Skip to main content

LLM Assistant Framework

LLM Assistant Framework is a flexible and powerful Python library for building AI assistants using various Large Language Models (LLMs). Inspired by OpenAI's Assistants API, this framework allows you to create, manage, and interact with AI assistants using different LLM providers.

Features

  • 🚀 Easy-to-use API for creating and managing AI assistants
  • 🔌 Flexible integration with multiple LLM providers
  • 💬 Thread-based conversation management
  • 🏃‍♂️ Asynchronous execution of assistant runs
  • 🛠️ Customizable and extensible architecture

Installation

You can install the LLM Assistant Framework using pip:

pip install llm-assistant-framework

Usage

from llm_assistant_framework import AssistantManager, ThreadManager, RunManager

# Initialize managers
assistant_manager = AssistantManager()
thread_manager = ThreadManager()
run_manager = RunManager(assistant_manager, thread_manager)

# Create an assistant with the custom LLM function
assistant = await assistant_manager.create_assistant(
    name="Sky Expert",
    instructions="You are an expert on atmospheric phenomena.",
    model="llama3",
    custom_llm_function=custom_llm_function,
    temperature=0.7,  # Additional parameter for the LLM
)
print(assistant)

# Create a thread
thread = await thread_manager.create_thread()
print(thread)

Contributing

We welcome contributions to the LLM Assistant Framework! If you have any ideas, suggestions, or bug reports, please open an issue or submit a pull request.

License

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

Metadata

Release files for llm-assistant-framework 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for llm-assistant-framework 0.1.0
File Size Uploaded Provenance Actions
llm-assistant-framework-0.1.0.tar.gz 3.9 kB Without provenance Details for llm-assistant-framework-0.1.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for llm-assistant-framework 0.1.0
File Interpreter ABI Platform Actions
llm_assistant_framework-0.1.0-py3-none-any.whl Python 3 none any Details for llm_assistant_framework-0.1.0-py3-none-any.whl

Total release size: 8.5 kB

Release files / llm-assistant-framework-0.1.0.tar.gz

Download URL llm-assistant-framework-0.1.0.tar.gz
Size 3.9 kB
Tags Source
SHA-256 checksum
How to use checksums
ee2d88e4a90a9790860f6b3654659948bcbd97da1a3fad562a13b74b47b45c65
BLAKE2b-256 checksum
How to use checksums
84f764894022370aa6bdc88f05b569bbfa7e96c2ee12e84f8cbcdb93f480dd0c
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/5.1.1 CPython/3.10.9

Release files / llm_assistant_framework-0.1.0-py3-none-any.whl

Download URL llm_assistant_framework-0.1.0-py3-none-any.whl
Size 4.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
56b7be9b3ce3cf8a494358afe9f11f87dff7cabb4be8e90ed23633bc79f97eea
BLAKE2b-256 checksum
How to use checksums
7fd534cb72007270ac4a969811d98e40337dcf293b91bcd256b24a89927a3920
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/5.1.1 CPython/3.10.9

Security for llm-assistant-framework 0.1.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page