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

22
ai_platform/DEPLOYMENT.md
View file

@ -1,5 +1,7 @@
# Deployment Guide
> **Note — delivered deployment:** the delivered stack runs **single-host on the GPU machine** via `ai_platform/local_gpu_stack/deploy.sh` (see `local_gpu_stack/README.md`). The guide below describes the **reference multi-host variant** (CPU host + separate GPU host), kept intentionally for portability.
This guide covers bootstrapping the **web + dashboard** stack on a fresh CPU-only host. All GPU-dependent services (`llm-inference`, `embeddings`, `rerank`, `audio`, `video-analysis`) remain on a separate GPU machine and are called over HTTP.
---
@ -27,7 +29,7 @@ This guide covers bootstrapping the **web + dashboard** stack on a fresh CPU-onl
│ │
│ ┌───────────────────┐ │
│ │ SearXNG │ (existing — free tier source of truth) │
│ │ :55100/8080 │ │
│ │ :8080 (intern) │ │
│ └───────────────────┘ │
│ │
└──────────┬────────────────────────────────────────────────────────────────────────────┘
@ -90,7 +92,7 @@ cd ml-projects
The script will:
1. Verify Docker + Compose.
2. Create the `deploy_default` network.
2. Create the `didi-network` network.
3. Prompt for:
- GPU host address (for LLM URL)
- SearXNG container name / URL
@ -120,8 +122,8 @@ If the bootstrap script fails or you prefer manual control:
### 1. Create the network
```bash
docker network inspect deploy_default >/dev/null 2>&1 \
|| docker network create deploy_default
docker network inspect didi-network >/dev/null 2>&1 \
|| docker network create didi-network
```
### 2. Ensure SearXNG is reachable
@ -129,7 +131,7 @@ docker network inspect deploy_default >/dev/null 2>&1 \
If SearXNG is already running on this host, connect it to the network:
```bash
docker network connect deploy_default <searxng-container-name>
docker network connect didi-network <searxng-container-name>
```
Otherwise, deploy the bundled SearXNG:
@ -248,7 +250,7 @@ The web-api polls the dashboard for runtime config every 30s and fires events ba
WEB_DASHBOARD_URL=http://didiAI-dashboard:51300
```
Both containers must be on the `deploy_default` network for internal hostname resolution.
Both containers must be on the `didi-network` network for internal hostname resolution.
---
@ -368,10 +370,10 @@ docker start didiAI-dashboard
## Troubleshooting
### `docker network deploy_default not found`
### `docker network didi-network not found`
```bash
docker network create deploy_default
docker network create didi-network
```
### SearXNG unreachable from web-api
@ -379,9 +381,9 @@ docker network create deploy_default
Check that SearXNG is on the shared network:
```bash
docker network inspect deploy_default | grep -A2 searxng
docker network inspect didi-network | grep -A2 searxng
# If missing:
docker network connect deploy_default <searxng-container>
docker network connect didi-network <searxng-container>
```
Then verify the hostname/port in `WEB_SEARXNG_BASE_URL`.