Supporting asyncio in langchain primitives allows for users to run them
concurrently and creates more seamless integration with
asyncio-supported frameworks (FastAPI, etc.)
Summary of changes:
**LLM**
* Add `agenerate` and `_agenerate`
* Implement in OpenAI by leveraging `client.Completions.acreate`
**Chain**
* Add `arun`, `acall`, `_acall`
* Implement them in `LLMChain` and `LLMMathChain` for now
**Agent**
* Refactor and leverage async chain and llm methods
* Add ability for `Tools` to contain async coroutine
* Implement async SerpaPI `arun`
Create demo notebook.
Open questions:
* Should all the async stuff go in separate classes? I've seen both
patterns (keeping the same class and having async and sync methods vs.
having class separation)
https://github.com/hwchase17/langchain/issues/354
Add support for running your own HF pipeline locally. This would allow
you to get a lot more dynamic with what HF features and models you
support since you wouldn't be beholden to what is hosted in HF hub. You
could also do stuff with HF Optimum to quantize your models and stuff to
get pretty fast inference even running on a laptop.
lots of kwargs! generation docs here:
https://docs.nlpcloud.com/#generation
This somewhat breaks the paradigm introduced in LLM base class as the
stop sequence isn't a list, and should rightfully be introduced at the
time of initialization of the class, along with the other kwargs that
depend on its presence (e.g. remove_end_sequence, etc.) curious if you'd
want to refactor LLM base class to take out stop as a specific named
kwarg?
Add support for huggingface hub
I could not find a good way to enforce stop tokens over the huggingface
hub api - that needs to hopefully be cleaned up in the future
