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

[repo] fix: max_tokens bug fix in completions #1887

Merged
merged 3 commits into from
Aug 1, 2024
Merged

[repo] fix: max_tokens bug fix in completions #1887

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
876abb7
fix for python
lilyydu Jul 30, 2024
39c9aaa
dotnet fix
lilyydu Jul 30, 2024
4277d0b
Merge branch 'main' into lilyydu/max-tokens-bugfix
lilyydu Jul 31, 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: 1 addition & 1 deletion dotnet/packages/Microsoft.TeamsAI/Microsoft.TeamsAI/AI/Models/OpenAIModel.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -178,7 +178,7 @@ public async Task<PromptResponse> CompletePromptAsync(ITurnContext turnContext,
IEnumerable<OAIChat.ChatMessage> chatMessages = prompt.Output.Select(chatMessage => chatMessage.ToOpenAIChatMessage());

ChatCompletionOptions? chatCompletionOptions = ModelReaderWriter.Read<ChatCompletionOptions>(BinaryData.FromString($@"{{
""max_tokens"": {maxInputTokens},
""max_tokens"": {promptTemplate.Configuration.Completion.MaxTokens},
""temperature"": {(float)promptTemplate.Configuration.Completion.Temperature},
""top_p"": {(float)promptTemplate.Configuration.Completion.TopP},
""presence_penalty"": {(float)promptTemplate.Configuration.Completion.PresencePenalty},
Expand Down
8 changes: 4 additions & 4 deletions python/packages/ai/teams/ai/models/openai_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -123,7 +123,7 @@ async def complete_prompt(
tokenizer: Tokenizer,
template: PromptTemplate,
) -> PromptResponse[str]:
max_tokens = template.config.completion.max_input_tokens
max_input_tokens = template.config.completion.max_input_tokens
model = (
template.config.completion.model
if template.config.completion.model is not None
Expand All @@ -134,15 +134,15 @@ async def complete_prompt(
memory=memory,
functions=functions,
tokenizer=tokenizer,
max_tokens=max_tokens,
max_tokens=max_input_tokens,
)

if res.too_long:
return PromptResponse[str](
status="too_long",
error=f"""
the generated chat completion prompt had a length of {res.length} tokens
which exceeded the max_input_tokens of {max_tokens}
which exceeded the max_input_tokens of {max_input_tokens}
""",
)

Expand Down Expand Up @@ -194,7 +194,7 @@ async def complete_prompt(
frequency_penalty=template.config.completion.frequency_penalty,
top_p=template.config.completion.top_p,
temperature=template.config.completion.temperature,
max_tokens=max_tokens,
max_tokens=template.config.completion.max_tokens,
extra_body=extra_body,
)

Expand Down
7 changes: 4 additions & 3 deletions python/packages/ai/teams/app.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -610,7 +610,7 @@ async def __handler__(context: TurnContext, state: StateT):
return False

feedback = context.activity.value
feedback.reply_to_id=context.activity.reply_to_id
feedback.reply_to_id = context.activity.reply_to_id

await func(context, state, feedback)
await context.send_activity(
Expand Down Expand Up @@ -819,8 +819,9 @@ async def _run_ai_chain(self, context: TurnContext, state):
return True

def _contains_non_text_attachments(self, context):
non_text_attachments = filter(lambda a: not a.content_type.startswith(
"text/html"), context.activity.attachments)
non_text_attachments = filter(
lambda a: not a.content_type.startswith("text/html"), context.activity.attachments
)
return len(list(non_text_attachments)) > 0

async def _run_after_turn_middleware(self, context: TurnContext, state):
Expand Down
Loading