranker-v2-m3) | Active |
| [web](modules/web/) | 51100 | Web scraping & fact-checking evidence gathering | Active |
| [dashboard](modules/dashboard/) | 51300 | Admin UI + API (monitoring, config, RBAC) | Active |
| [audio](modules/audio/) | 54300 | Speech-to-text (Whisper large-v3-turbo) | Active |
| [extractors](modules/extractors/) | 54400 | Feature extraction: metadata/sentiment/OCR/NER (GLiNER)/detect (YOLOv8n) | Active |
| [video-analysis](modules/video-analysis/) | 54600 | Deepfake detection (BusterX) & semantic video analysis | Active |
| [forensic_features](modules/forensic_features/) | 8085 | Forensic detectors (rPPG/lip-sync/forgery) via MediaPipe | Active |
| [didi_brain](modules/didi_brain/) | 8090 | Result cache (Postgres/pgvector) + RAG + fact-checking | Active |
| [cloak](modules/cloak/) | internal | Stealth SERP scraper (tier-3 fallback for web) | Active |
## Port Allocation Summary
@ -396,12 +412,20 @@ Port allocation follows datacenter schema (5-digit ports):
| Port | Service | Module | Environment |
|------|---------|--------|-------------|
| 11000 | Catalog API | catalog-api | Production |
| 11000 | Gateway (nginx, external entry) | gateway | Production |
| 11000 | Catalog API (internal) | catalog-api | Production |
| 14001 | vLLM Qwen3.5-35B-A3B | llm-inference | Production |
| 14011 | LLM API Gateway | llm-inference | Production |
| 14100 | Embeddings API | embeddings | Production |
| 14200 | Rerank API | rerank | Production |
| 51100 | Web API | web | Development |
| 51300 | Dashboard | dashboard | Development |
| 54300 | Audio API (Whisper) | audio | Development |
| 54400 | Extractors API | extractors | Development |
| 54500 | BusterX vLLM | video-analysis | Development |
| 54600 | Video Analysis API | video-analysis | Development |
| 8080 (intern) | SearXNG | web | Development |
| 8085 | Forensic Features API | forensic_features | Other |
| 8090 | didi_brain API | didi_brain | Other |
For detailed endpoint documentation, see [ENDPOINTS.md](ENDPOINTS.md).