langchain/libs/partners/together
ccurme 1925bde32e
together: bump langchain-core (#22616)
langchain-together depends on langchain-openai ^0.1.8
langchain-openai 0.1.8 has langchain-core >= 0.2.2

Here we bump langchain-core to 0.2.2, just to pass minimum dependency
version tests.
2024-06-06 14:09:40 +00:00
..
langchain_together core, standard tests, partner packages: add test for model params (#21677) 2024-05-17 13:51:26 -04:00
scripts together: add chat models, use openai base (#21337) 2024-05-06 17:47:06 -07:00
tests infra: rm unused # noqa violations (#22049) 2024-05-22 15:21:08 -07:00
.gitignore together: package and embedding model (#14936) 2023-12-19 18:48:32 -08:00
LICENSE together: add chat models, use openai base (#21337) 2024-05-06 17:47:06 -07:00
Makefile together: add chat models, use openai base (#21337) 2024-05-06 17:47:06 -07:00
poetry.lock together: bump langchain-core (#22616) 2024-06-06 14:09:40 +00:00
pyproject.toml together: bump langchain-core (#22616) 2024-06-06 14:09:40 +00:00
README.md together: add chat models, use openai base (#21337) 2024-05-06 17:47:06 -07:00

langchain-together

This package contains the LangChain integrations for Together AI through their APIs.

Installation and Setup

  • Install the LangChain partner package
pip install -U langchain-together
  • Get your Together AI api key from the Together Dashboard and set it as an environment variable (TOGETHER_API_KEY)

Chat Completions

This package contains the ChatTogether class, which is the recommended way to interface with Together AI chat models.

ADD USAGE EXAMPLE HERE. Can we add this in the langchain docs?

NEED to add image endpoint + completions endpoint as well

Embeddings

See a usage example

Use togethercomputer/m2-bert-80M-8k-retrieval as the default model for embeddings.