n8nとollamaを連動する その１：n8nチャットとnetcatでためす

外観

n8nのdocker

まず、lobechatとollamaを実験したときのネットワーク名を

$ docker inspect ollama | jq '.[0].NetworkSettings.Networks | keys'
[
  "lobe-net"
]

この名前をネットワーク名として変数に保存

NETWORK_NAME="lobe-net"

$ docker run -d \
  --name n8n_docker \
  --network $NETWORK_NAME \
  -p 5678:5678 \
  -v n8n_data:/home/node/.n8n \
  --restart unless-stopped \
  n8nio/n8n:1.100.1

ollama

openaiのときと同様、認証してモデル選択をします

HTTPリクエスト

key

{{ $json.text }}

受け手のnetcat

$ nc -l -w 3 -p 9999
POST / HTTP/1.1
Accept: application/json,text/html,application/xhtml+xml,application/xml,text/*;q=0.9, image/*;q=0.8, */*;q=0.7
Content-Type: application/json
User-Agent: axios/1.8.3
Content-Length: 278
Accept-Encoding: gzip, compress, deflate, br
Host: 172.17.0.1:9999
Connection: close

{"value":"Awesome! That's great to hear. Local n8n and local Ollama can be really powerful – and cool! \n\nSo, what's the test about? Are you running the test with a specific dataset in Ollama and configuring the workflow in n8n?\n\nLet's go! 😊 \n\nHow's it going so far?"}