llm/docs/logging.md
2023-07-11 07:21:22 -07:00

2.4 KiB

Logging to SQLite

llm can log all prompts and responses to a SQLite database.

First, create a database in the correct location. You can do that using the llm init-db command:

llm init-db

This creates a database in a directory on your computer. You can find the location of that database using the llm logs path command:

llm logs path

On my Mac that outputs:

/Users/simon/Library/Application Support/io.datasette.llm/logs.db

This will differ for other operating systems.

Once that SQLite database has been created any prompts you run will be logged to that database.

To avoid logging a prompt, pass --no-log or -n to the command:

llm 'Ten names for cheesecakes' -n

Viewing the logs

You can view the logs using the llm logs command:

llm logs

This will output the three most recent logged items as a JSON array of objects.

Add -n 10 to see the ten most recent items:

llm logs -n 10

Or -n 0 to see everything that has ever been logged:

llm logs -n 0

You can truncate the display of the prompts and responses using the -t/--truncate option:

llm logs -n 5 -t

This is useful for finding a conversation that you would like to continue.

You can also use Datasette to browse your logs like this:

datasette "$(llm logs path)"

SQL schema

Here's the SQL schema used by the logs.db database:

CREATE TABLE [conversations] (
  [id] TEXT PRIMARY KEY,
  [name] TEXT,
  [model] TEXT
);
CREATE TABLE [responses] (
  [id] TEXT PRIMARY KEY,
  [model] TEXT,
  [prompt] TEXT,
  [system] TEXT,
  [prompt_json] TEXT,
  [options_json] TEXT,
  [response] TEXT,
  [response_json] TEXT,
  [conversation_id] TEXT REFERENCES [conversations]([id]),
  [duration_ms] INTEGER,
  [datetime_utc] TEXT
);