MinimalLLM
pip install MinimalLLM
Minimal and handy interfaces of LLMs based on LiteLLM.
Features:
- Minimal and intuitive interfaces. You don't need to learn
- Handy cache system for faster testing
- Support for multiple LLMs by LiteLLM
Usage
Chat
from mllm import Chat
chat = Chat()
chat += "Give me a random number from 1 to 10"
res = chat.complete(cache=True)
print(res)
chat = Chat()
chat += "Give a json dict with keys 'a' and 'b' and values 1 and 2"
res = chat.complete(parse="dict", cache=True)
print(res)
Embedding
from mllm import get_embeddings
embeddings = get_embeddings(["Hello, world!", "Goodbye, world!"])
print(embeddings)
# Embeddings are automatically cached
Visualized Log of chats
from mllm import Chat, display_chats
with display_chats():
chat = Chat()
chat += "Who is your developer?"
res = chat.complete(cache=True)
# A web page will be opened to show the chat log
Providers
MinimalLLM is based on LiteLLM, which supports multiple providers. You can switch the provider to use different LLMs.
Switch provider
from mllm.provider_switch import set_default_to_anthropic
set_default_to_anthropic()
To setup the API keys for the providers, we recommend to use the following streamlit app (run pip install streamlit first):
from mllm.setup import run_setup_app
run_setup_app()
Why minimal?
Minimal means stable. We only provide the most basic interfaces and features.
1 maintainer
Release files for MinimalLLM 1.2.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| minimalllm-1.2.2.tar.gz | 107.9 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| minimalllm-1.2.2-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 136.4 kB
Release files / minimalllm-1.2.2.tar.gz
| Download URL | minimalllm-1.2.2.tar.gz |
|---|---|
| Size | 107.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
db4e98eb6e0e5f3f39469a2df8a9dc1183287b0f55f3d36b4bd986d1aa3cd047
|
|
BLAKE2b-256 checksum How to use checksums |
7ab826cd134944bc7a20672be7631b031a18ebfd07dd52ca074a2ba551e7a54d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.1.1 CPython/3.10.16
|
Release files / minimalllm-1.2.2-py3-none-any.whl
| Download URL | minimalllm-1.2.2-py3-none-any.whl |
|---|---|
| Size | 28.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
960238434dd96232510f818eeeb1e813a3a7d08549774b340e7aeafb99224aa8
|
|
BLAKE2b-256 checksum How to use checksums |
309579b15fb881f5a2d05679a6541287ed3f35af87dc6eae8f792b2a5b9f4e86
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.1.1 CPython/3.10.16
|
