Crate avocado_core 

AvocadoDB Core Engine

The deterministic context compiler that fixes RAG.

AvocadoDB replaces traditional vector databases’ chaotic “top-k” retrieval with deterministic, citation-backed context generation using span-based compilation.

Key Features

• 100% Deterministic: Same query → same context, every time
• Citation-Backed: Every piece of context has exact line number citations
• Token Efficient: 95%+ token budget utilization (vs 60-70% in RAG)
• Fast: < 500ms for 8K token context

Architecture

Query → Embed → [Semantic Search + Lexical Search] → Hybrid Fusion
      → MMR Diversification → Token Packing → Deterministic Sort → WorkingSet

Re-exports

pub use types::Artifact;

pub use types::Citation;

pub use types::CompilerConfig;

pub use types::Error;

pub use types::Result;

pub use types::ScoredSpan;

pub use types::Span;

pub use types::WorkingSet;

pub use types::Session;

pub use types::Message;

pub use types::MessageRole;

pub use types::SessionWorkingSet;

pub use session::SessionManager;

pub use session::SessionReplay;

pub use session::SessionTurn;

Modules

approx

compiler

Context compilation engine

db

Database operations using SQLite

embedding

Embedding generation with local and OpenAI support

index

In-memory vector index for similarity search

session

High-level session management API

span

Span extraction from documents

types

Core data types for AvocadoDB

Constants

VERSION

The version of AvocadoDB