Metadata-Version: 2.1
Name: thinkcol_llm_client
Version: 0.1.2
Summary: Package for calling llm clients asynchronously
Author: jedric01
Author-email: jedric@connect.ust.hk
Requires-Python: >=3.11,<4.0
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Requires-Dist: boto3 (>=1.34.68,<2.0.0)
Requires-Dist: openai (>=1.14.2,<2.0.0)
Requires-Dist: python-dotenv (>=1.0.1,<2.0.0)
Description-Content-Type: text/markdown

# LLM Client 
Internal package for making multi-threaded calls to LLMs.

# Supported Models
Cohere Command, Cohere Embed, OpenAI Models, Titan Embed, Mixtral

## Install
```
pip install thinkcol_llm_client
```

## Usage: 
### Normal Usage
```
from thinkcol_llm_client import OpenAIClient, AnthropicClient

texts = ["Hello", "Text 1", "ThinkCol"]

client = OpenAIClient()
client.embed(texts)

questions = ["How do I implement best practices in data science projects" for _ in range(500)]
client.invoke(questions)

anthropic_client = AnthropicClient()
anthropic_client.invoke(questions)
```


