Spring AI RAG with PGVector and Ollama Integration

spring-ai-rag/rag-with-pgvector/.gitattributes

@@ -0,0 +1,2 @@
+/mvnw text eol=lf
+*.cmd text eol=crlf

spring-ai-rag/rag-with-pgvector/.gitignore

@@ -0,0 +1,33 @@
+HELP.md
+target/
+.mvn/wrapper/maven-wrapper.jar
+!**/src/main/**/target/
+!**/src/test/**/target/
+
+### STS ###
+.apt_generated
+.classpath
+.factorypath
+.project
+.settings
+.springBeans
+.sts4-cache
+
+### IntelliJ IDEA ###
+.idea
+*.iws
+*.iml
+*.ipr
+
+### NetBeans ###
+/nbproject/private/
+/nbbuild/
+/dist/
+/nbdist/
+/.nb-gradle/
+build/
+!**/src/main/**/build/
+!**/src/test/**/build/
+
+### VS Code ###
+.vscode/

spring-ai-rag/rag-with-pgvector/.mvn/wrapper/maven-wrapper.properties

@@ -0,0 +1,2 @@
+distributionType=only-script
+distributionUrl=https://repo.maven.apache.org/maven2/org/apache/maven/apache-maven/3.9.11/apache-maven-3.9.11-bin.zip

spring-ai-rag/rag-with-pgvector/README.md

@@ -0,0 +1,38 @@
+# Spring AI RAG with PGVector Example
+
+This is an example project demonstrating **Retrieval-Augmented Generation (RAG)** using **Spring AI**, with **PGVector** as the vector database and **Ollama** for running LLM and embedding models. This setup uses **Docker** for running the PGVector database locally.
+
+---
+
+## 🧠 What This Project Does
+
+- Upload a PDF file with paragraphs to the application.
+- Extracts content and embeds it using a local embedding model via Ollama.
+- Stores the embeddings in a PostgreSQL + PGVector database.
+- Enables retrieval and interaction with a local chat LLM (via Ollama).
+- Provides a simple RAG flow powered by Spring AI.
+
+---
+
+## 🛠 Prerequisites
+
+Before running the application, make sure you have the following installed and configured:
+
+- **Java 17**
+- **Docker** (to run PGVector via `compose.yaml`)
+- **Ollama** installed locally with:
+    - `gemma:3b` (chat model)
+    - `nomic-embed-text:latest` (embedding model)
+- **Postman** or any API testing tool (for uploading PDF files)
+- **DBeaver** or another database UI client (optional, for inspecting the database)
+
+---
+
+## ⚙️ Setup Instructions
+
+### 1. Start the PGVector Database
+
+Ensure Docker is running and start the PGVector service using the provided `compose.yaml`:
+
+```bash
+docker compose up -d

spring-ai-rag/rag-with-pgvector/compose.yaml

@@ -0,0 +1,11 @@
+services:
+  pgvector:
+    image: 'pgvector/pgvector:pg16'
+    environment:
+      - 'POSTGRES_DB=rag-with-pgvector'
+      - 'POSTGRES_PASSWORD=user'
+      - 'POSTGRES_USER=user'
+    labels:
+      - "org.springframework.boot.service-connection=postgres"
+    ports:
+      - '5432:5432'