Commit graph

87 commits

Author SHA1 Message Date
Simon Willison
bd2180df7d
llm chat --tool and --functions (#1062)
* Tool support for llm chat, closes #1004
2025-05-20 21:30:27 -07:00
Simon Willison
f320de1b0c LLM_TOOLS_DEBUG env var, closes #1045 2025-05-17 22:38:15 -04:00
Simon Willison
a888efa271 Ran cog, refs #1037 2025-05-15 10:41:06 -04:00
Simon Willison
92b0c6b99c Basic tool usage docs using --functions
Refs #1022, #995, #1016
2025-05-13 17:19:30 -07:00
github-actions[bot]
89c99df39c Ran cog 2025-05-13 17:19:30 -07:00
github-actions[bot]
e8894b19f5 Ran cog 2025-05-13 17:19:30 -07:00
Simon Willison
8e68c5e2d9 o4-mini, closes #976 2025-05-04 16:04:28 -07:00
Kevin Burke
5d0a2bba59
llm/default_plugins: add o3 model (#945)
* llm/default_plugins: add o3 model

This is the newest model released by OpenAI and is available through
the API.

* Ran cog

---------

Co-authored-by: Simon Willison <swillison@gmail.com>
2025-05-04 16:01:55 -07:00
Abizer Lokhandwala
0b37123a38
Add GPT-4.1 model family to default OpenAI plugin (#965)
* openai: add gpt-4.1 models
* Refactor and run cog

---------

Co-authored-by: Simon Willison <swillison@gmail.com>
2025-05-04 10:27:12 -07:00
Benedikt Willi
7dcfa31143
Add '!edit' command to modify prompts in chat sessions using default editor (#969)
* Add '!edit' command to modify prompts in chat sessions
2025-05-04 10:19:48 -07:00
Simon Willison
e78e1fceb2 LLM_MODEL and LLM_EMBEDDING_MODEL environment vars, closes #932 2025-04-19 20:41:24 -07:00
Steve Morin
4894b13414
llm models --options now shows keys and environment variables
Closes #903
2025-04-08 20:15:56 -07:00
Simon Willison
f740a5cbbd
Fragments (#859)
* WIP fragments: schema plus reading but not yet writing, refs #617
* Unique index on fragments.alias, refs #617
* Fragments are now persisted, added basic CLI commands
* Fragment aliases work now, refs #617
* Improved help for -f/--fragment
* Support fragment hash as well
* Documentation for fragments
* Better non-JSON display of llm fragments list
* llm fragments -q search option
* _truncate_string is now truncate_string
* Use condense_json to avoid duplicate data in JSON in DB, refs #617
* Follow up to 3 redirects for fragments
* Python API docs for fragments= and system_fragments=
* Fragment aliases cannot contain a : - this is to ensure we can add custom fragment loaders later on, refs https://github.com/simonw/llm/pull/859#issuecomment-2761534692
* Use template fragments when running prompts
* llm fragments show command plus llm fragments group tests
* Tests for fragments family of commands
* Test for --save with fragments
* Add fragments tables to docs/logging.md
* Slightly better llm fragments --help
* Handle fragments in past conversations correctly
* Hint at llm prompt --help in llm --help, closes #868
* llm logs -f filter plus show fragments in llm logs --json
* Include prompt and system fragments in llm logs -s
* llm logs markdown fragment output and tests, refs #617
2025-04-05 17:22:37 -07:00
Simon Willison
22175414f0 Extra OpenAI docs including mention of PDFs, closes #834 2025-03-25 19:30:42 -07:00
Simon Willison
468b0551ee
llm models options commands for setting default model options
Closes #829
2025-03-22 18:28:45 -07:00
Simon Willison
3541415db4 llm prompt -q X -q Y option, closes #841 2025-03-21 15:17:16 -07:00
Simon Willison
c3a0bb7bb6 Ran cog, refs #834 2025-03-18 16:29:08 -07:00
Simon Willison
1d552aeacc llm models -m option, closes #825 2025-03-10 14:18:50 -07:00
Simon Willison
b829cd92e0 Show async in list of features, closes #806 2025-02-28 06:44:09 -08:00
Simon Willison
bf80b8a19b Schemas tutorial and cleaned up other schema docs, refs #788 2025-02-28 00:16:29 -08:00
Simon Willison
98cccd294a llm models list --schemas option, closes #797
Also fixed bug where features showed even without --options, refs #796
2025-02-27 15:50:28 -08:00
Simon Willison
4a7a1f19ed Show features (including streaming) in llm models --options, closes #796 2025-02-27 15:44:38 -08:00
Simon Willison
6bec92fd78 Assign gpt-4.5 default alias, refs #795 2025-02-27 14:51:09 -08:00
Simon Willison
133d3bb173 Ran cog, refs #795 2025-02-27 14:50:02 -08:00
Simon Willison
74baf33a56 Moved some docs into schemas.md, refs #788 2025-02-27 11:20:50 -08:00
Simon Willison
523fc4f1a3 Fixed typo 2025-02-27 07:48:10 -08:00
Simon Willison
edc9e2dd7e Basic docs for llm schema list, closes #781 2025-02-27 07:46:34 -08:00
Simon Willison
a0845874ec
Schema template --save --schema support
* Don't hang on stdin if llm -t template-with-schema
* Docs on using schemas with templates
* Schema in template YAML file example
* Test for --save with --schema

Refs #778
2025-02-27 07:19:15 -08:00
Simon Willison
f35ac31c21
llm logs --schema, --data, --data-array and --data-key options (#785)
* llm logs --schema option, refs #782
* --data and --data-array and --data-key options, refs #782
* Tests for llm logs --schema options, refs #785
* Also implemented --schema ID lookup, refs #780
* Using --data-key implies --data
* Docs for llm logs --schema and --data etc
2025-02-26 21:51:08 -08:00
Simon Willison
62c90dd472
llm prompt --schema X option and model.prompt(..., schema=) parameter (#777)
Refs #776

* Implemented new llm prompt --schema and model.prompt(schema=)
* Log schema to responses.schema_id and schemas table
* Include schema in llm logs Markdown output
* Test for schema=pydantic_model
* Initial --schema CLI documentation
* Python docs for schema=
* Advanced plugin docs on schemas
2025-02-26 16:58:28 -08:00
Simon Willison
8611d9203c Updated docs with new chatgpt-4o-latest model, refs #752 2025-02-15 17:46:07 -08:00
Simon Willison
747d92ea4f Docs for multiple -q option, closes #748 2025-02-13 16:01:02 -08:00
Simon Willison
eb0e1e761b o3-mini and reasoning_effort option, refs #728 2025-01-31 12:14:02 -08:00
Simon Willison
656d8fa3c4
--xl/--extract-last flag for prompt and log list commands (#718)
Closes #717
2025-01-24 10:52:46 -08:00
Amjith Ramanujam
e3c104b136
Show the default model when listing all available models. (#688) 2025-01-11 12:04:39 -08:00
Simon Willison
6baf1f7d83 o1
Closes #676
2025-01-10 15:57:06 -08:00
Simon Willison
b452effa09 llm models -q/--query option, closes #700 2025-01-09 11:37:33 -08:00
Simon Willison
67d4a99645 llm prompt -x/--extract option, closes #681 2024-12-19 06:40:05 -08:00
Simon Willison
6305b86026 gpt-4o-mini-audio-preview, closes #677 2024-12-17 20:28:57 -08:00
Simon Willison
8898584ba6 New OpenAI audio models, closes #677 2024-12-17 11:14:42 -08:00
Simon Willison
7520671176 audio/wav not audio/wave, refs #603 2024-11-12 21:43:07 -08:00
Travis Northcutt
c0cb1697bc
Update default model information (#622)
The default model is now 4o-mini; this change updates the usage page of the docs to reflect that
2024-11-12 19:06:16 -08:00
Simon Willison
245e025270 Ran cog, refs #612 2024-11-05 23:45:17 -08:00
Simon Willison
12df1a3b2a Show attachment types in llm models --options, closes #612 2024-11-05 22:49:26 -08:00
Simon Willison
41cb5c3387 Ran cog, refs #608 2024-11-05 21:13:36 -08:00
Simon Willison
ba1ccb3a4a Release 0.17a0
Refs #587, #590
2024-10-28 15:46:52 -07:00
Simon Willison
f0ed54abf1 Docs for CLI attachments, refs #587 2024-10-28 15:41:34 -07:00
Simon Willison
bfcfd2c91b
o1-preview and o1-mini, refs #570 (#573) 2024-09-12 16:08:04 -07:00
Simon Donohue
50454c1957
Update outdated reference to gpt-4-turbo (#525)
Looks like this alias was overlooked in 8171c9a. This commit makes it
match with the usage of gpt-4o in the associated example.
2024-07-18 12:10:40 -07:00
Simon Willison
2881576dd0 Re-ran cog, refs #536 2024-07-18 12:00:35 -07:00