# `Rho.LLMCatalog`
[🔗](https://github.com/GenericJam/rho/blob/v0.1.0/lib/rho/llm_catalog.ex#L1)

Gives llm_db (the model catalog req_llm resolves models through) a
snapshot that works on a phone.

llm_db reads its packaged `priv/llm_db/snapshot.json` (10 MB, 230
providers) at runtime, but deps' priv/ isn't shipped to a mob device and
`Application.app_dir/2` doesn't resolve there. `compile_embed: true`
works but costs a 12.9 MB beam and a 2.4-20 s first lookup on a
1-scheduler phone BEAM. rho only talks to Anthropic, OpenAI (req_llm
resolves `openai_codex:` models through `openai`'s) and Google, so this
module trims the packaged snapshot to those providers at compile time
(its own snapshot_id, so llm_db's strict integrity check still holds),
and `install!/0` writes it to the data dir and points
`config :llm_db, :snapshot_path` at it before the first lookup
(`Rho.Supervisor` does this when it starts).

# `install!`

```elixir
@spec install!() :: :ok
```

Writes the trimmed snapshot to the data dir and points llm_db at it.
Call before the first model lookup; `Rho.Supervisor` does (its
`:llm_catalog` option), so only a host that looks models up before
starting it needs to.

# `providers`

```elixir
@spec providers() :: [String.t()]
```

The providers the trimmed snapshot keeps.

---

*Consult [api-reference.md](api-reference.md) for complete listing*