dartmouth-langchain 0.2.7

LangChain components for Dartmouth-hosted models.

Dartmouth LangChain

LangChain components for Dartmouth-hosted models.

⚠️⚠️⚠️⚠️ Deprecation Notice ⚠️⚠️⚠️⚠️

The dartmouth_langchain package has been renamed to langchain_dartmouth, to conform with the existing third-party packages in the LangChain ecosystem. Versions higher than 0.2.7 will only be released under the new name.

Getting started

1. Install the package:

pip install dartmouth-langchain

2. Obtain a Dartmouth API key from developer.dartmouth.edu
3. Store the API key as an environment variable called DARTMOUTH_API_KEY:

export DARTMOUTH_API_KEY=<your_key_here>

What is this?

This library provides an integration of Darmouth-hosted generative AI resources with the LangChain framework.

There are three main components currently implemened:

• Large Language Models
• Embedding models
• Reranking models

All of these components are based on corresponding LangChain base classes and can be used seamlessly wherever the corresponding LangChain objects can be used.

Using the library

Large Language Models

There are two kinds of Large Language Models (LLMs) hosted by Dartmouth:

• Base models without instruction tuning (require no special prompt format)
• Instruction-tuned models (also known as Chat models) requiring specific prompt formats

Using a Dartmouth-hosted base language model:

from dartmouth_langchain.llms import DartmouthLLM

llm = DartmouthLLM(model_name="codellama-13b-hf")

response = llm.invoke("Write a Python script to swap two variables.")
print(response)

Using a Dartmouth-hosted chat model:

from dartmouth_langchain.llms import ChatDartmouth


llm = ChatDartmouth(model_name="llama-3-8b-instruct")

response = llm.invoke("Hi there!")

print(response.content)

Note: The required prompt format is enforced automatically when you are using ChatDartmouth.

Embeddings model

Using a Dartmouth-hosted embeddings model:

from dartmouth_langchain import DartmouthEmbeddingsModel


embeddings = DartmouthEmbeddingsModel()

embeddings.embed_query("Hello? Is there anybody in there?")

Reranking

Using a Dartmouth-hosted reranking model:

from dartmouth_langchain.retrievers.document_compressors import DartmouthReranker
from langchain.docstore.document import Document


docs = [
    Document(page_content="Deep Learning is not..."),
    Document(page_content="Deep learning is..."),
    ]

query = "What is Deep Learning?"
reranker = DartmouthReranker(model_name="bge-reranker-v2-m3")
ranked_docs = reranker.compress_documents(query=query, documents=docs)

print(ranked_docs)

Available models

For a list of available models, check the documentation of the RESTful Dartmouth AI API.

License

Created by Simon Stone for Dartmouth College Libraries under Creative Commons CC BY-NC 4.0 License. For questions, comments, or improvements, email Research Data Services.

Except where otherwise noted, the example programs are made available under the OSI-approved MIT license.