Files
homelab/podman/retired/localai/README.md

264 lines
6.5 KiB
Markdown

# Local AI with Anything LLM
<https://github.com/Mintplex-Labs/anything-llm/blob/master/docker/HOW_TO_USE_DOCKER.md>
<https://localai.io/>
## Running with Podman
This installs both Local AI and Anything LLM as backend/frontend services.
```bash
podman network create localai
# Local AI
podman run \
-d \
-p 127.0.0.1:8080:8080 \
--network localai \
--name local-ai \
-v /models:/build/models \
quay.io/go-skynet/local-ai:latest-cpu
# Anything LLM Interface
export STORAGE_LOCATION=/anything-llm && \
mkdir -p $STORAGE_LOCATION && \
touch "$STORAGE_LOCATION/.env" && \
chown -R 1000:1000 $STORAGE_LOCATION && \
podman run \
-d \
-p 127.0.0.1:3001:3001 \
--name anything-llm \
--network localai \
--cap-add SYS_ADMIN \
-v ${STORAGE_LOCATION}:/app/server/storage \
-v ${STORAGE_LOCATION}/.env:/app/server/.env \
-e STORAGE_DIR="/app/server/storage" \
mintplexlabs/anythingllm
```
### Quadlets with Podlet
Note: on Arch Linux the location is `/etc/containers/systemd/`.
<https://wiki.archlinux.org/title/Podman>
```bash
podman run --rm ghcr.io/containers/podlet --install --description "Local AI Network" \
podman network create localai
podman run --rm ghcr.io/containers/podlet --install --description "Local AI" \
podman run \
-d \
-p 127.0.0.1:8080:8080 \
--network localai \
--name local-ai \
-v /models:/build/models \
quay.io/go-skynet/local-ai:latest-cpu
export STORAGE_LOCATION=/anything-llm && \
podman run --rm ghcr.io/containers/podlet --install --description "Anything LLM" \
podman run \
-d \
-p 127.0.0.1:3001:3001 \
--name anything-llm \
--network localai \
--cap-add SYS_ADMIN \
-v ${STORAGE_LOCATION}:/app/server/storage \
-v ${STORAGE_LOCATION}/.env:/app/server/.env \
-e STORAGE_DIR="/app/server/storage" \
docker.io/mintplexlabs/anythingllm
```
Make sure to add
```conf
[Service]
Restart=always
```
To the service to have them autostart.
Put the generated files in `/usr/share/containers/systemd/`.
## Models
Example configs can be found here:
<https://github.com/mudler/LocalAI/tree/9099d0c77e9e52f4a63c53aa546cc47f1e0cfdb1/gallery>
### Config
```yaml
name: llama-3.2
parameters:
model: huggingface/Llama-3.2-3B-Instruct-f16.gguf
temperature: 0.6
backend: llama-cpp
# Default context size
context_size: 8192
threads: 16
```
### Chat
llama-3.2-3b-instruct:q8_0
### Code
<https://huggingface.co/bartowski/Codestral-22B-v0.1-GGUF/tree/main>
### Agent
llama-3.2-3b-instruct:q8_0
## Podman systemd service
See [generating AWS credentials](cloud/graduated/aws_iam/README.md)
```bash
curl "https://awscli.amazonaws.com/awscli-exe-linux-x86_64.zip" -o "awscliv2.zip"
unzip awscliv2.zip
./aws/install
# Configure default credentials
aws configure
```
Open http/s in firewalld:
```bash
firewall-cmd --permanent --zone=public --add-service=http
firewall-cmd --permanent --zone=public --add-service=https
firewall-cmd --reload
```
Here are the detailed instructions for installing and setting up Nginx on Fedora Linux with Certbot
using the Route53 DNS challenge to put in front of a service called "Anything LLM" running on port
3001 with WebSockets. The domain will be chatreesept.reeseapps.com.
1. Install Nginx:
```
dnf install -y nginx
```
2. Start and enable Nginx service:
```
systemctl enable --now nginx
```
3. Install Certbot and the Route53 DNS plugin:
```
dnf install -y certbot python3-certbot-dns-route53
```
4. Request a certificate for your domain using the Route53 DNS challenge:
```
certbot certonly --dns-route53 -d chatreesept.reeseapps.com
```
Follow the prompts to provide your Route53 credentials and email address.
5. Configure Nginx for your domain: Create a new Nginx configuration file for your domain:
```
vim /etc/nginx/conf.d/chatreesept.reeseapps.com.conf
```
Add the following configuration to the file:
```
keepalive_timeout 1h;
send_timeout 1h;
client_body_timeout 1h;
client_header_timeout 1h;
proxy_connect_timeout 1h;
proxy_read_timeout 1h;
proxy_send_timeout 1h;
server {
listen 80;
server_name chatreesept.reeseapps.com;
location / {
return 301 https://$host$request_uri;
}
}
server {
listen 443 ssl;
server_name chatreesept.reeseapps.com;
ssl_certificate /etc/letsencrypt/live/chatreesept.reeseapps.com/fullchain.pem;
ssl_certificate_key /etc/letsencrypt/live/chatreesept.reeseapps.com/privkey.pem;
location / {
client_max_body_size 50m;
proxy_pass http://localhost:3001;
proxy_http_version 1.1;
proxy_set_header Upgrade $http_upgrade;
proxy_set_header Connection "upgrade";
proxy_set_header Host $host;
proxy_cache_bypass $http_upgrade;
}
}
```
6. Test your Nginx configuration for syntax errors:
```
nginx -t
```
If there are no errors, reload Nginx to apply the changes:
```
systemctl reload nginx
```
7. Set up automatic certificate renewal: Add the following line to your crontab to renew the
certificate daily:
```
sudo crontab -e
```
Add the following line to the end of the file:
```
0 0 * * * certbot renew --quiet --no-self-upgrade --pre-hook "systemctl stop nginx" --post-hook "systemctl start nginx"
```
Now, your "Anything LLM" service running on port 3001 with WebSockets is accessible through the
domain chatreesept.reeseapps.com with a valid SSL certificate from Let's Encrypt. The certificate
will be automatically renewed daily.
## Nginx
```bash
certbot-3 certonly --dns-route53 -d chatreesept.reeseapps.com
```
Make sure to add the following timeout configurations to your http block:
```conf
server {
# Enable websocket connections for agent protocol.
location ~* ^/api/agent-invocation/(.*) {
proxy_pass http://0.0.0.0:3001;
proxy_http_version 1.1;
proxy_set_header Upgrade $http_upgrade;
proxy_set_header Connection "Upgrade";
}
listen 80;
server_name [insert FQDN here];
location / {
# Prevent timeouts on long-running requests.
proxy_connect_timeout 605;
proxy_send_timeout 605;
proxy_read_timeout 605;
send_timeout 605;
keepalive_timeout 605;
# Enable readable HTTP Streaming for LLM streamed responses
proxy_buffering off;
proxy_cache off;
# Proxy your locally running service
proxy_pass http://0.0.0.0:3001;
}
}
```