PyLLMs

PyLLMs is a minimal Python library to connect to various Language Models (LLMs) with a built-in model performance benchmark.

Features
Installation
Quick Start
Usage
Configuration
Model Benchmarks
Supported Models
Advanced Usage
Contributing
License

Features

Connect to top LLMs in a few lines of code
Response meta includes tokens processed, cost, and latency standardized across models
Multi-model support: Get completions from different models simultaneously
LLM benchmark: Evaluate models on quality, speed, and cost
Async and streaming support for compatible models

Installation

Install the package using pip:

pip install pyllms

Quick Start

import llms

model = llms.init('gpt-4o')
result = model.complete("What is 5+5?")

print(result.text)

Usage

Basic Usage

import llms

model = llms.init('gpt-4o')
result = model.complete(
    "What is the capital of the country where Mozart was born?",
    temperature=0.1,
    max_tokens=200
)

print(result.text)
print(result.meta)

Multi-model Usage

models = llms.init(model=['gpt-3.5-turbo', 'claude-instant-v1'])
result = models.complete('What is the capital of the country where Mozart was born?')

print(result.text)
print(result.meta)

Async Support

result = await model.acomplete("What is the capital of the country where Mozart was born?")

Streaming Support

model = llms.init('claude-v1')
result = model.complete_stream("Write an essay on the Civil War")
for chunk in result.stream:
   if chunk is not None:
      print(chunk, end='')

Chat History and System Message

history = []
history.append({"role": "user", "content": user_input})
history.append({"role": "assistant", "content": result.text})

model.complete(prompt=prompt, history=history)

# For OpenAI chat models
model.complete(prompt=prompt, system_message=system, history=history)

Other Methods

count = model.count_tokens('The quick brown fox jumped over the lazy dog')

Configuration

PyLLMs will attempt to read API keys and the default model from environment variables. You can set them like this:

export OPENAI_API_KEY="your_api_key_here"
export ANTHROPIC_API_KEY="your_api_key_here"
export AI21_API_KEY="your_api_key_here"
export COHERE_API_KEY="your_api_key_here"
export ALEPHALPHA_API_KEY="your_api_key_here"
export HUGGINFACEHUB_API_KEY="your_api_key_here"
export GOOGLE_API_KEY="your_api_key_here"
export MISTRAL_API_KEY="your_api_key_here"
export REKA_API_KEY="your_api_key_here"
export TOGETHER_API_KEY="your_api_key_here"
export GROQ_API_KEY="your_api_key_here"
export DEEPSEEK_API_KEY="your_api_key_here"

export LLMS_DEFAULT_MODEL="gpt-3.5-turbo"

Alternatively, you can pass initialization values to the init() method:

model = llms.init(openai_api_key='your_api_key_here', model='gpt-4')

Model Benchmarks

PyLLMs includes an automated benchmark system. The quality of models is evaluated using a powerful model (e.g., GPT-4) on a range of predefined questions, or you can supply your own.

model = llms.init(model=['claude-3-haiku-20240307', 'gpt-4o-mini', 'claude-3-5-sonnet-20240620', 'gpt-4o', 'mistral-large-latest', 'open-mistral-nemo', 'gpt-4', 'gpt-3.5-turbo', 'deepseek-coder', 'deepseek-chat', 'llama-3.1-8b-instant', 'llama-3.1-70b-versatile'])

gpt4 = llms.init('gpt-4o')

models.benchmark(evaluator=gpt4)

Check Kagi LLM Benchmarking Project for the latest benchmarks!

To evaluate models on your own prompts:

models.benchmark(prompts=[("What is the capital of Finland?", "Helsinki")], evaluator=gpt4)

Supported Models

To get a full list of supported models:

model = llms.init()
model.list()
model.list("gpt")  # lists only models with 'gpt' in name/provider name

Currently supported models (may be outdated):

Provider	Models
HuggingfaceHubProvider	hf_pythia, hf_falcon40b, hf_falcon7b, hf_mptinstruct, hf_mptchat, hf_llava, hf_dolly, hf_vicuna
GroqProvider	llama-3.1-8b-instant, llama-3.1-405b-reasoning, llama-3.1-70b-versatile
DeepSeekProvider	deepseek-chat, deepseek-coder
MistralProvider	mistral-tiny, open-mistral-7b, open-mistral-nemo, mistral-small, open-mixtral-8x7b, mistral-small-latest, mistral-medium-latest, mistral-large-latest
OpenAIProvider	gpt-4o-mini, gpt-3.5-turbo, gpt-3.5-turbo-1106, gpt-3.5-turbo-instruct, gpt-4o, gpt-4-1106-preview, gpt-4-turbo-preview, gpt-4-turbo
GoogleProvider	gemini-1.5-pro-preview-0514, gemini-1.5-flash-preview-0514, chat-bison, text-bison, text-bison-32k, code-bison, code-bison-32k, codechat-bison, codechat-bison-32k, gemini-pro
GoogleGenAIProvider	chat-bison-genai, text-bison-genai, gemini-1.5-pro-latest
AnthropicProvider	claude-3-haiku-20240307, claude-instant-v1.1, claude-instant-v1, claude-instant-1, claude-instant-1.2, claude-3-sonnet-20240229, claude-3-5-sonnet-20240620, claude-2.1, claude-v1, claude-v1-100k, claude-3-opus-20240229
BedrockAnthropicProvider	anthropic.claude-3-haiku-20240307-v1:0, anthropic.claude-instant-v1, anthropic.claude-v1, anthropic.claude-v2, anthropic.claude-3-sonnet-20240229-v1:0
TogetherProvider	meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
RekaProvider	reka-edge, reka-flash, reka-core
AlephAlphaProvider	luminous-base, luminous-extended, luminous-supreme, luminous-supreme-control
AI21Provider	j2-grande-instruct, j2-jumbo-instruct, command, command-nightly
CohereProvider	command, command-nightly

Advanced Usage

Using OpenAI API on Azure

import llms
AZURE_API_BASE = "{insert here}"
AZURE_API_KEY = "{insert here}"

model = llms.init('gpt-4')

azure_args = {
    "engine": "gpt-4",  # Azure deployment_id
    "api_base": AZURE_API_BASE,
    "api_type": "azure",
    "api_version": "2023-05-15",
    "api_key": AZURE_API_KEY,
}

azure_result = model.complete("What is 5+5?", **azure_args)

Using Google Vertex LLM models

Set up a GCP account and create a project
Enable Vertex AI APIs in your GCP project
Install gcloud CLI tool
Set up Application Default Credentials

Then:

model = llms.init('chat-bison')
result = model.complete("Hello!")

Using Local Ollama LLM models

Ensure Ollama is running and you've pulled the desired model
Get the name of the LLM you want to use
Initialize PyLLMs:

model = llms.init("tinyllama:latest")
result = model.complete("Hello!")

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

This project is licensed under the MIT License. See the LICENSE file for details.

kagisearch/pyllms