Amazon Bedrock: dane uwierzytelniające i routing modeli

docker run --rm -p 8080:8080 --env-file .env enterpilot/gomodel

docker run --rm -p 8080:8080 \
  -e GOMODEL_MASTER_KEY="change-me" \
  -e BEDROCK_BASE_URL="us-east-1" \
  -e AWS_ACCESS_KEY_ID="..." \
  -e AWS_SECRET_ACCESS_KEY="..." \
  enterpilot/gomodel

make build
./bin/gomodel

curl -s http://localhost:8080/v1/chat/completions \
  -H "Authorization: Bearer $GOMODEL_MASTER_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic.claude-3-5-haiku-20241022-v1:0",
    "messages": [{"role": "user", "content": "Reply with the single word ok."}],
    "max_tokens": 80
  }'

import os

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:8080/v1",
    api_key=os.environ["GOMODEL_MASTER_KEY"],
)

completion = client.chat.completions.create(
    model="anthropic.claude-3-5-haiku-20241022-v1:0",
    messages=[{"role": "user", "content": "Reply with the single word ok."}],
    max_tokens=80,
)

print(completion.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "http://localhost:8080/v1",
  apiKey: process.env.GOMODEL_MASTER_KEY,
});

const completion = await client.chat.completions.create({
  model: "anthropic.claude-3-5-haiku-20241022-v1:0",
  messages: [{ role: "user", content: "Reply with the single word ok." }],
  max_tokens: 80,
});

console.log(completion.choices[0].message.content);