Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add Chat Settings to Generic Langchain Provider #622

Merged
merged 8 commits into from
Jan 3, 2024
Merged

Add Chat Settings to Generic Langchain Provider #622

Changes from 6 commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
c8a9465
Add Chat Settings to Generic Langchain Provider
tylertitsworth Jan 1, 2024
cbd797c
Update langchain.py
tylertitsworth Jan 1, 2024
cadb0cb
Set default inputs to empty list
tylertitsworth Jan 2, 2024
199ec21
Do not require settings for stream event
tylertitsworth Jan 2, 2024
64590cf
use chainlit 1.0.0 attrs
tylertitsworth Jan 2, 2024
512835a
remove unecessary whitespace
tylertitsworth Jan 2, 2024
bf18ab9
Update langchain.py
tylertitsworth Jan 3, 2024
9b5dca2
Update backend/chainlit/playground/providers/langchain.py
tylertitsworth Jan 3, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 9 additions & 3 deletions backend/chainlit/playground/providers/langchain.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
from typing import Union
from typing import List, Union

from chainlit.input_widget import InputWidget
from chainlit.playground.provider import BaseProvider
from chainlit.sync import make_async
from chainlit_client import GenerationMessage
Expand All @@ -18,13 +19,14 @@ def __init__(
id: str,
name: str,
llm: Union[LLM, BaseChatModel],
inputs: List[InputWidget] = [],
is_chat: bool = False,
):
super().__init__(
id=id,
name=name,
env_vars={},
inputs=[],
inputs=inputs,
is_chat=is_chat,
)
self.llm = llm
Expand Down Expand Up @@ -65,7 +67,11 @@ async def create_completion(self, request):

messages = self.create_generation(request)

stream = make_async(self.llm.stream)
# /~https://github.com/langchain-ai/langchain/issues/14980
stream = make_async(self.llm.stream)(
input=messages,
**request.generation.settings
)

result = await stream(
input=messages,
Expand Down
Loading