Skip to main content

Module llm

Module llm 

Source
Expand description

The external-LLM seam. Embeddings and structured method-extraction are the only steps that need a language model; everything else in the crate is deterministic. That model is reached over HTTP behind this trait, so it can be a local Ollama server today, a hosted API tomorrow, or the native QualiaDB engine later — without touching the rest of the pipeline. It is never compiled into QualiaDB’s core inference path.

Re-exports§

pub use ollama::OllamaBackend;

Modules§

ollama
Ollama HTTP backend — an external LLM reached over its REST API.

Traits§

LlmBackend
A swappable language-model backend.

Functions§

analyze_container
Analysis pass: ask the backend for topical tags from the document’s leading chunks and write them into the container manifest (drives reorganise/route).
embed_container
Enrichment pass: open a container, embed its chunks with backend, and write the embedding matrix + updated manifest back into the same container.