ehs-llm-client 0.1.1

Unified LLM client. Currently supports Openai, Azure Openai and Google Gemini

llm-client

llm-client is a unified async Python client for interacting with multiple LLM providers, including OpenAI, Azure OpenAI, and Google Gemini.
It supports single calls, structured JSON outputs, and batch processing, designed for production-ready, reusable code in applications, scripts, or pipelines.

---

Features

• Async support for multiple LLM providers
• Unified interface across OpenAI, Azure, and Google Gemini
• Structured JSON responses via schemas
• Retry and timeout handling
• Batch processing support
• Environment variable configuration for API keys
• Easy integration into existing projects or monorepos

---

Installation

# Install from PyPI
pip install llm-client

Or install editable version during development:

# From project root
pip install -e .

---

Configuration

llm-client supports three configuration modes:

1️⃣ Config file (.cfg)

Example: llmconfig.cfg

[default_settings]
provider = openai
model = gpt-4.1-mini

[prod]
provider = openai
model = gpt-4.1
model_batch = gpt-4.1-mini

Usage:

from llm_client import LLM

llm = LLM("prod", config_file_path="llmconfig.cfg")

---

2️⃣ Config dictionary (for tests / CI)

from llm_client import LLM

llm = LLM(
    "default",
    config={
        "default_settings": {
            "provider": "openai",
            "model": "gpt-4.1-mini"
        }
    }
)

---

3️⃣ Environment variable fallback

export LLM_PROVIDER=openai
export LLM_MODEL=gpt-4.1-mini
export OPENAI_API_KEY=sk-...

llm = LLM("default")

---

Usage

Single async call

import asyncio
from llm_client import LLM

async def main():
    llm = LLM("prod")
    messages = [{"role": "user", "content": "Say hello in JSON"}]

    response, in_tokens, out_tokens = await llm.get_response_async(
        messages, schema="return json"
    )

    print(response)

asyncio.run(main())

---

Batch request

batch_line = llm.create_batch_request(
    custom_id="test1",
    messages=[{"role": "user", "content": "Give me a JSON object"}],
    schema="return json"
)

batch_id = await llm.run_batch_process([batch_line], submission_id="batch123")
status = await llm.get_batch_status(batch_id)
print(status)

---

API Key Management

Keep API keys out of code. Recommended environment variables:

Provider	Env var name
OpenAI	OPENAI_API_KEY
Azure OpenAI	AZURE_OPENAI_API_KEY
Google Gemini	GOOGLE_API_KEY

---

Development

# Create a virtual environment
python -m venv .venv
source .venv/bin/activate  # macOS/Linux
.venv\Scripts\activate     # Windows

# Install dependencies
pip install -e .

---

License

MIT License © 2026 Your Name