mirror of
https://github.com/hwchase17/langchain.git
synced 2025-10-21 17:25:34 +00:00
c5bf114c0f
Here we allow standard tests to specify a value for `tool_choice` via a `tool_choice_value` property, which defaults to None. Chat models [available in Together](https://docs.together.ai/docs/chat-models) have issues passing standard tool calling tests: - llama 3.1 models currently [appear to rely on user-side parsing](https://docs.together.ai/docs/llama-3-function-calling) in Together; - Mixtral-8x7B and Mistral-7B (currently tested) consistently do not call tools in some tests. Specifying tool_choice also lets us remove an existing `xfail` and use a smaller model in Groq tests.
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.