Implement RAG systems using Weaviate vector database. Use when building semantic search, document retrieval, or knowledge base systems.
This skill is limited to using the following tools:
Configure MoodleNRW RAG system with Weaviate vector store.
localhost:8095localhost:50055localhost:8000/opt/cloodle/tools/ai/multi_agent_rag_system//opt/cloodle/tools/ai/moodle-chatbot/import weaviate
client = weaviate.Client(
url="http://localhost:8095",
additional_headers={
"X-OpenAI-Api-Key": os.getenv("OPENAI_API_KEY", "")
}
)
# Start Weaviate
cd /opt/cloodle/tools/ai/multi_agent_rag_system
docker-compose up -d
# Check status
docker ps | grep weaviate
# View logs
docker logs multi_agent_rag_system_weaviate_1
schema = {
"class": "MoodleDocument",
"vectorizer": "text2vec-transformers",
"properties": [
{"name": "content", "dataType": ["text"]},
{"name": "source", "dataType": ["string"]},
{"name": "course_id", "dataType": ["int"]}
]
}
client.schema.create_class(schema)
| Model | Dimensions | Best For |
|---|---|---|
| nomic-embed-text | 768 | General purpose |
| bge-m3 | 1024 | Multilingual |
| mxbai-embed-large | 1024 | High quality |
cd /opt/cloodle/tools/ai/multi_agent_rag_system
source .venv/bin/activate
chainlit run app.py