Langchain-Nexus is a Python library enabling easy integration with diverse language models like ChatGPT and GLM through a unified interface.
Project description
🦜️🔗langchain-nexus
Langchain-Nexus is a versatile Python library that provides a unified interface for interacting with various language models, allowing seamless integration and easy development with models like ChatGPT, GLM, and others.
Quick Install
With pip:
pip install langchain-nexus
🚀 How does LangChain-Nexus help?
📃LLM Model I/O
ChatOpenAI:
from langchain_core.messages import HumanMessage, SystemMessage
from langchain_nexus import ChatOpenAI
chat = ChatOpenAI(temperature=0, openai_api_key="YOUR_API_KEY")
messages = [
SystemMessage(
content="You are a helpful assistant that translates English to French."
),
HumanMessage(
content="Translate this sentence from English to French. I love programming."
),
]
chat.invoke(messages)
ChatZhipuAI:
from langchain_core.messages import HumanMessage, SystemMessage
from langchain_nexus import ChatZhipuAI
chat = ChatZhipuAI(temperature=0, zhipuai_api_key="YOUR_API_KEY")
messages = [
SystemMessage(
content="You are a helpful assistant that translates English to French."
),
HumanMessage(
content="Translate this sentence from English to French. I love programming."
),
]
chat.invoke(messages)
🧬 Embedding
OpenAIEmbeddings
from langchain_nexus import OpenAIEmbeddings
embeddings_model = OpenAIEmbeddings(openai_api_key="...")
# Embed list of texts
embeddings = embeddings_model.embed_documents(
[
"Hi there!",
"Oh, hello!",
"What's your name?",
"My friends call me World",
"Hello World!"
]
)
len(embeddings), len(embeddings[0])
# embed_query
embedded_query = embeddings_model.embed_query("What was the name mentioned in the conversation?")
embedded_query[:5]
ZhipuAIEmbeddings
from langchain_nexus import ZhipuAIEmbeddings
embeddings_model = ZhipuAIEmbeddings(zhipuai_api_key="...")
# Embed list of texts
embeddings = embeddings_model.embed_documents(
[
"Hi there!",
"Oh, hello!",
"What's your name?",
"My friends call me World",
"Hello World!"
]
)
len(embeddings), len(embeddings[0])
# embed_query
embedded_query = embeddings_model.embed_query("What was the name mentioned in the conversation?")
embedded_query[:5]
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
langchain_nexus-0.0.0.tar.gz
(15.3 kB
view details)
Built Distribution
File details
Details for the file langchain_nexus-0.0.0.tar.gz
.
File metadata
- Download URL: langchain_nexus-0.0.0.tar.gz
- Upload date:
- Size: 15.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.0.0 CPython/3.11.7
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 21b6ba79bd521fb418bdb977cd930355af8d68213719ec0f4bd2e668ec0963a6 |
|
MD5 | 58dcbe4a2d6f9a1bb48c66d1fe9993f1 |
|
BLAKE2b-256 | 743b34070ce99307feb13df34bd8cc8dedcabfd804a7a5fd35e34987455ebbe5 |
File details
Details for the file langchain_nexus-0.0.0-py3-none-any.whl
.
File metadata
- Download URL: langchain_nexus-0.0.0-py3-none-any.whl
- Upload date:
- Size: 23.3 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.0.0 CPython/3.11.7
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | b13a5d8572eef219e9d45f4e1035232336a45454afe114ea02c1c4d792b2ec8a |
|
MD5 | 0d6faa631afa5ccfc5e3c88158397e0e |
|
BLAKE2b-256 | 890eb5a2668c1a5a865952cdfde0a511e1aac76e80b898735b179c1348500061 |