feat: run flow component with tool mode option to run a flow as a tool #5518
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
format
sample component update
tests
solves issues with agents and session ids
update to FlowOrchetstor
github-actions
bot
added
enhancement
github-actions
bot
added
enhancement
dosubot
bot
added
size:XL
github-actions
bot
added
enhancement
dosubot
bot
added
size:L
github-actions
bot
added
enhancement
github-actions
bot
added
enhancement
…field_template for improved input validation
github-actions
bot
added
enhancement
github-actions
bot
added
enhancement
github-actions
bot
added
enhancement
github-actions
bot
added
enhancement
| outputs = [ | ||
| Output(display_name="Run Outputs", name="run_outputs", method="generate_results"), | ||
| ] | ||
| async def run_flow_with_tweaks(self) -> list[Data]: |
There was a problem hiding this comment.
I think we should have two or three outputs in this component. One for Data, one for DataFrame and possibly one for the first Message. What do you think?
There was a problem hiding this comment.
Data and Dataframe sure I could add that.
Can you clarify "" possibly one for the first Message""" Means?
There was a problem hiding this comment.
Also, I had assumed that there is only one output function in the tool mode of runflow.
Can I proceed in such a way that the in tool mode the output/method from the data output is utilised, we need not have multiple tools for each outputs right?
| for output in run_output.outputs: | ||
| if output: | ||
| data.extend(build_data_from_result_data(output)) | ||
| return Data(data=data[-1].data) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This pull request introduces several significant changes across multiple files to enhance the functionality and performance of the Langflow backend. The key changes include converting several synchronous methods to asynchronous, adding new imports, and restructuring the
RunFlowComponentclass.Asynchronous Method Updates:
run_and_validate_update_outputsmethod to asynchronous insrc/backend/base/langflow/api/v1/endpoints.py.to_toolkitmethod to asynchronous insrc/backend/base/langflow/base/agents/agent.py.run_and_validate_update_outputsand_append_tool_to_outputs_mapmethods to asynchronous insrc/backend/base/langflow/custom/custom_component/component.py. [1] [2]New Imports:
create_input_schema_from_dictanddotdictimports insrc/backend/base/langflow/base/tools/component_tool.py. [1] [2]RunFlowComponent Refactor:
RunFlowComponentclass and replaced it with a new implementation insrc/backend/base/langflow/components/logic/runflow.py. The new class inherits fromRunFlowBaseand includes methods to handle flow execution with tweaks and updating build configurations. [1] [2]Other Changes:
RunFlowComponentinsrc/backend/base/langflow/components/logic/__init__.py.run_flow_with_tweaksto handle running flows with specific tweaks inRunFlowBase.