Modules
Fast, persistent_term-backed LLM model metadata catalog.
OTP Application for LLMDB.
Configuration reading and normalization for LLMDB.
Shim to call DeepMerge.deep_merge/3 with a 3-arity resolver without Dialyzer false positives.
Pure ETL pipeline for BUILD-TIME LLM model catalog generation.
Lightweight, deterministic enrichment of model data.
Wire protocol enrichment using Azure AI Foundry inference task metadata.
Deterministic runtime-contract enrichment for packaged provider and model data.
Auto-generated module containing all valid modality atoms.
Read-only runtime access to generated model history artifacts.
Backfills model history by diffing committed provider snapshots across git history.
Snapshot-store helpers for local history bundles.
One-time migration from Git-tracked metadata history into snapshot-store artifacts.
Rebuilds snapshot-based history artifacts from an ordered snapshot observation chain.
Handles loading and merging of packaged snapshots with runtime customization.
Precedence-aware merging with exclude handling for LLM model data.
Model struct with Zoi schema validation.
Complete normalization utilities for raw data into consistent formats.
Provides access to the packaged base snapshot.
Pricing pipeline for converting legacy cost data and applying provider defaults.
Provider struct with Zoi schema validation.
Query functions for selecting models based on capabilities and requirements.
Runtime configuration compilation for consumer applications.
Canonical snapshot artifact helpers.
Builds canonical snapshot artifacts from configured sources.
GitHub Releases-backed snapshot artifact store.
Unified data source interface for LLMDB.
Remote source for Anthropic models (https://api.anthropic.com/v1/models).
Remote source for Google Gemini models (https://generativelanguage.googleapis.com/v1beta/models).
Sidecar source for llmfit open-weight metadata.
Loads model metadata from local TOML files in a directory structure.
Remote source for models.dev metadata (https://models.dev/api.json).
Remote source for OpenAI models (https://api.openai.com/v1/models).
Remote source for OpenRouter metadata (https://openrouter.ai/api/v1/models).
Remote source for xAI (Grok) models (https://api.x.ai/v1/models).
Remote source for Zenmux models (https://zenmux.ai/api/v1/models).
Canonical "provider:model" spec parsing and resolution.
Manages persistent_term storage for LLM model snapshots with atomic swaps.
Validation functions for providers and models using Zoi schemas.
Mix Tasks
Builds a canonical snapshot.json from configured sources.
Backfills model history from committed provider snapshots.
Checks whether the local installed history bundle matches the published history metadata in the snapshot store.
Performs the one-time migration from legacy Git-tracked metadata commits into content-addressed snapshots plus snapshot-based history artifacts.
Rebuilds local history artifacts from the published snapshot observation chain,
then bundles the result and optionally republishes history.tar.gz plus
history-meta.json to an immutable history-<snapshot_id> release for the
latest snapshot in the chain.
Downloads the published history bundle from the snapshot store and extracts it into the local history directory.
Install and configure LLM DB for use in an application.
Lists all models from the LLMDB catalog with lifecycle status and aliases.
Pulls latest model metadata from all configured remote sources and caches locally.
Alias for mix llm_db.build.
Fetches a published snapshot from GitHub Releases.
Builds and publishes a canonical snapshot to GitHub Releases.
Updates the version in mix.exs to CalVer format (YYYY.M.PATCH).