389acdf52c
Track usage on OpenAI stream requests, closes #591
2024-10-28 17:40:40 -07:00
a68af9c8e6
Don't redact non-data URLs for OpenAI models
...
Refs #587
2024-10-28 15:41:34 -07:00
cd722f653b
Redact base64 data from _prompt_json, refs #587
2024-10-28 15:41:34 -07:00
dff5b456fd
Got llm --continue to work with images, refs #587
2024-10-28 15:41:34 -07:00
6df00f92ff
First working prototype of new attachments feature, refs #587
2024-10-28 15:41:34 -07:00
bfcfd2c91b
o1-preview and o1-mini, refs #570 ( #573 )
2024-09-12 16:08:04 -07:00
e867e13d1b
Use model_dump() instead of dict()
...
Closes #554
2024-08-18 17:39:09 -07:00
24cc042e59
Use self.get_key() in OpenAI Chat class, refs #552
2024-08-18 17:01:28 -07:00
963a5ba467
gpt-4o-mini with alias 4o-mini, refs #536
2024-07-18 11:53:00 -07:00
9a3236db61
gpt-4-turbo model ID, closes #493
Test / test (ubuntu-latest, ==1.10.2, 3.9) (push) Has been cancelled
Test / test (ubuntu-latest, >=2.0.0, 3.10) (push) Has been cancelled
Test / test (ubuntu-latest, >=2.0.0, 3.11) (push) Has been cancelled
Test / test (ubuntu-latest, >=2.0.0, 3.12) (push) Has been cancelled
Test / test (ubuntu-latest, >=2.0.0, 3.8) (push) Has been cancelled
Test / test (ubuntu-latest, >=2.0.0, 3.9) (push) Has been cancelled
Test / test (windows-latest, ==1.10.2, 3.10) (push) Has been cancelled
Test / test (windows-latest, ==1.10.2, 3.11) (push) Has been cancelled
Test / test (windows-latest, ==1.10.2, 3.12) (push) Has been cancelled
Test / test (windows-latest, ==1.10.2, 3.8) (push) Has been cancelled
Test / test (windows-latest, ==1.10.2, 3.9) (push) Has been cancelled
Test / test (windows-latest, >=2.0.0, 3.10) (push) Has been cancelled
Test / test (windows-latest, >=2.0.0, 3.11) (push) Has been cancelled
Test / test (windows-latest, >=2.0.0, 3.12) (push) Has been cancelled
Test / test (windows-latest, >=2.0.0, 3.8) (push) Has been cancelled
Test / test (windows-latest, >=2.0.0, 3.9) (push) Has been cancelled
Test / test (macos-latest, ==1.10.2, 3.10) (push) Has been cancelled
Test / test (macos-latest, ==1.10.2, 3.11) (push) Has been cancelled
Test / test (macos-latest, ==1.10.2, 3.12) (push) Has been cancelled
Test / test (macos-latest, ==1.10.2, 3.8) (push) Has been cancelled
Test / test (macos-latest, ==1.10.2, 3.9) (push) Has been cancelled
Test / test (macos-latest, >=2.0.0, 3.10) (push) Has been cancelled
Test / test (macos-latest, >=2.0.0, 3.11) (push) Has been cancelled
Test / test (macos-latest, >=2.0.0, 3.12) (push) Has been cancelled
Test / test (macos-latest, >=2.0.0, 3.8) (push) Has been cancelled
Test / test (macos-latest, >=2.0.0, 3.9) (push) Has been cancelled
Test / test (ubuntu-latest, ==1.10.2, 3.10) (push) Has been cancelled
Test / test (ubuntu-latest, ==1.10.2, 3.11) (push) Has been cancelled
Test / test (ubuntu-latest, ==1.10.2, 3.12) (push) Has been cancelled
Test / test (ubuntu-latest, ==1.10.2, 3.8) (push) Has been cancelled
2024-05-13 13:37:23 -07:00
73bbbec372
gpt-4o model, refs #490
2024-05-13 12:49:45 -07:00
a06bef8f83
default_headers, not headers - fixes llm-openrouter, refs #401
2024-01-26 13:42:34 -08:00
0f8ffbfbbd
Fix compatibility with llm-anyscale-endpoints, refs #401
2024-01-26 13:35:03 -08:00
1f67f14cdb
Re-implemented LLM_OPENAI_SHOW_RESPONSES against httpx
...
Closes #404
Refs #364
2024-01-26 10:33:03 -08:00
214fcaaf86
Upgrade to run against OpenAI >= 1.0
...
* strategy: fail-fast: false - to help see all errors
* Apply latest Black
Refs #325
2024-01-25 22:00:44 -08:00
5bed6f13af
gpt-4-1106-preview, gpt-4-0125-preview, gpt-4-turbo-preview models - refs #396
2024-01-25 15:13:55 -08:00
a1b97c06e6
3-small-512, 3-large-256, 3-large-1024 embedding models, refs #394
2024-01-25 13:22:21 -08:00
044689351d
Support new OpenAI embeddings models, refs #394
2024-01-25 13:10:41 -08:00
184273876f
Fix for json_object tests I broke in #373
2024-01-25 13:04:05 -08:00
53f80dd531
-o json_object 1 option for OpenAI Chat models, refs #373
2024-01-25 12:51:14 -08:00
b2a12727f1
Add GPT 4 turbo model and -o seed 1 option ( #329 )
...
Closes #323
Closes #324
2023-11-06 13:32:04 -08:00
31b02ecfd6
Actually do the gpt-4-turbo work in a branch, refs #323
...
This reverts commit 2bfd039ff4
2023-11-06 10:17:36 -08:00
2bfd039ff4
Guessing model will be gpt-4-turbo - refs #323
...
This doesn't work yet though, they have not released the model.
2023-11-06 10:16:45 -08:00
b4ec54ef19
NotImplementedError for system prompts with OpenAI completion models, refs #284
...
Signed-off-by: Simon Willison <swillison@gmail.com >
2023-09-18 22:51:22 -07:00
f76b2120e4
Revert "Handle system prompts for completion models, refs #284 "
...
This reverts commit 4eed871cf1#288
2023-09-18 22:44:38 -07:00
4eed871cf1
Handle system prompts for completion models, refs #284
2023-09-18 22:36:38 -07:00
fcff36c6bc
completion: true to register completion models, refs #284
2023-09-18 22:17:26 -07:00
4fea46113f
logprobs support for OpenAI completion models, refs #284
2023-09-18 22:04:28 -07:00
ae14ce4add
LLM_OPENAI_SHOW_RESPONSES=1 debug trick, closes #286
2023-09-18 21:13:42 -07:00
4d18da4e11
Bump default gpt-3.5-turbo-instruct max tokens to 256, refs #284
2023-09-18 20:29:39 -07:00
4d46ebaa32
OpenAI completion models including gpt-3.5-turbo-instruct, refs #284
2023-09-18 18:34:32 -07:00
52cec1304b
Binary embeddings ( #254 )
...
* Binary embeddings support, refs #253
* Write binary content to content_blob, with tests - refs #253
* supports_text and supports_binary embedding validation, refs #253
2023-09-11 18:58:44 -07:00
e49c816e18
Drop llm.EmbeddingModel.embedding_size property, closes #208
2023-09-02 08:45:17 -07:00
7a4429f100
Fix mypy errors
...
Refs https://github.com/simonw/llm/issues/191#issuecomment-1703266224
2023-09-01 13:14:59 -07:00
817aff8bae
Embeddings now happen in batches, closes #200
2023-08-31 22:27:06 -07:00
77cf56e54a
Initial CLI support and plugin hook for embeddings, refs #185
...
* Embeddings plugin hook + OpenAI implementation
* llm.get_embedding_model(name) function
* llm embed command, for returning embeddings or saving them to SQLite
* Tests using an EmbedDemo embedding model
* llm embed-models list and emeb-models default commands
* llm embed-db path and llm embed-db collections commands
2023-08-27 22:24:10 -07:00
a105d98b58
Ignore mypy error, refs #169
2023-08-19 21:35:35 -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
9518515de0
Extra header configuration for openrouter.ai, refs #165
2023-08-19 18:53:49 -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
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
255f768707
Rename ._response_json to .response_json
2023-07-11 08:31:38 -07:00
b38b8314b9
Initial working implementation of conversations, refs #85
2023-07-10 22:37:45 -07:00
bb7813e0f5
Removed obsolete Model.Response class
2023-07-10 21:58:10 -07:00
aa37d3307f
Example for logit_bias, closes #36
2023-07-10 15:43:44 -07:00
bee1817284
Added a . for consistency
2023-07-10 15:32:07 -07:00
8f7c3a9797
llm models list --options - closes #82
2023-07-10 13:40:27 -07:00
199f7e0767
Renamed iter_prompt() to execute() and updated tutorial
2023-07-10 07:59:12 -07:00
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