AI Module Configuration example

Below you can see a configuration example using LiteLLM with OpenAI, PgVector as RAG and the Ingestion process configured in preview mode.

See Initialize and configure the AI Content Assistant and child pages for detailed explanation on the available options and supported confgiurations

Properties format

brxm.ai.provider=LiteLLM
brxm.ai.chat.max-messages=30
brxm.ai.chat.pdf.max-size-bytes=19000

#LiteLLM
spring.ai.litellm.api.url=https://mylitellmhost/
spring.ai.litellm.api_key=mykey
spring.ai.litellm.chat.options.model=openai/gpt-4o
spring.ai.litellm.chat.options.max-tokens=15000
spring.ai.litellm.embedding.options.model=openai/text-embedding-3-large
spring.ai.litellm.embedding.options.dimensions=1536

#Vector store config
brxm.ai.vectorstore=PgVector
brxm.ai.vectorstore.pgvector.url=jdbc:postgresql://mypostgreshost:5432/myvectordb
brxm.ai.vectorstore.pgvector.password=mypassword
brxm.ai.vectorstore.pgvector.username=mypguser
brxm.ai.vectorstore.pgvector.dimensions=1536

#Ingestion config
brxm.ai.ingest.mode=preview
brxm.ai.ingest.types=myproject:bannerdocument, hippogallery:exampleAssetSet
brxm.ai.ingest.interval=120
brxm.ai.ingest.batch-size=5
brxm.ai.ingest.delay=1000
brxm.ai.ingest.initial-delay=300

Yaml format

/hippo:moduleconfig:
  jcr:primaryType: hipposys:moduleconfig
 
  brxm.ai.provider: LiteLLM
  brxm.ai.chat.max-messages: '30'
  brxm.ai.chat.pdf.max-size-bytes: '19000'

  #LiteLLM
  spring.ai.litellm.api.url: https://mylitellmhost/
  spring.ai.litellm.api_key: mykey
  spring.ai.litellm.chat.options.model: openai/gpt-4o
  spring.ai.litellm.chat.options.max-tokens: '15000'
  spring.ai.litellm.embedding.options.model: openai/text-embedding-3-large
  spring.ai.litellm.embedding.options.dimensions: '1536'

  #Vector store config
  brxm.ai.vectorstore: PgVector
  brxm.ai.vectorstore.pgvector.url: jdbc:postgresql://mypostgreshost:5432/myvectordb 
  brxm.ai.vectorstore.pgvector.password: mypassword
  brxm.ai.vectorstore.pgvector.username: mypguser
  brxm.ai.vectorstore.pgvector.dimensions: '1536'

  #Ingestion config 
  brxm.ai.ingest.mode: preview 
  brxm.ai.ingest.types: myproject:bannerdocument, hippogallery:exampleAssetSet  
  brxm.ai.ingest.interval: '120'
  brxm.ai.ingest.batch-size: '5' 
  brxm.ai.ingest.delay: '1000'
  brxm.ai.ingest.initial-delay: '300'