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.
bool
default:"False"
Whether to return the raw JSON response from the API
ListType | list[KeyValue] | list[List[Dict[str, Any]]]
default:"[]"
The body parameters to include in the API request
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.
ListType | list[FileKeyValue] | list[List[Dict[str, Any]]]
default:"[]"
Files to include in the API request
ListType | list[KeyValue] | list[List[Dict[str, Any]]]
default:"[]"
Headers to include in the API request
str
default:"'GET'"
Choose the API Method desired (GET, POST, PUT, DELETE, PATCH)
One of:
DELETE, GET, PATCH, POST, PUTListType | list[KeyValue] | list[List[Dict[str, Any]]]
default:"[]"
Query parameters to include in the API request
str
required
Target URL for the API Request
str
default:"''"
The raw JSON request to the API
arxiv — Arxiv
Query ARXIV to return relevant articles
bool
default:"False"
Whether to chunk the text
str
required
The ARXIV query
int
default:"0"
The overlap of the chunks
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.
str
default:"''"
str
required
str
default:"''"
csv_query — CSV Query
Utilizes an LLM agent to query CSV(s). Delimeter for the CSV must be commas.
str
required
AcceptsFile
required
bool
default:"False"
deep_research — Deep Research
Perform advanced AI research and analysis with specialized model capabilities
Platform docs: Deep Research
str
required
Select the LLM provider for deep research
bool
default:"False"
Whether to stream the research response
bool
default:"False"
Whether to use a personal API key
str
default:"''"
Select the LLM model for deep research
str
required
Your personal API key for the research provider
str
default:"''"
Previous conversation context for research continuity
str
default:"''"
The data input for deep research analysis
str
default:"''"
Specific instructions for the deep research task
int
default:"128000"
Maximum number of tokens in the research output
int
default:"10"
Maximum number of tool calls during research
bool
default:"True"
Enable parallel tool execution for faster research
str
default:"''"
ID of previous response for continuation
str
default:"''"
Cache key for prompt optimization
str
default:"''"
Safety identifier for content filtering
str
default:"''"
Service tier for the research request
str
default:"''"
Specific tool choice for research
ListType | list[List[Dict[str, Any]]] | list[dict]
default:"[]"
Tools to use for research
str
default:"''"
Truncation strategy for long inputs
str
default:"''"
The deployment ID for the Azure OpenAI model
str
default:"''"
The Azure OpenAI endpoint URL
str
default:"''"
Use your finetuned model for deep research
exa_ai — Query the Exa search API
Query the Exa search API
str
required
str
default:"''"
str
default:"''"
bool
default:"True"
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_TWEETSint
default:"2000"
int
default:"10"
str
default:"'auto'"
One of:
auto, deep, deep-max, deep-reasoning, fast, instant, neuralstr
default:"''"
str
default:"''"
bool
default:"False"
fetch_filings — Fetch Filings
Search for financial filings (10-K, 10-Q) by stock ticker
str
default:"'3,4'"
str
default:"''"
int
default:"5"
str
default:"'filings'"
One of:
filingsstr
default:"''"
str
required
fetch_financials — Fetch Financials
Fetch income statements, balance sheets, or cash flow statements with SEC filing citations
str
default:"''"
int
default:"5"
str
default:"'financials'"
One of:
financialsstr
default:"''"
str
default:"'annual'"
One of:
annual, latest, ltm, quarterlystr
required
One of:
balance-sheet, cash-flow-statement, income-statementstr
required
fetch_logos — Fetch Logos
Fetch company logos by ticker or domain
str
default:"''"
str
default:"'png'"
One of:
jpg, png, webpbool
default:"True"
int
default:"256"
str
default:"'light'"
One of:
dark, lightstr
required
fetch_ratios — Fetch Ratios
Fetch financial ratios (P/E, EV/EBITDA, margins, growth) for one or more companies
str
default:"''"
str
default:"'false'"
str
default:"'ratios'"
One of:
ratiosstr
default:"'annual'"
One of:
annual, latest, quarterlystr
default:"''"
str
required
fetch_slides — Fetch Slides
Search for investor presentation slides by stock ticker
str
default:"''"
str
default:"''"
int
default:"1"
str
default:"'slides'"
One of:
slidesstr
default:"''"
str
required
fetch_stock_prices — Fetch Stock Prices
Fetch historical stock prices for one or more companies
str
default:"''"
str
default:"'stock_prices'"
One of:
stock_pricesstr
default:"''"
str
required
fetch_transcripts — Fetch Transcripts
Search for earnings call transcripts by stock ticker
str
default:"''"
int
default:"5"
str
default:"'transcripts'"
One of:
transcriptsstr
default:"''"
str
required
file — File
Load a static file into the workflow as a raw File or process it into Text.
Platform docs: File
str
default:"'upload'"
Select an existing file from the VectorShift platform
One of:
name, uploadstr
required
The name of the file from the VectorShift platform (for files on the File tab)
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, textractAcceptsFile
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
str
required
str
default:"'all'"
One of:
all, past day, past month, past weekgoogle_search — Google Search
Query the Google Search search API
str
required
str
default:"'us'"
int
default:"10"
str
default:"'web'"
One of:
events, hotels, image, news, webparallel_ai_search — Parallel AI Search
Search the web with Parallel’s Search API
list[str]
default:"[]"
int
default:"1500"
bool
default:"False"
int
default:"1500"
int
default:"10"
str
default:"'one-shot'"
One of:
agentic, one-shotstr
default:"''"
list[str]
default:"[]"
str
default:"''"
One of: “,
base, prolist[str]
default:"[]"
perplexity_search — Query the Perplexity search API
Query the Perplexity search API
str
required
str
default:"''"
str
default:"''"
int
default:"10"
int
default:"1000"
list[str]
default:"[]"
bool
default:"False"
bool
default:"True"
str
default:"''"
str
default:"''"
list[str]
default:"[]"
str
default:"''"
One of: “,
academic, webstr
default:"''"
One of: “,
day, month, week, yearstr
default:"''"
str
default:"''"
str
default:"''"
str
default:"''"
reducto_extract — Reducto Extract
Extract structured data from documents using Reducto
bool
default:"False"
Use your own Reducto API key instead of the platform default.
bool
default:"False"
Return citation bounding boxes for extracted fields.
str
default:"''"
Your personal Reducto API key.
bool
default:"True"
Enable agentic deep extraction for higher accuracy. Uses iterative verification against the source material.
AcceptsFileList
default:"[]"
Documents to extract data from (up to 2,500 pages per document).
str
required
A JSON schema defining the structure of data to extract. Use descriptive field names.
str
required
Instructions for how the AI should extract and verify data from the documents.
rss — RSS
RSS
str
default:"''"
rss_feed_reader — RSS Feed Reader
Read the contents from an RSS feed
int
default:"10"
str
default:"'all'"
One of:
all, past day, past month, past weekstr
required
serp_api — Serp API
Query the SERPAPI Google search API
str
required
str
required
url_loader — URL Loader
Scrape the contents from a URL
str
default:"'jina'"
The provider to use for the URL Scraper
One of:
apify, jina, modalbool
default:"True"
Perform browser actions to interact with the input website
bool
default:"False"
Whether to recursively load the URL
str
required
The API key to use
str
required
The URL to load
int
default:"10"
The maximum number of URLs to load
AcceptsAnyList | ListType | list[AcceptsAnyList]
default:"[]"
The browser actions to perform on the URL
bool
default:"False"
Whether to enhance the content
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.
bool
default:"False"
Use a proxy to crawl the website
web — Web Search
Web Search
str
default:"''"
wikipedia — Wikipedia
Query Wikipedia to return relevant articles
bool
default:"False"
Whether to chunk the text
str
required
The Wikipedia query
int
default:"0"
The overlap of the chunks
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
str
default:"'YOU_DOT_COM'"
Select the loader type: General or News
One of:
YOU_DOT_COM, YOU_DOT_COM_NEWSstr
required
The search query
str
required
You.com API key
youtube — Youtube
Get the transcript of a youtube video.
bool
default:"False"
Whether to chunk the text
str
required
The YouTube URL to get the transcript of
int
default:"0"
The overlap of the chunks
int
default:"512"
The size of the chunks to create