983301bb6c
Fixed bug if LLM directory does not exist, closes #193
2023-08-31 20:31:51 -07:00
dff36f0edc
Change of policy: keys.json over-rides environment variables, closes #158
2023-08-20 23:27:21 -07:00
e959026051
llm keys command, closes #174
2023-08-20 23:11:47 -07:00
85e18389b5
Removed rogue pdb.set_trace() I left in
...
Mistake made in 0eeb8393ca
2023-08-20 23:04:52 -07:00
c8e9565f47
Combine piped and argument prompts, closes #153
2023-08-20 22:57:29 -07:00
091984cca2
Refactor to use llm.set_alias() / remove_alias(), closes #154
2023-08-19 22:11:19 -07:00
c290b44d45
llm.remove_alias() function, refs #154
2023-08-19 22:06:51 -07:00
8cdcf1e689
llm.set_alias() function, refs #154
2023-08-19 22:01:29 -07:00
0cd9333054
llm aliases defaults to llm aliases list, refs #154
...
Refs #167
2023-08-19 21:48:20 -07:00
adb900be1a
Restore extra=forbid for Template, refs #169
2023-08-19 21:42:32 -07:00
5bf0f4165f
Removed incomplete model_config feature, refs #169
2023-08-19 21:38:09 -07:00
a105d98b58
Ignore mypy error, refs #169
2023-08-19 21:35:35 -07:00
36f8ffc2a1
Test for llm models --options, refs #169
2023-08-19 21:26:23 -07:00
0537622f40
Fix llm models --options in pydantic 1, refs #169
2023-08-19 21:21:03 -07:00
14a91efbad
Fixes for Pydantic 1, including matrix test - refs #169
...
Also refs #147
2023-08-19 20:59:30 -07:00
740a8e8344
Allow for use of Pydantic v1 as well as v2. ( #147 )
...
* Allow for use of Pydantic v1 as well as v2.
Use v1-style configuration. While this is officially
deprecated (https://docs.pydantic.dev/latest/usage/model_config/ ),
it is supported by v2. I would assume this support will remain
for a while, this will help ease the transition to v2
2023-08-19 20:50:59 -07:00
0eeb8393ca
llm models and llm templates default to list, closes #167
2023-08-19 20:04:14 -07:00
9518515de0
Extra header configuration for openrouter.ai, refs #165
2023-08-19 18:53:49 -07:00
c4dbb62e68
Fix for broken migrations on sqlite-utils 3.35, refs #162
2023-08-19 13:09:41 -07:00
d31d97e06f
Refactor get_key() with docs and better varible names
...
The actual logic is unchanged, but it is a lot easier to understand what it does now.
Refs #158
2023-08-17 15:03:55 -07:00
a4f55e9987
--cid/--conversation option, docs for search - refs #160
2023-08-17 14:32:43 -07:00
a2eab1b0f7
Fixed test failure, refs #160
2023-08-17 14:17:39 -07:00
79d09936cb
Lose the indentation for log output, refs #160
2023-08-17 14:12:57 -07:00
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
6a578c35cf
mypy fix for new aliases code, refs #151
2023-08-12 09:17:29 -07:00
458a59a8f4
Actually register aliases from aliases.json, closes #151
2023-08-12 09:15:17 -07:00
53289e3767
llm aliases remove command, refs #151
2023-08-12 09:05:02 -07:00
4a68aa408a
llm aliases path command, refs #151
2023-08-12 09:01:51 -07:00
8fc9cd1902
llm aliasess set command, refs #151
2023-08-12 09:01:12 -07:00
b8f8869778
llm aliases list --json option, refs #151
2023-08-12 08:52:57 -07:00
4980f5a7c0
llm aliases list command, refs #151
2023-08-11 22:57:30 -07:00
609e8dead8
--no-cache-dir and --force-reinstall options, closes #146
2023-08-03 21:30:47 -07:00
838484b1f3
Set min/max constraints to float arguments
...
* Add .idea/ to .gitignore
* Set min and max constraints to float parameters
Closes #115
2023-07-26 10:59:09 -07:00
531d188199
Fix: Prevent TypeError in llm templates list for templates with empty prompts ( #132 )
2023-07-26 10:46:58 -07:00
65d16663f5
Fix bug in --editable, closes #136
2023-07-25 22:21:20 -07:00
cb41409e2b
conversation_name should not have newlines, closes #110
2023-07-15 21:28:35 -07:00
178af27d95
llm logs list -q/--query option, closes #109
2023-07-15 16:20:28 -07:00
75e40e7077
Enable FTS indexes on responses prompt and response columns, refs #109
2023-07-15 16:03:35 -07:00
ed8cd776a4
llm logs list -m model_id/alias option, closes #108
2023-07-15 15:55:13 -07:00
e2072f7044
Ability to register additional OpenAI-compatible models
...
Closes #107 , closes #106
2023-07-15 10:01:03 -07:00
58d1f9291d
Don't use openai.api_key global, refs #107
2023-07-14 14:07:42 -07:00
54881ebfd5
Remove init-db command, refs #68
2023-07-11 21:38:14 -07:00
fa67b3fdaf
--log option, closes #68
2023-07-11 20:18:16 -07:00
d2fcff3f3a
llm logs on / off commands, refs #98
2023-07-11 19:48:16 -07:00
875c6a9669
Initial llm logs status command, refs #98
2023-07-11 19:38:27 -07:00
7bef414de7
Nicer error message for unknown models with -c mode, closes #92
2023-07-11 19:29:54 -07:00
19ba1a3099
Improvements to Response.fake() plus __repr__ for some classes
2023-07-11 15:14:52 -07:00
abfc9c69dc
Response.fake() method
...
I'm using this in https://github.com/simonw/llm-gpt4all/issues/4
2023-07-11 11:08:15 -07:00
18a89d8bb8
Removed obsolete OptionsError class
2023-07-11 10:53:04 -07:00
c7271dd6b4
llm.ModelError class, refs #96
2023-07-11 10:52:48 -07:00
Simon Willison