v5.2.0

• Minor bug fixes
• Docker image updates and move of prebuilt images to Splunk's dockerhub repository
• New AI capabilities (currently for Docker only)
  -- Standalone LLM: using LLM for zero-shot Q&A or natural language processing tasks
  -- Standalone VectorDB: using VectorDB to encode data from Splunk and conduct similarity search
  -- Document-based LLM-RAG: encoding documents such as internal knowledge bases or past support tickets into VectorDB and using them as contextual information for LLM generation
  -- Function-Calling-based LLM-RAG: defining function tools in the Jupyter notebook for the LLM to execute automatically in order to obtain contextual information for generation

v5.1.2

Current state of DSDL v5.1.2 compatible container images. Including library updates and bug fixes in examples and notebooks.

Release notes from the DSDL app:

• Bug fixes in several Juypter notebooks
• Update and rebuilt of all containers
• Consolidation of examples
• Deprecation of examples and notebooks:
  -- Automated Machine Learning
  -- Linear Regressor
  -- Deep Neural Network Regressor
  -- Causal Inference
  -- Online Learning Anomaly Detection
  -- Named Entity Recognition and Extraction for Japanese