NebulaAIFlow处理组件

处理组件在流程中处理和转换数据。

在流程中使用处理组件

在这个流程中，拆分文本处理组件将传入的数据拆分成块，以嵌入到向量存储组件中。

该组件提供对块大小、重叠度和分隔符的控制，这些参数会影响向量存储检索结果的上下文和粒度。

Combine text

This component concatenates two text sources into a single text chunk using a specified delimiter.

Inputs

Name	Display Name	Info
first_text	First Text	The first text input to concatenate.
second_text	Second Text	The second text input to concatenate.
delimiter	Delimiter	A string used to separate the two text inputs. Defaults to a space.

Outputs

Name	Display Name	Info
message	Message	A Message object containing the combined text.

Data combiner

This component combines multiple data sources into a single unified Data object.

The component iterates through the input list of data objects, merging them into a single data object. If the input list is empty, it returns an empty data object. If there's only one input data object, it returns that object unchanged. The merging process uses the addition operator to combine data objects.

Inputs

Name	Display Name	Info
data	Data	A list of data objects to be merged.

Outputs

Name	Display Name	Info
merged_data	Merged Data	A single Data object containing the combined information from all input data objects.

DataFrame operations

This component performs the following operations on Pandas DataFrame:

Operation	Description	Required Inputs
Add Column	Adds a new column with a constant value	new_column_name, new_column_value
Drop Column	Removes a specified column	column_name
Filter	Filters rows based on column value	column_name, filter_value
Head	Returns first n rows	num_rows
Rename Column	Renames an existing column	column_name, new_column_name
Replace Value	Replaces values in a column	column_name, replace_value, replacement_value
Select Columns	Selects specific columns	columns_to_select
Sort	Sorts DataFrame by column	column_name, ascending
Tail	Returns last n rows	num_rows

Inputs

Name	Display Name	Info
df	DataFrame	The input DataFrame to operate on.
operation	Operation	Select the DataFrame operation to perform. Options: Add Column, Drop Column, Filter, Head, Rename Column, Replace Value, Select Columns, Sort, Tail
column_name	Column Name	The column name to use for the operation.
filter_value	Filter Value	The value to filter rows by.
ascending	Sort Ascending	Whether to sort in ascending order.
new_column_name	New Column Name	The new column name when renaming or adding a column.
new_column_value	New Column Value	The value to populate the new column with.
columns_to_select	Columns to Select	List of column names to select.
num_rows	Number of Rows	Number of rows to return (for head/tail). Default: 5
replace_value	Value to Replace	The value to replace in the column.
replacement_value	Replacement Value	The value to replace with.

Outputs

Name	Display Name	Info
output	DataFrame	The resulting DataFrame after the operation.

Filter data

This component filters a Data object based on a list of keys.

Inputs

Name	Display Name	Info
data	Data	Data object to filter.
filter_criteria	Filter Criteria	List of keys to filter by.

Outputs

Name	Display Name	Info
filtered_data	Filtered Data	A new Data object containing only the key-value pairs that match the filter criteria.

Filter values

The Filter values component filters a list of data items based on a specified key, filter value, and comparison operator.

Inputs

Name	Display Name	Info
input_data	Input data	The list of data items to filter.
filter_key	Filter Key	The key to filter on, for example, 'route'.
filter_value	Filter Value	The value to filter by, for example, 'CMIP'.
operator	Comparison Operator	The operator to apply for comparing the values.

Outputs

Name	Display Name	Info
filtered_data	Filtered data	The resulting list of filtered data items.

Lambda filter

This component uses an LLM to generate a Lambda function for filtering or transforming structured data.

To use the Lambda filter component, you must connect it to a Language Model component, which the component uses to generate a function based on the natural language instructions in the Instructions field.

This example gets JSON data from the https://jsonplaceholder.typicode.com/users API endpoint. The Instructions field in the Lambda filter component specifies the task extract emails. The connected LLM creates a filter based on the instructions, and successfully extracts a list of email addresses from the JSON data.

Inputs

Name	Display Name	Info
data	Data	The structured data to filter or transform using a Lambda function.
llm	Language Model	The connection port for a Model component.
filter_instruction	Instructions	Natural language instructions for how to filter or transform the data using a Lambda function, such as Filter the data to only include items where the 'status' is 'active'.
sample_size	Sample Size	For large datasets, the number of characters to sample from the dataset head and tail.
max_size	Max Size	The number of characters for the data to be considered "large", which triggers sampling by the sample_size value.

Outputs

Name	Display Name	Info
filtered_data	Filtered Data	The filtered or transformed Data object.
dataframe	DataFrame	The filtered data as a DataFrame.

LLM router

This component routes requests to the most appropriate LLM based on OpenRouter model specifications.

Inputs

Name	Display Name	Info
models	Language Models	List of LLMs to route between
input_value	Input	The input message to be routed
judge_llm	Judge LLM	LLM that will evaluate and select the most appropriate model
optimization	Optimization	Optimization preference (quality/speed/cost/balanced)

Outputs

Name	Display Name	Info
output	Output	The response from the selected model
selected_model	Selected Model	Name of the chosen model

Message to data

This component converts Message objects to Data objects.

Inputs

Name	Display Name	Info
message	Message	The Message object to convert to a Data object.

Outputs

Name	Display Name	Info
data	Data	The converted Data object.

Parser

This component formats DataFrame or Data objects into text using templates, with an option to convert inputs directly to strings using stringify.

To use this component, create variables for values in the template the same way you would in a Prompt component. For DataFrames, use column names, for example Name: {Name}. For Data objects, use {text}.

Inputs

Name	Display Name	Info
stringify	Stringify	Enable to convert input to a string instead of using a template.
template	Template	Template for formatting using variables in curly brackets. For DataFrames, use column names (e.g. Name: {Name}). For Data objects, use {text}.
input_data	Data or DataFrame	The input to parse - accepts either a DataFrame or Data object.
sep	Separator	String used to separate rows/items. Default: newline.
clean_data	Clean Data	When stringify is enabled, cleans data by removing empty rows and lines.

Outputs

Name	Display Name	Info
parsed_text	Parsed Text	The resulting formatted text as a Message object.

Split text

This component splits text into chunks based on specified criteria.

Inputs

Name	Display Name	Info
data_inputs	Input Documents	The data to split.The component accepts Data or DataFrame objects.
chunk_overlap	Chunk Overlap	The number of characters to overlap between chunks. Default: 200.
chunk_size	Chunk Size	The maximum number of characters in each chunk. Default: 1000.
separator	Separator	The character to split on. Default: newline.
text_key	Text Key	The key to use for the text column (advanced). Default: text.

Outputs

Name	Display Name	Info
chunks	Chunks	List of split text chunks as Data objects.
dataframe	DataFrame	List of split text chunks as DataFrame objects.

Update data

This component dynamically updates or appends data with specified fields.

Inputs

Name	Display Name	Info
old_data	Data	The records to update
number_of_fields	Number of Fields	Number of fields to add (max 15)
text_key	Text Key	Key for text content
text_key_validator	Text Key Validator	Validates text key presence

Outputs

Name	Display Name	Info
data	Data	Updated Data objects.