Skip to main content

An integration package connecting Together and LangChain

Project description

langchain-together

This package contains the LangChain integration for Together's generative models.

Installation

pip install -U langchain-together

Embeddings

You can use Together's embedding models through TogetherEmbeddings class.

from langchain_together import TogetherEmbeddings

embeddings = TogetherEmbeddings(
    model='togethercomputer/m2-bert-80M-8k-retrieval'
)
embeddings.embed_query("What is a large language model?")

LLMs

You can use Together's generative AI models as Langchain LLMs:

from langchain_together import Together
from langchain_core.prompts import PromptTemplate

llm = Together(
    model="togethercomputer/RedPajama-INCITE-7B-Base",
    temperature=0.7,
    max_tokens=64,
    top_k=1,
    # together_api_key="..."
)

template = """Question: {question}
Answer: """
prompt = PromptTemplate.from_template(template)

chain = prompt | llm

question = "Who was the president in the year Justin Beiber was born?"
print(chain.invoke({"question": question}))

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

langchain_together-0.0.2.post2.tar.gz (5.8 kB view details)

Uploaded Source

Built Distribution

File details

Details for the file langchain_together-0.0.2.post2.tar.gz.

File metadata

File hashes

Hashes for langchain_together-0.0.2.post2.tar.gz
Algorithm Hash digest
SHA256 a6926b52b5b303f504870064f3f22e0ab3e75e3663e55ca18c0c8761bb516037
MD5 d60b470767047b7a95ad688a8fe4c3d9
BLAKE2b-256 5dc062d25d673511fcfead20874b2ec98baa458b0c435504839eb5b3254c12dc

See more details on using hashes here.

File details

Details for the file langchain_together-0.0.2.post2-py3-none-any.whl.

File metadata

File hashes

Hashes for langchain_together-0.0.2.post2-py3-none-any.whl
Algorithm Hash digest
SHA256 b5a6e336792813f080e4bc675bf71f9ec1be5ce5435cd33733af2fb4f8f53427
MD5 217acab6cdea53ca03e95baf88b8f9d1
BLAKE2b-256 25bc871cb66a964bea5ef17bba8ebbb3854b58d323f0c0ee97fb92133abfed0e

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page