54 lines
841 B
Markdown
54 lines
841 B
Markdown
# AI Assistant Java (Spring AI + pgvector)
|
|
|
|
This module is an independent Spring Boot 3 service that provides an OpenAI-compatible API.
|
|
|
|
## Requirements
|
|
|
|
- Java 17+
|
|
- PostgreSQL with pgvector
|
|
- Ollama (local inference)
|
|
|
|
## Start pgvector (Docker)
|
|
|
|
```
|
|
docker run --name pgvector -e POSTGRES_PASSWORD=postgres -e POSTGRES_DB=assistant \
|
|
-p 5432:5432 -d pgvector/pgvector:pg16
|
|
```
|
|
|
|
## Start Ollama models
|
|
|
|
```
|
|
ollama pull qwen2.5:7b
|
|
ollama pull bge-m3
|
|
```
|
|
|
|
## Configure
|
|
|
|
- `src/main/resources/application.yml`
|
|
- `src/main/resources/domains.yml`
|
|
|
|
## Run
|
|
|
|
```
|
|
./mvnw spring-boot:run
|
|
```
|
|
|
|
## OpenAI-compatible endpoint
|
|
|
|
```
|
|
POST http://127.0.0.1:8010/v1/chat/completions
|
|
```
|
|
|
|
Sample payload:
|
|
|
|
```
|
|
{
|
|
"model": "local",
|
|
"tenant_id": "customer_a",
|
|
"stream": true,
|
|
"messages": [
|
|
{"role": "user", "content": "订单有多少?"}
|
|
]
|
|
}
|
|
```
|