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

fix(workflow): enhance prompt handling with vision support #9790

Merged
merged 2 commits into from
Oct 24, 2024
Merged

fix(workflow): enhance prompt handling with vision support #9790

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ed6f7e6
fix(workflow): enhance prompt handling with vision support
laipz8200 Oct 24, 2024
1f0198a
feat(node): add vision detail configuration support
laipz8200 Oct 24, 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
8 changes: 7 additions & 1 deletion api/core/workflow/nodes/llm/node.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -127,9 +127,10 @@ def _run(self) -> NodeRunResult | Generator[NodeEvent | InNodeEvent, None, None]
context=context,
memory=memory,
model_config=model_config,
vision_detail=self.node_data.vision.configs.detail,
prompt_template=self.node_data.prompt_template,
memory_config=self.node_data.memory,
vision_enabled=self.node_data.vision.enabled,
vision_detail=self.node_data.vision.configs.detail,
)

process_data = {
Expand Down Expand Up @@ -518,6 +519,7 @@ def _fetch_prompt_messages(
model_config: ModelConfigWithCredentialsEntity,
prompt_template: Sequence[LLMNodeChatModelMessage] | LLMNodeCompletionModelPromptTemplate,
memory_config: MemoryConfig | None = None,
vision_enabled: bool = False,
vision_detail: ImagePromptMessageContent.DETAIL,
) -> tuple[list[PromptMessage], Optional[list[str]]]:
inputs = inputs or {}
Expand All @@ -542,6 +544,10 @@ def _fetch_prompt_messages(
if not isinstance(prompt_message.content, str):
prompt_message_content = []
for content_item in prompt_message.content or []:
# Skip image if vision is disabled
if not vision_enabled and content_item.type == PromptMessageContentType.IMAGE:
continue

if isinstance(content_item, ImagePromptMessageContent):
# Override vision config if LLM node has vision config,
# cuz vision detail is related to the configuration from FileUpload feature.
Expand Down
1 change: 1 addition & 0 deletions api/core/workflow/nodes/question_classifier/question_classifier_node.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,6 +88,7 @@ def _run(self):
memory=memory,
model_config=model_config,
files=files,
vision_enabled=node_data.vision.enabled,
vision_detail=node_data.vision.configs.detail,
)

Expand Down