mirror of
https://github.com/Hopiu/llm.git
synced 2026-04-05 22:10:59 +00:00
121 lines
2.7 KiB
Markdown
121 lines
2.7 KiB
Markdown
(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:
|
|
|
|
```bash
|
|
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:
|
|
```bash
|
|
llm 'Ten names for cheesecakes' -n
|
|
```
|
|
|
|
To turn logging by default off:
|
|
|
|
```bash
|
|
llm logs off
|
|
```
|
|
If you've turned off logging you can still log an individual prompt and response by adding `--log`:
|
|
```bash
|
|
llm 'Five ambitious names for a pet pterodactyl' --log
|
|
```
|
|
To turn logging by default back on again:
|
|
|
|
```bash
|
|
llm logs on
|
|
```
|
|
To see the status of the logs database, run this:
|
|
```bash
|
|
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:
|
|
```bash
|
|
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:
|
|
```bash
|
|
llm logs -n 10
|
|
```
|
|
Or `-n 0` to see everything that has ever been logged:
|
|
```bash
|
|
llm logs -n 0
|
|
```
|
|
You can truncate the display of the prompts and responses using the `-t/--truncate` option:
|
|
```bash
|
|
llm logs -n 5 -t
|
|
```
|
|
This is useful for finding a conversation that you would like to continue.
|
|
|
|
You can also use [Datasette](https://datasette.io/) to browse your logs like this:
|
|
|
|
```bash
|
|
datasette "$(llm logs path)"
|
|
```
|
|
## SQL schema
|
|
|
|
Here's the SQL schema used by the `logs.db` database:
|
|
|
|
<!-- [[[cog
|
|
import cog
|
|
from llm.migrations import migrate
|
|
import sqlite_utils
|
|
import re
|
|
db = sqlite_utils.Database(memory=True)
|
|
migrate(db)
|
|
|
|
def cleanup_sql(sql):
|
|
first_line = sql.split('(')[0]
|
|
inner = re.search(r'\((.*)\)', sql, re.DOTALL).group(1)
|
|
columns = [l.strip() for l in inner.split(',')]
|
|
return first_line + '(\n ' + ',\n '.join(columns) + '\n);'
|
|
|
|
cog.out("```sql\n")
|
|
for table in ("conversations", "responses"):
|
|
schema = db[table].schema
|
|
cog.out(format(cleanup_sql(schema)))
|
|
cog.out("\n")
|
|
cog.out("```\n")
|
|
]]] -->
|
|
```sql
|
|
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
|
|
);
|
|
```
|
|
<!-- [[[end]]] -->
|