Library for creating LLM-based agents with tools and RAG
Project description
Fyodorov LLM Agents
fyodorov_llm_agents is a Python library that provides tooling for creating LLM-based agents using arbitrary API
providers (such as OpenAI). You can optionally provide those agents with tools (via ChatGPT style plugins) and
search to perform Retrieval Augmented Generation (RAG).
This library is used in the FyodorovAI suite to create agents and provide them with tools and access to a search database.
# Importing the library
from fyodorov_llm_agents import create_agent, OpenAIProvider, Tool, DostoyevskyRAG
agent = create_agent(
llm=OpenAIProvider(api_key="###"),
tools = [
Tool("https://example.com/.well-known/tool-name.json"),
],
rag=[
DostoyevskyRAG(endpoint="https://dostoyevsky.example.com"),
],
)
Installation
You can install fyodorov_llm_agents using pip:
pip install fyodorov-llm-agents==0.0.1
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file fyodorov_llm_agents-0.0.5.tar.gz.
File metadata
- Download URL: fyodorov_llm_agents-0.0.5.tar.gz
- Upload date:
- Size: 5.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.11.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
ed42f9c7ad2cfa782c9e5b072a0058410fbb8b7e306696d0977389cb6067039a
|
|
| MD5 |
86f1847d69e3e0a738899244d7573c9e
|
|
| BLAKE2b-256 |
faad4e906b6ba107717f0f1cedcbd6f95f4be1e7668d8ff2eabc7a0e72260867
|
File details
Details for the file fyodorov_llm_agents-0.0.5-py3-none-any.whl.
File metadata
- Download URL: fyodorov_llm_agents-0.0.5-py3-none-any.whl
- Upload date:
- Size: 5.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.11.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
b43e888ef55d65e6b74ab17dffd8d8f5b53405f9260a1f2d4d8600201f874689
|
|
| MD5 |
8699007bd2a66e7a2e62cc2294fd9659
|
|
| BLAKE2b-256 |
cbfb286862f1e6d563cfb3ea31ed059666ebb5937e25a29bf8929a7b073c24f1
|