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

23
ai_platform/ML_PROJECTS_DEPLOY_KEYS_AND_REQUIREMENTS.md
View file

@ -8,6 +8,10 @@
NU pe email/Slack public, NU în repo public, NU pe wiki. Pentru transfer:
scp criptat sau message DM.
> **Notă topologie:** acest document descrie topologia **multi-host de referință**
> (URL-uri/IP-uri distribuite pe mai multe mașini). Valorile reale pentru
> deployment-ul **single-host** livrat se află în `local_gpu_stack/.env.example`.
---
## Cuprins
@ -53,8 +57,8 @@ Stack-ul depinde de aceste hosts care rulează GPU-side:
|---|---|---|
| LLM Router (gateway Qwen) | `http://10.11.10.17:14011` | web, didi_brain, dashboard |
| vLLM Qwen3.5-35B (direct) | `http://10.11.10.17:14001` | dashboard (provider stats) |
| llama.cpp Qwen3.5-397B #1 | `http://10.11.10.18:14001` | LLM router upstream |
| llama.cpp Qwen3.5-397B #2 | `http://10.11.10.19:14001` | LLM router upstream |
| llama.cpp Qwen3.5-35B-A3B #1 | `http://10.11.10.18:14001` | LLM router upstream |
| llama.cpp Qwen3.5-35B-A3B #2 | `http://10.11.10.19:14001` | LLM router upstream |
| BGE-M3 embeddings | `http://10.11.10.15:8200` | didi_brain (Atomic auto-embeds) |
| BGE-reranker-v2-m3 | `http://10.11.10.15:8100` | didi_brain (gather rerank) |
| Whisper STT | (host-local, audio module) | audio module |
@ -188,13 +192,14 @@ LLM_VLLM_URL=http://localhost:14001
LLM_LLAMACPP_URLS=http://10.11.10.18:14001,http://10.11.10.19:14001
# Models
MODEL_REASONING=Qwen3.5-397B-A17B
MODEL_REASONING=Qwen/Qwen3.5-35B-A3B
MODEL_REASONING_BACKEND=llamacpp
MODEL_FAST=qwen3.5
MODEL_FAST_BACKEND=vllm
MODEL_FAST_ENABLED=false
MODEL_VISION=gemma-3-27b-it
MODEL_VISION_URL=http://10.11.10.16:8001
# Vision: nu exista model vision separat — OCR/vision se face prin Qwen3.5 (gateway LLM)
MODEL_VISION=qwen3.5
MODEL_VISION_URL=http://10.11.10.17:14011
MODEL_VISION_ENABLED=false
# Embeddings
@ -253,7 +258,7 @@ AUDIO_EXTERNAL_URL=http://localhost:54300
CATALOG_EXTERNAL_URL=http://localhost
CATALOG_PORT=11000
CATALOG_LLM_URL=http://didiAI-llm-api:14011
CATALOG_AUDIO_URL=http://didiAI-audio-api:54300
CATALOG_AUDIO_URL=http://didiAI-audio:54300
CATALOG_WEB_URL=http://didiAI-web-api:51100
CATALOG_VIDEO_URL=
```
@ -273,9 +278,9 @@ GATEWAY_API_TOKEN=0x2-m0W5oG7MjZUu5v3-ejBWMExwLeGDv4aRKqBI7bM
| 51100 | Web API (gather, search, fetch) | `didiAI-web-api` |
| 51300 | Dashboard UI + API | `didiAI-dashboard` |
| 15432 | Dashboard Postgres (debug only) | `didiAI-dashboard-db` |
| 54300 | Audio STT proxy | `didiAI-audio-proxy` |
| 54300 | Audio STT | `didiAI-audio` |
| 54600 | Video Analysis | `didiAI-video-api` |
| 55100 | SearXNG metasearch | `didiAI-web-searxng` |
| 8080 (intern) | SearXNG metasearch | `didiAI-web-searxng` |
| 8090 | didi-brain HTTP API | `didibrain-api` |
| 8088 | didi-brain Atomic | `didibrain-atomic` |
| 5434 | didi-brain Postgres (debug only) | `didibrain-postgres` |
@ -360,7 +365,7 @@ BRAIN_IMPORT_CORPUS=0 BRAIN_RUN_EXTRACTION=0 ./scripts/bootstrap_deploy.sh
### 8. Conectează web-api la rețeaua didibrain
Web-api rulează pe network `deploy_default`, didi-brain pe `didibrain`. Trebuie unit:
Web-api rulează pe network `didi-network`, didi-brain pe `didibrain`. Trebuie unit:
```bash
docker network connect didibrain didiAI-web-api