Simple interface for creating and managing LLM chains
Project description
LLM Blocks
LLM Blocks is a Python library that provides a simple interface for creating and managing Language Model (LLM) chains. It is designed to make it easy to interact with OpenAI's GPT-3 API.
📚 Table of Contents
🎯 Why Use LLM Blocks
LLM Blocks makes it easy to create and manage LLM chains. It provides a simple, intuitive interface for interacting with OpenAI's GPT-3 API. With LLM Blocks, you can focus on building your application without worrying about the intricacies of the API.
🏗️ Repo Structure
llm_blocks
├── .gitignore
├── llm_blocks
│ ├── __init__.py
│ └── blocks.py
├── requirements.txt
├── setup.py
└── turbo_docs.toml
📦 Installation
To install LLM Blocks, you can use pip:
pip install llm-blocks
🚀 Usage
LLM Blocks provides three main classes: Block
, TemplateBlock
, and ChatBlock
. These classes are the recommended interfaces for calling OpenAI APIs.
Here is an example of how to use them:
from llm_blocks import Block, TemplateBlock, ChatBlock
template = "Hello, {name}! How are you?"
# Create a Block
block = Block()
response = block("Hello, world!")
# Create a TemplateBlock
template_block = TemplateBlock(template)
response = template_block("AI Friend")
# template_block(name="AI Friend") also valid
# Create a ChatBlock
chat_block = ChatBlock(template)
response = chat_block("AI Friend")
response = chat_block("What is the meaning of life?")
🤝 Contributing
Contributions are welcome! Please feel free to submit a pull request.
📧 Contact
If you have any questions or feedback, please feel free to contact the author at voynow99@gmail.com.
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
File details
Details for the file llm-blocks-0.3.3.tar.gz
.
File metadata
- Download URL: llm-blocks-0.3.3.tar.gz
- Upload date:
- Size: 3.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.10.1
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | d1d4b110a26cdf3a7c4f504333ac410a0d5823d8efa6dc5940dd3cf74b6ae3f0 |
|
MD5 | b6faf0bd41a09db68318c59775d2f4e4 |
|
BLAKE2b-256 | 90c92b1fd4fbb4868865da031f30be6979c54e31b5ef0cbafd68125fa73953c6 |
File details
Details for the file llm_blocks-0.3.3-py3-none-any.whl
.
File metadata
- Download URL: llm_blocks-0.3.3-py3-none-any.whl
- Upload date:
- Size: 5.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.10.1
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 5a9eba1f5ecff37969f92311d222f5d86c45e0aa29b356e4577f36dd94b38a04 |
|
MD5 | 5d8e1720f16cf7e82c29b919b4b10abf |
|
BLAKE2b-256 | a1d0a71865d77243d1171296e17a02a1e0a2a5a74d9d2a95d8a1ba4e52248401 |