Preston Rasmussen 0f50b74735

Set max tokens by prompt (#255) ...

* set max tokens

* update generic openai client

* mypy updates

* fix: dockerfile

---------

Co-authored-by: paulpaliychuk <pavlo.paliychuk.ca@gmail.com>

2025-01-24 10:14:49 -05:00

..

__init__.py

Fix llm client retry (#102)

2024-09-10 08:15:27 -07:00

anthropic_client.py

Set max tokens by prompt (#255)

2025-01-24 10:14:49 -05:00

client.py

Set max tokens by prompt (#255)

2025-01-24 10:14:49 -05:00

config.py

Set max tokens by prompt (#255)

2025-01-24 10:14:49 -05:00

errors.py

Implement OpenAI Structured Output (#225)

2024-12-05 07:03:18 -08:00

groq_client.py

Set max tokens by prompt (#255)

2025-01-24 10:14:49 -05:00

openai_client.py

Set max tokens by prompt (#255)

2025-01-24 10:14:49 -05:00

openai_generic_client.py

Set max tokens by prompt (#255)

2025-01-24 10:14:49 -05:00

utils.py

update new names with input_data (#204)

2024-10-29 11:03:31 -04:00