Skip to content

refactor: use semantic kernel instead of langchain #877

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

Merged
merged 5 commits into from
May 13, 2024
Merged

refactor: use semantic kernel instead of langchain #877

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
eb8c679
starting a branch for this pairing task
gaurarpit May 13, 2024
38f6612
removing TODOs
gaurarpit May 13, 2024
0991787
Merge branch 'main' into arpit/feature/semantic-kernel-instead-of-lan…
gaurarpit May 13, 2024
9b5a9b1
Merge branch 'main' into arpit/feature/semantic-kernel-instead-of-lan…
gaurarpit May 13, 2024
4f16864
update semantic_kernel in the allowed list.
gaurarpit May 13, 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
2 changes: 0 additions & 2 deletions code/backend/batch/utilities/plugins/ChatPlugin.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,6 @@ def search_documents(
str, "A standalone question, converted from the chat history"
],
) -> Answer:
# TODO: Use Semantic Kernel to call LLM
return QuestionAnswerTool().answer_question(
question=question, chat_history=self.chat_history
)
Expand All @@ -37,7 +36,6 @@ def text_processing(
"The operation to be performed on the text. Like Translate to Italian, Summarize, Paraphrase, etc. If a language is specified, return that as part of the operation. Preserve the operation name in the user language.",
],
) -> Answer:
# TODO: Use Semantic Kernel to call LLM
return TextProcessingTool().answer_question(
question=self.question,
chat_history=self.chat_history,
Expand Down
1 change: 0 additions & 1 deletion code/backend/batch/utilities/plugins/PostAnsweringPlugin.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,5 +8,4 @@
class PostAnsweringPlugin:
@kernel_function(description="Run post answering prompt to validate the answer.")
def validate_answer(self, arguments: KernelArguments) -> Answer:
# TODO: Use Semantic Kernel to call LLM
return PostPromptTool().validate_answer(arguments["answer"])
2 changes: 1 addition & 1 deletion infra/main.bicep
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -119,7 +119,7 @@ param azureOpenAIVisionModelVersion string = 'vision-preview'
@description('Azure OpenAI Vision Model Capacity - See here for more info https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/quota')
param azureOpenAIVisionModelCapacity int = 10

@description('Orchestration strategy: openai_function or langchain str. If you use a old version of turbo (0301), plese select langchain')
@description('Orchestration strategy: openai_function or langchain str. If you use a old version of turbo (0301), please select langchain')
@allowed([
'openai_function'
'langchain'
Expand Down
Loading