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.

​
api — API

Make an API request to a given URL. 
pipeline.add(name="node").api(url="...")
Parameters
​
is_raw_json
bool
default:"False"
Whether to return the raw JSON response from the API
​
body_params
ListType | list[KeyValue] | list[List[Dict[str, Any]]]
default:"[]"
The body parameters to include in the API request
​
fail_non_2xx_response
bool
default:"False"
If enabled, the node fails when the API response status code is not in the 2xx range. Otherwise the response body is returned regardless of status code.
​
files
ListType | list[FileKeyValue] | list[List[Dict[str, Any]]]
default:"[]"
Files to include in the API request
​
headers
ListType | list[KeyValue] | list[List[Dict[str, Any]]]
default:"[]"
Headers to include in the API request
​
method
str
default:"'GET'"
Choose the API Method desired (GET, POST, PUT, DELETE, PATCH) One of: DELETE, GET, PATCH, POST, PUT
​
query_params
ListType | list[KeyValue] | list[List[Dict[str, Any]]]
default:"[]"
Query parameters to include in the API request
​
url
str
required
Target URL for the API Request
​
raw_json
str
default:"''"
The raw JSON request to the API

​
arxiv — Arxiv

Query ARXIV to return relevant articles 
pipeline.add(name="node").arxiv(query="...")
Parameters
​
chunk_text
bool
default:"False"
Whether to chunk the text
​
query
str
required
The ARXIV query
​
chunk_overlap
int
default:"0"
The overlap of the chunks
​
chunk_size
int
default:"512"
The size of the chunks to create

​
crunchbase — Crunchbase

Call the Crunchbase API to look up companies, people, funding rounds, and acquisitions. 
pipeline.add(name="node").crunchbase(endpoint="...")
Parameters
​
body
str
default:"''"
​
endpoint
str
required
​
query_params
str
default:"''"

​
csv_query — CSV Query

Utilizes an LLM agent to query CSV(s). Delimeter for the CSV must be commas. 
pipeline.add(name="node").csv_query(query="...", csv=...)
Parameters
​
query
str
required
​
csv
AcceptsFile
required
​
stream
bool
default:"False"

​
deep_research — Deep Research

Perform advanced AI research and analysis with specialized model capabilities
Platform docs: Deep Research
pipeline.add(name="node").deep_research(provider="anthropic", api_key="...")
Parameters
​
provider
str
required
Select the LLM provider for deep research
​
stream
bool
default:"False"
Whether to stream the research response
​
use_personal_api_key
bool
default:"False"
Whether to use a personal API key
​
model
str
default:"''"
Select the LLM model for deep research
​
api_key
str
required
Your personal API key for the research provider
​
conversation
str
default:"''"
Previous conversation context for research continuity
​
input
str
default:"''"
The data input for deep research analysis
​
instructions
str
default:"''"
Specific instructions for the deep research task
​
max_output_tokens
int
default:"128000"
Maximum number of tokens in the research output
​
max_tool_calls
int
default:"10"
Maximum number of tool calls during research
​
parallel_tool_calls
bool
default:"True"
Enable parallel tool execution for faster research
​
previous_response_id
str
default:"''"
ID of previous response for continuation
​
prompt_cache_key
str
default:"''"
Cache key for prompt optimization
​
safety_identifier
str
default:"''"
Safety identifier for content filtering
​
service_tier
str
default:"''"
Service tier for the research request
​
tool_choice
str
default:"''"
Specific tool choice for research
​
tools
ListType | list[List[Dict[str, Any]]] | list[dict]
default:"[]"
Tools to use for research
​
truncation
str
default:"''"
Truncation strategy for long inputs
​
deployment_id
str
default:"''"
The deployment ID for the Azure OpenAI model
​
endpoint
str
default:"''"
The Azure OpenAI endpoint URL
​
finetuned_model
str
default:"''"
Use your finetuned model for deep research

​
exa_ai — Query the Exa search API

Query the Exa search API 
pipeline.add(name="node").exa_ai(query="...")
Parameters
​
query
str
required
​
end_crawl_date
str
default:"''"
​
end_published_date
str
default:"''"
​
livecrawl
bool
default:"True"
​
loader_type
str
default:"'EXA_AI_SEARCH'"
One of: EXA_AI_SEARCH, EXA_AI_SEARCH_COMPANIES, EXA_AI_SEARCH_FINANCIAL_REPORTS, EXA_AI_SEARCH_NEWS, EXA_AI_SEARCH_PEOPLE, EXA_AI_SEARCH_PERSONAL_SITES, EXA_AI_SEARCH_RESEARCH_PAPERS, EXA_AI_SEARCH_TWEETS
​
max_characters
int
default:"2000"
​
num_results
int
default:"10"
​
search_type
str
default:"'auto'"
One of: auto, deep, deep-max, deep-reasoning, fast, instant, neural
​
start_crawl_date
str
default:"''"
​
start_published_date
str
default:"''"
​
use_highlights
bool
default:"False"

​
fetch_filings — Fetch Filings

Search for financial filings (10-K, 10-Q) by stock ticker 
pipeline.add(name="node").fetch_filings(tickers="...")
Parameters
​
document_group_ids
str
default:"'3,4'"
​
end_date
str
default:"''"
​
limit
int
default:"5"
​
loader_type
str
default:"'filings'"
One of: filings
​
start_date
str
default:"''"
​
tickers
str
required

​
fetch_financials — Fetch Financials

Fetch income statements, balance sheets, or cash flow statements with SEC filing citations 
pipeline.add(name="node").fetch_financials(statement_type="balance-sheet", tickers="...")
Parameters
​
currency
str
default:"''"
​
limit
int
default:"5"
​
loader_type
str
default:"'financials'"
One of: financials
​
metrics
str
default:"''"
​
period_type
str
default:"'annual'"
One of: annual, latest, ltm, quarterly
​
statement_type
str
required
One of: balance-sheet, cash-flow-statement, income-statement
​
tickers
str
required

​
fetch_logos — Fetch Logos

Fetch company logos by ticker or domain 
pipeline.add(name="node").fetch_logos(tickers="...")
Parameters
​
domains
str
default:"''"
​
format
str
default:"'png'"
One of: jpg, png, webp
​
retina
bool
default:"True"
​
size
int
default:"256"
​
theme
str
default:"'light'"
One of: dark, light
​
tickers
str
required

​
fetch_ratios — Fetch Ratios

Fetch financial ratios (P/E, EV/EBITDA, margins, growth) for one or more companies 
pipeline.add(name="node").fetch_ratios(tickers="...")
Parameters
​
currency
str
default:"''"
​
daily
str
default:"'false'"
​
loader_type
str
default:"'ratios'"
One of: ratios
​
period_type
str
default:"'annual'"
One of: annual, latest, quarterly
​
ratio_ids
str
default:"''"
​
tickers
str
required

​
fetch_slides — Fetch Slides

Search for investor presentation slides by stock ticker 
pipeline.add(name="node").fetch_slides(tickers="...")
Parameters
​
document_group_ids
str
default:"''"
​
end_date
str
default:"''"
​
limit
int
default:"1"
​
loader_type
str
default:"'slides'"
One of: slides
​
start_date
str
default:"''"
​
tickers
str
required

​
fetch_stock_prices — Fetch Stock Prices

Fetch historical stock prices for one or more companies 
pipeline.add(name="node").fetch_stock_prices(tickers="...")
Parameters
​
end_date
str
default:"''"
​
loader_type
str
default:"'stock_prices'"
One of: stock_prices
​
start_date
str
default:"''"
​
tickers
str
required

​
fetch_transcripts — Fetch Transcripts

Search for earnings call transcripts by stock ticker 
pipeline.add(name="node").fetch_transcripts(tickers="...")
Parameters
​
end_date
str
default:"''"
​
limit
int
default:"5"
​
loader_type
str
default:"'transcripts'"
One of: transcripts
​
start_date
str
default:"''"
​
tickers
str
required

​
file — File

Load a static file into the workflow as a raw File or process it into Text.
Platform docs: File
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

​
google_alert_rss_reader — Google Alert RSS Reader

Read the contents from an RSS feed created from a Google Alert: https://www.google.com/alerts 
pipeline.add(name="node").google_alert_rss_reader(feed_link="...")
Parameters
​
feed_link
str
required
​
timeframe
str
default:"'all'"
One of: all, past day, past month, past week
Query the Google Search search API 
pipeline.add(name="node").google_search(query="...")
Parameters
​
query
str
required
​
location
str
default:"'us'"
​
num_results
int
default:"10"
​
search_type
str
default:"'web'"
One of: events, hotels, image, news, web
Search the web with Parallel’s Search API 
pipeline.add(name="node").parallel_ai_search()
Parameters
​
blocked_domains
list[str]
default:"[]"
​
excerpts_max_chars_per_result
int
default:"1500"
​
fetch_live_results
bool
default:"False"
​
max_chars_per_result
int
default:"1500"
​
max_results
int
default:"10"
​
mode
str
default:"'one-shot'"
One of: agentic, one-shot
​
objective
str
default:"''"
​
preferred_domains
list[str]
default:"[]"
​
processor
str
default:"''"
One of: “, base, pro
​
search_queries
list[str]
default:"[]"

​
perplexity_search — Query the Perplexity search API

Query the Perplexity search API 
pipeline.add(name="node").perplexity_search(query="...")
Parameters
​
query
str
required
​
last_updated_after_filter
str
default:"''"
​
last_updated_before_filter
str
default:"''"
​
max_results
int
default:"10"
​
max_tokens_per_page
int
default:"1000"
​
query_list
list[str]
default:"[]"
​
return_images
bool
default:"False"
​
return_snippets
bool
default:"True"
​
search_after_date_filter
str
default:"''"
​
search_before_date_filter
str
default:"''"
​
search_domain_filter
list[str]
default:"[]"
​
search_mode
str
default:"''"
One of: “, academic, web
​
search_recency_filter
str
default:"''"
One of: “, day, month, week, year
​
user_location_latitude
str
default:"''"
​
user_location_longitude
str
default:"''"
​
user_location_name
str
default:"''"
​
user_location_radius_km
str
default:"''"

​
reducto_extract — Reducto Extract

Extract structured data from documents using Reducto 
pipeline.add(name="node").reducto_extract(json_schema="...", system_prompt="...")
Parameters
​
use_personal_api_key
bool
default:"False"
Use your own Reducto API key instead of the platform default.
​
return_citations
bool
default:"False"
Return citation bounding boxes for extracted fields.
​
api_key
str
default:"''"
Your personal Reducto API key.
​
deep_extract
bool
default:"True"
Enable agentic deep extraction for higher accuracy. Uses iterative verification against the source material.
​
files
AcceptsFileList
default:"[]"
Documents to extract data from (up to 2,500 pages per document).
​
json_schema
str
required
A JSON schema defining the structure of data to extract. Use descriptive field names.
​
system_prompt
str
required
Instructions for how the AI should extract and verify data from the documents.

​
rss — RSS

RSS 
pipeline.add(name="node").rss()
Parameters
​
sub_type
str
default:"''"

​
rss_feed_reader — RSS Feed Reader

Read the contents from an RSS feed 
pipeline.add(name="node").rss_feed_reader(url="...")
Parameters
​
entries
int
default:"10"
​
timeframe
str
default:"'all'"
One of: all, past day, past month, past week
​
url
str
required

​
serp_api — Serp API

Query the SERPAPI Google search API 
pipeline.add(name="node").serp_api(query="...", api_key="...")
Parameters
​
query
str
required
​
api_key
str
required

​
url_loader — URL Loader

Scrape the contents from a URL 
pipeline.add(name="node").url_loader(api_key="...", url="...")
Parameters
​
provider
str
default:"'jina'"
The provider to use for the URL Scraper One of: apify, jina, modal
​
use_actions
bool
default:"True"
Perform browser actions to interact with the input website
​
recursive
bool
default:"False"
Whether to recursively load the URL
​
api_key
str
required
The API key to use
​
url
str
required
The URL to load
​
url_limit
int
default:"10"
The maximum number of URLs to load
​
actions
AcceptsAnyList | ListType | list[AcceptsAnyList]
default:"[]"
The browser actions to perform on the URL
​
ai_enhance_content
bool
default:"False"
Whether to enhance the content
​
load_sitemap
bool
default:"False"
Load URLs to crawl from a sitemap. If the URL is a sitemap, it will be used directly. If the URL is not a sitemap, the sitemap will be fetched automatically.
​
use_proxy
bool
default:"False"
Use a proxy to crawl the website
Web Search 
pipeline.add(name="node").web()
Parameters
​
sub_type
str
default:"''"

​
wikipedia — Wikipedia

Query Wikipedia to return relevant articles 
pipeline.add(name="node").wikipedia(query="...")
Parameters
​
chunk_text
bool
default:"False"
Whether to chunk the text
​
query
str
required
The Wikipedia query
​
chunk_overlap
int
default:"0"
The overlap of the chunks
​
chunk_size
int
default:"512"
The size of the chunks to create

​
you_dot_com — Query the You.com search API

Query the You.com search API 
pipeline.add(name="node").you_dot_com(query="...", api_key="...")
Parameters
​
loader_type
str
default:"'YOU_DOT_COM'"
Select the loader type: General or News One of: YOU_DOT_COM, YOU_DOT_COM_NEWS
​
query
str
required
The search query
​
api_key
str
required
You.com API key

​
youtube — Youtube

Get the transcript of a youtube video. 
pipeline.add(name="node").youtube(url="...")
Parameters
​
chunk_text
bool
default:"False"
Whether to chunk the text
​
url
str
required
The YouTube URL to get the transcript of
​
chunk_overlap
int
default:"0"
The overlap of the chunks
​
chunk_size
int
default:"512"
The size of the chunks to create