llm/docs/logging.md
2023-07-15 15:55:13 -07:00

2.9 KiB

(logging)=

Logging to SQLite

llm defaults to logging all prompts and responses to a SQLite database.

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.

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

llm 'Ten names for cheesecakes' -n

To turn logging by default off:

llm logs off

If you've turned off logging you can still log an individual prompt and response by adding --log:

llm 'Five ambitious names for a pet pterodactyl' --log

To turn logging by default back on again:

llm logs on

To see the status of the logs database, run this:

llm logs status

Example output:

Logging is ON for all prompts
Found log database at /Users/simon/Library/Application Support/io.datasette.llm/logs.db
Number of conversations logged: 33
Number of responses logged:     48
Database file size:             19.96MB

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 filter to logs just for a specific model (or model alias) using -m/--model:

llm logs -m chatgpt

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
);