文件历史

提交图

144 次代码提交

作者 SHA1 备注 提交日期
Simon Willison 36f8ffc2a1 Test for llm models --options, refs #169 2023-08-19 21:26:23 -07:00
Simon Willison 0537622f40 Fix llm models --options in pydantic 1, refs #169 2023-08-19 21:21:03 -07:00
Simon Willison 14a91efbad Fixes for Pydantic 1, including matrix test - refs #169
Also refs #147
2023-08-19 20:59:30 -07:00
Simon Willison 0eeb8393ca llm models and llm templates default to list, closes #167 2023-08-19 20:04:14 -07:00
Simon Willison a4f55e9987 --cid/--conversation option, docs for search - refs #160 2023-08-17 14:32:43 -07:00
Simon Willison a2eab1b0f7 Fixed test failure, refs #160 2023-08-17 14:17:39 -07:00
Simon Willison 79d09936cb Lose the indentation for log output, refs #160 2023-08-17 14:12:57 -07:00
Simon Willison 113df5dd87 llm logs now defaults to text output, use --json for JSON, use -c X for specific conversation
Refs #160
2023-08-17 13:57:18 -07:00
Simon Willison 53289e3767 llm aliases remove command, refs #151 2023-08-12 09:05:02 -07:00
Simon Willison 4a68aa408a llm aliases path command, refs #151 2023-08-12 09:01:51 -07:00
Simon Willison 8fc9cd1902 llm aliasess set command, refs #151 2023-08-12 09:01:12 -07:00
Simon Willison b8f8869778 llm aliases list --json option, refs #151 2023-08-12 08:52:57 -07:00
Simon Willison 4980f5a7c0 llm aliases list command, refs #151 2023-08-11 22:57:30 -07:00
Simon Willison 609e8dead8 --no-cache-dir and --force-reinstall options, closes #146 2023-08-03 21:30:47 -07:00
Sherwin Daganato 531d188199 Fix: Prevent TypeError in llm templates list for templates with empty prompts (#132) 2023-07-26 10:46:58 -07:00
Simon Willison 65d16663f5 Fix bug in --editable, closes #136 2023-07-25 22:21:20 -07:00
Simon Willison 178af27d95 llm logs list -q/--query option, closes #109 2023-07-15 16:20:28 -07:00
Simon Willison ed8cd776a4 llm logs list -m model_id/alias option, closes #108 2023-07-15 15:55:13 -07:00
Simon Willison 54881ebfd5 Remove init-db command, refs #68 2023-07-11 21:38:14 -07:00
Simon Willison fa67b3fdaf --log option, closes #68 2023-07-11 20:18:16 -07:00
Simon Willison d2fcff3f3a llm logs on / off commands, refs #98 2023-07-11 19:48:16 -07:00
Simon Willison 875c6a9669 Initial llm logs status command, refs #98 2023-07-11 19:38:27 -07:00
Simon Willison 7bef414de7 Nicer error message for unknown models with -c mode, closes #92 2023-07-11 19:29:54 -07:00
Simon Willison 2d3ebe7fe1 llm logs now uses new DB schema, refs #91 2023-07-11 07:21:22 -07:00
Simon Willison 88d839fa85 Create conversations and responses tables and write to them, refs #91 2023-07-11 07:21:22 -07:00
Simon Willison 898418a518 Fix for cogapp on Python 3.8, refs #82 2023-07-10 14:12:20 -07:00
Simon Willison 8f7c3a9797 llm models list --options - closes #82 2023-07-10 13:40:27 -07:00
Simon Willison 6cdbc7a270 Show error for --continue mode, remove deleted code 2023-07-10 08:34:36 -07:00
Simon Willison a421aab7f0 Renamed template.execute() to template.evaluate() and added type hints 2023-07-10 08:27:28 -07:00
Simon Willison ae87f978bd Moved iter_prompt from Response to Model, moved a lot of other stuff
- Moved a whole bunch of things from llm/cli.py into llm/__init__.py
- Switched plugin listings to use importlib.metadata to avoid deprecation warning
- iter_prompt() is now a method on Model, not on Response
2023-07-10 07:45:11 -07:00
Simon Willison 3d5c9b2d3b Read prompt after validating options
This means that if you do this:

    llm -m markov -o length -1

You will see an error message rather than have the command hang
waiting for a prompt to be entered on stdin.
2023-07-06 19:57:04 -07:00
Simon Willison c08344f986 llm logs now decodes JSON for prompt_json etc 2023-07-05 18:31:38 -07:00
Simon Willison 6ef6b343a9 Improved how keys work, execute() now has default implementation 2023-07-05 18:25:57 -07:00
Simon Willison f193468f76 llm install -e/--editable option 2023-07-05 17:58:19 -07:00
Simon Willison 23886e04ae Better error message display
Refs https://github.com/pydantic/pydantic/issues/6441
2023-07-05 16:36:38 -07:00
Simon Willison 49e4d688c6 Removed .stream() method in favor of .prompt(stream=False) 2023-07-04 07:50:31 -07:00
Simon Willison 345ad0d2dc Implemented new logs database schema 2023-07-03 07:27:47 -07:00
Simon Willison 61dd8afc60 Drop the debug field from the logs, combine chunks from stream 2023-07-03 06:39:54 -07:00
Simon Willison 84b99f8baf -o/--option, implemented for OpenAI models - closes #63 2023-07-02 17:42:22 -07:00
Simon Willison 52add96ec1 Rough initial version of new logging, to log2 table 2023-07-02 16:35:36 -07:00
Simon Willison 4a9f7f4908 Lint using Ruff, refs #78 2023-07-02 12:41:40 -07:00
Simon Willison 9a180e65a8 llm models default command, plus refactored env variables
Closes #76
Closes #31
2023-07-01 14:01:29 -07:00
Simon Willison feff460496 Fix for pydantic warning, refs #74 2023-07-01 11:56:35 -07:00
Simon Willison 714b867e92 -s shortcut for --system, closes #69 2023-07-01 10:46:20 -07:00
Simon Willison c1938a4987 Fix for --key being beaten by env variable, closes #71 2023-07-01 10:33:49 -07:00
Simon Willison 52cedc03e0 CLI now uses new prompt/stream methods 2023-07-01 09:09:19 -07:00
Simon Willison 5e056fad8a Implemented PaLM 2, to test out new plugin hook - refs #20 2023-06-26 08:25:01 -07:00
Simon Willison 5103f77c40 New mechanism for handling API keys for models 2023-06-26 08:05:48 -07:00
Simon Willison 274126d9f8 WIP register_models() plugin hook, refs #53 2023-06-26 07:43:46 -07:00
Simon Willison 9f1085eece --save now stores -p as default parameters, closes #58 2023-06-23 07:51:50 -07:00