Blame: pyproject.toml - BerriAI/litellm

BerriAI / litellm UNCLAIMED

Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]

0 0 1 Python

Normal View History Raw

Expanded .env, added Poetry and basic Docstring 2023-08-02 12:05:35 +03:00			`[tool.poetry]`
			`name = "litellm"`
bump v 2023-09-26 11:57:09 -07:00			`version = "0.1.765"`
Expanded .env, added Poetry and basic Docstring 2023-08-02 12:05:35 +03:00			`description = "Library to easily interface with LLM API providers"`
			`authors = ["BerriAI"]`
			`license = "MIT License"`
			`readme = "README.md"`

			`[tool.poetry.dependencies]`
use build 2023-08-05 09:43:21 -07:00			`python = "^3.8"`
new lock + poetry 2023-09-15 09:47:28 -07:00			`openai = "^0.28.0 \|\| ^0.27.0"`
loosen python dotenv version requirements 2023-09-02 15:25:34 -07:00			`python-dotenv = ">=0.2.0"`
loosen depedencies 2023-09-25 07:33:23 -07:00			`tiktoken = ">=0.4.0"`
			`importlib-metadata = ">=6.8.0"`
remove tokenizers version requirement 2023-09-25 09:15:50 -07:00			`tokenizers = "*"`
Expanded .env, added Poetry and basic Docstring 2023-08-02 12:05:35 +03:00
			`[build-system]`
			`requires = ["poetry-core"]`
			`build-backend = "poetry.core.masonry.api"`