Skip to main content
Add these nodes with the pipeline builder: pipeline.add(name="...").<node>(...). Each entry lists the node’s configuration parameters. See the Pipeline reference for add, run, and lifecycle methods.

​
append_files

Append files together in successive fashion 
pipeline.add(name="node").append_files()
Parameters
​
file_type
str
default:"'PDF'"
One of: PDF, PPTX
​
selected_files
AcceptsFileList
default:"[]"

​
file

Load a static file into the workflow as a raw File or process it into Text.
Platform docs: Load a static file into the workflow as a raw File or process it into Text.
pipeline.add(name="node").file(file_name="...", file=...)
Parameters
​
selected_option
str
default:"'upload'"
Select an existing file from the VectorShift platform One of: name, upload
​
file_name
str
required
The name of the file from the VectorShift platform (for files on the File tab)
​
file_parser
str
default:"'default'"
The processing model with which the document will be processed. Default processing model includes standard document parsing / OCR. Llamaparse will allow for ability to read documents with complex features (e.g., tables, charts, etc.). Llamaparse will be charged at 0.3 cents per page. Textract for most advanced data extraction and will be charged at 1.5 cents per page. One of: contextual_ai, default, docling, llama_parse, mistral_ocr, reducto, textract
​
file
AcceptsFile
required
The file that was passed in

​
file_operations

Process and manipulate files 
pipeline.add(name="node").file_operations()
Parameters
​
sub_type
str
default:"''"

​
file_save

Save a file on the VectorShift platform (under the ‘Files’ tab).
Platform docs: Save a file on the VectorShift platform (under the ‘Files’ tab).
pipeline.add(name="node").file_save(files=..., name="...")
Parameters
​
files
AcceptsFileList
required
​
name
str
required

​
file_to_text

Convert data from type File to type Text 
pipeline.add(name="node").file_to_text(file=...)
Parameters
​
chunk_text
bool
default:"False"
Whether to chunk the text into smaller pieces.
​
decrypt
bool
default:"False"
Use a password to decrypt the file.
​
file
AcceptsFile
required
The file to convert to text.
​
file_parser
str
default:"'default'"
The type of file parser to use. One of: contextual_ai, default, docling, llama_parse, mistral_ocr, reducto, textract
​
password
str
default:"''"
The password to decrypt the file.
​
chunk_overlap
int
default:"400"
The overlap of each chunk of text.
​
chunk_size
int
default:"1024"
The size of each chunk of text.

​
get_run_data

Fetch run metrics (trace, latency, cost, tokens, status) for a session
Platform docs: Fetch run metrics (trace, latency, cost, tokens, status) for a session
pipeline.add(name="node").get_run_data(session_id="...")
Parameters
​
session_id
str
required

​
input

Pass data of different types into your workflow
Platform docs: Pass data of different types into your workflow
pipeline.add(name="node").input()
Parameters
​
input_type
str
default:"'string'"
Raw Text
​
use_default_value
bool
default:"False"
Set default value to be used if no value is provided
​
description
str
default:"''"
The input description. If pipeline is used as a tool in an agent, the description will be passed to the agent to help the agent know how to fill this input.
​
default_value
AcceptsAgent | AcceptsAudio | AcceptsDataframe | AcceptsFile | AcceptsFileList | AcceptsImage | AcceptsKnowledgeBase | AcceptsPipeline | AcceptsTable | AcceptsTimestamp | ListType | bool | float | int | list[AcceptsFileList] | list[list[str]] | list[str] | str
default:"{}"
The default value to be used if no value is provided
​
dataframe_type
str
default:"'table'"
The type of dataframe to be used One of: csv, dataframe_file, json, md, sql, table
​
file_parser
str
default:"'default'"
The processing model with which the document will be processed. Default processing model includes standard document parsing / OCR. Llamaparse will allow for ability to read documents with complex features (e.g., tables, charts, etc.). Llamaparse will be charged at 0.3 cents per page. Textract for most advanced data extraction and will be charged at 1.5 cents per page. Reducto enables rich structured parsing. One of: contextual_ai, default, docling, llama_parse, mistral_ocr, reducto, textract

​
output

Output data of different types from your workflow.
Platform docs: Output data of different types from your workflow.
pipeline.add(name="node").output(value=...)
Parameters
​
output_type
str
default:"'string'"
​
description
str
default:"''"
The output description. If pipeline is used as a tool in an agent, the description will be passed to the agent to help the agent know how to fill this output.
​
format_output
bool
default:"True"
​
value
AcceptsAudio | AcceptsDataframe | AcceptsFile | AcceptsFileList | AcceptsImage | AcceptsStream | AcceptsTimestamp | bool | float | int | str
required
​
dataframe_type
str
default:"'table'"
The type of dataframe to be used One of: csv, dataframe_file, json, md, sql, table

​
rename_file

Rename an existing file, assigning a new name along with the file extension. 
pipeline.add(name="node").rename_file(file=..., new_name="...")
Parameters
​
file
AcceptsFile
required
​
new_name
str
required

​
text

Accepts Text from upstream nodes and allows you to write additional text / concatenate different texts to pass to downstream nodes. 
pipeline.add(name="node").text(text="...")
Parameters
​
text
str
required

​
text_to_file

Convert data from type Text to type File. 
pipeline.add(name="node").text_to_file(text="...", file_name="...")
Parameters
​
text
str
required
​
file_name
str
required
​
file_type
str
default:"'PDF'"
One of: DOCX, PDF, TXT