SQL functions

AIDB functions are available as standalone SQL functions that you can call directly in queries for one-off transformations, testing and exploration, or to build custom workflows outside of the pipeline framework.

Each page here focuses on usage context and examples. For terse parameter tables and return types, see the API reference:

• Transformation functions (chunk_text , parse_html , parse_pdf , perform_ocr , summarize_text ) are in Functions reference

• Inference functions (encode_text , decode_text , rerank_text ) are in Reference → Models .

Page	Functions	What it covers
Text chunking	aidb.chunk_text()	Splitting text into segments for LLM context windows
Data parsing	aidb.parse_html(), aidb.parse_pdf()	Extracting readable text from HTML and PDF inputs
Performing OCR	aidb.perform_ocr()	Extracting text from images using an OCR-capable model
Summarization cookbook	aidb.summarize_text(), aidb.summarize_text_aggregate()	Generating and aggregating AI-powered text summaries, use cases, and cookbook
AI inference functions	aidb.encode_text(), aidb.decode_text(), and variants	Embedding text and images into vectors; generating completions
Text reranking	aidb.rerank_text()	Scoring and reordering candidate passages by relevance

!!!Note To use these operations as steps inside a pipeline, see Pipeline steps .

• Text chunking
  • Configuration options
    • Algorithm summary
• Data parsing
  • Parse HTML
  • Parse PDF
• Performing OCR
• Text summarization
  • aidb.summarize_text()
• Text summarization
• Text summarization
  • Summarization use cases
    • The problem
    • What AIDB does differently
    • Business value
    • Enterprise use cases
    • How it works
    • The wow moment
    • Example with chunking and custom prompt
    • Competitive position
  • Summarization cookbook
    • Recipes
    • Combining recipes: the full optimization stack
    • Performance benchmarks
    • Recommended configurations
    • Known limitations
    • Optimization patterns
• AI inference functions
  • aidb.encode_text()
  • aidb.encode_text_batch()
  • aidb.encode_image()
  • aidb.decode_text()
  • aidb.decode_text_batch()
  • aidb.inference_config()
• Text reranking
  • Using reranking after knowledge base retrieval