A tiny language interpreter
Project description
🦜🔗🔍 Tinylang
Make working with LLMs insanely simpler and easier than ever before.
What is tinylang?
A hackable and simpler Langchain.
Langchain can be very cumbersome and annoying to work with. It's too big, complicated, and shoves pre-made prompts down your throat.
With tinylang, everything is intuitive and customizable, following most of the Langchain API.
Installation
pip install tinylang
Usage
from tinylang.chains import Chain
from tinylang.llms import OpenAI
from tinylang.memory import ConversationMemory
model = "gpt-3.5-turbo"
chatGPT = OpenAI(
openai_api_key=openai_api_key,
openai_organization=openai_organization,
model=model,
)
memory = ConversationMemory()
chain = Chain(
llm=chatGPT,
memory=memory,
)
prompt = "Hello"
print(chain.run(prompt))
Features
- 🧠 Conversation Memory. Keep all or some aspects of your conversation
- 🛸 OpenAI LLMs. It couldn't be easier to call the OpenAI API.
- 💻 Prompts. Simple and hackable.
- 🤖 Agents. Coming soon!
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
tinylang-2.0.1.tar.gz
(9.9 kB
view hashes)
Built Distribution
tinylang-2.0.1-py3-none-any.whl
(12.3 kB
view hashes)