Skip to main content

A unified interface for multiple LLM providers

Project description

multillm-core

A unified interface for multiple LLM providers (OpenAI, Anthropic, Gemini, Mistral).

Installation

pip install multillm-core

Install with specific providers:

pip install "multillm-core[openai]"
pip install "multillm-core[anthropic]"
pip install "multillm-core[gemini]"
pip install "multillm-core[mistral]"
pip install "multillm-core[all]"

Example Usage

Synchronous:

from multillm import create_client

client = create_client("openai", api_key="your-key")
response = client.generate(
    model="gpt-4o",
    prompt="Explain quantum entanglement in one sentence."
)
print(f"[{response.provider}] {response.text}")

Asynchronous:

import asyncio
from multillm import create_client

async def main():
    client = create_client("openai", api_key="your-key")
    response = await client.async_generate(
        model="gpt-4o",
        prompt="Explain quantum entanglement in one sentence."
    )
    print(f"[{response.provider}] {response.text}")

if __name__ == "__main__":
    asyncio.run(main())

Supported Providers

  • OpenAI
  • Anthropic
  • Google Gemini
  • Mistral (Pixtral for images)

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

multillm_core-0.2.0.tar.gz (103.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

multillm_core-0.2.0-py3-none-any.whl (11.8 kB view details)

Uploaded Python 3

File details

Details for the file multillm_core-0.2.0.tar.gz.

File metadata

  • Download URL: multillm_core-0.2.0.tar.gz
  • Upload date:
  • Size: 103.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.12

File hashes

Hashes for multillm_core-0.2.0.tar.gz
Algorithm Hash digest
SHA256 408148dcfb9b6fd21c1b5994b46ea704b057818e562600cdcdf972c2d7908b18
MD5 2b4a0806a68da0682e37604871403dcc
BLAKE2b-256 593a8fd1d37e4d4d7e609a9823173913caadcaeb358b1d536d4427c493c0291f

See more details on using hashes here.

File details

Details for the file multillm_core-0.2.0-py3-none-any.whl.

File metadata

  • Download URL: multillm_core-0.2.0-py3-none-any.whl
  • Upload date:
  • Size: 11.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.12

File hashes

Hashes for multillm_core-0.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 1fb9a73d5b819fe955d545254c5f41cc34e1ded4d3394a9b300651beab2b7c95
MD5 4124f2a789ef07b6f4c027af14036250
BLAKE2b-256 f6a80996f86001ee1b35f89ceface144e740780831d5aa9f2d3f9493083bda4f

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page