readme.adoc

Camel Example Spring Boot RAG with Qdrant

This example shows a full end-to-end RAG (Retrieval-Augmented Generation) pipeline using the Camel OpenAI component for embeddings and chat, with Qdrant as vector store.

Prerequisites

1. A running Qdrant instance:

camel infra run qdrant

1. A running Ollama instance with the required models:

ollama pull nomic-embed-text
ollama pull granite4:3b

How to run

You can run this example using:

mvn spring-boot:run

What happens

When the application starts, it executes the following RAG pipeline:

1. Create Collection - Creates rag_collection in Qdrant. A collection is a named group of points, where each point holds an embedding vector and an optional payload (in this case, the original text). The collection is configured with Cosine distance, which measures how semantically similar two vectors are: the closer to 1.0, the more similar.

2. Index Documents - Reads .txt files from the input/ directory (a playlist of songs is provided as sample data). Each document is sent to the nomic-embed-text model via openai:embeddings, which converts the text into a 768-dimensional numerical vector (the embedding). An embedding is a dense array of floats that captures the semantic meaning of the text: texts with similar meaning produce vectors that are close together in the vector space. The embedding and the original text are then upserted into Qdrant as a point.

3. RAG Query - Takes a question (e.g. "Give me at least five songs containing the 'moon' word in the title"), converts it into an embedding using the same model, and performs a similarity search in Qdrant to find the documents whose vectors are closest to the question vector. The retrieved document texts are assembled into a context prompt and sent to openai:chat-completion for a grounded answer.

Configuration

Edit src/main/resources/application.properties to configure:

• camel.component.qdrant.host - Qdrant server host (default: localhost)

• camel.component.qdrant.port - Qdrant gRPC port (default: 6334)

• camel.component.openai.base-url - OpenAI-compatible API base URL (default: Ollama at http://localhost:11434/v1)

• camel.component.openai.model - Chat completion model (default: granite4:3b)

• camel.component.openai.embedding-model - Embedding model (default: nomic-embed-text)

To use OpenAI instead of Ollama, change the base URL and set your API key:

camel.component.openai.base-url=https://api.openai.com/v1
camel.component.openai.api-key=${OPENAI_API_KEY}
camel.component.openai.model=gpt-4o-mini
camel.component.openai.embedding-model=text-embedding-3-small

Note: when switching to a different embedding model, update the vector size in the collection creation accordingly (e.g., 1536 for text-embedding-3-small).

Trying out the example on OpenShift

First, start with creating a new OpenShift project:

$ oc new-project csb-example-qdrant

Deploy a Qdrant instance:

$ cat << EOF| oc apply -f -
apiVersion: apps/v1
kind: Deployment
metadata:
  name: qdrant
spec:
  replicas: 1
  selector:
    matchLabels:
      app: qdrant
  template:
    metadata:
      labels:
        app: qdrant
    spec:
      containers:
        - name: qdrant
          image: qdrant/qdrant:latest
          ports:
            - containerPort: 6333
            - containerPort: 6334
---
apiVersion: v1
kind: Service
metadata:
  name: qdrant
spec:
  selector:
    app: qdrant
  ports:
    - name: http
      port: 6333
      targetPort: 6333
    - name: grpc
      port: 6334
      targetPort: 6334
EOF

Deploy an Ollama instance with the required models:

$ cat << EOF| oc apply -f -
apiVersion: apps/v1
kind: Deployment
metadata:
  name: ollama
spec:
  replicas: 1
  selector:
    matchLabels:
      app: ollama
  template:
    metadata:
      labels:
        app: ollama
    spec:
      containers:
        - name: ollama
          image: ollama/ollama:latest
          ports:
            - containerPort: 11434
---
apiVersion: v1
kind: Service
metadata:
  name: ollama
spec:
  selector:
    app: ollama
  ports:
    - port: 11434
      targetPort: 11434
EOF

Wait for both pods to be ready, then pull the required models:

$ oc wait --for=condition=available deployment/qdrant deployment/ollama --timeout=300s
$ oc exec deployment/ollama -- ollama pull nomic-embed-text
$ oc exec deployment/ollama -- ollama pull granite4:3b

How to run

The application is deployed using the openshift-maven-plugin that takes care of creating all the necessary OpenShift resources.

Simply use the following command to deploy the application:

$ mvn clean package -Popenshift

After the application pod reaches the Ready state, you can try the same steps as in the local machine deployment.

To view the application logs, use oc logs deployment/csb-qdrant

Help and contributions

If you hit any problem using Camel or have some feedback, then please let us know.

We also love contributors, so get involved :-)

The Camel riders!