AgentTools.<tool>(tool_name="...", ...) or agent.add_tool.<tool>(tool_name="...", ...). Every tool requires a unique tool_name=. Each entry lists the tool’s configuration parameters. See the Agent reference for attaching and running tools.
agent — Agent
Any
default:"{}"
The complete agent configuration including instructions, tools, inputs, and outputs
str
default:"'gpt-5.4'"
Select the LLM model to be used
dict
default:"{}"
Dynamic inputs generated from agent inputs configuration
dict
default:"{}"
Dynamic outputs generated from agent outputs configuration
str
default:"'openai'"
Select the LLM provider to be used
bool
default:"False"
Whether to use an existing agent
Agent | str
default:"\"{'object_id': '', 'object_type': 25}\""
The ID of the agent to be used
code_interpreter — Code Interpreter
Execute Python code in a sandboxed environment with file I/O support. Supports spreadsheet analysis, data visualization, and generating artifacts. To read or edit uploaded files, pass them in the files input as an actual array of file references; those files are mounted at /work/inputs/{filename} (curly braces shown for clarity; replace with the exact filename). Continued sessions restore prior inputs and generated files, so work can resume even if Python memory reset. Save output files to /work/outputs/ to have them collected as artifacts; call save_file(…) for durable/versioned user-visible files. Example: files=[“$history.69dd11a49033ae4d8e65ab33”] and pd.read_csv(‘/work/inputs/data.csv’); plt.savefig(‘/work/outputs/chart.png’). You will see stdout and stderr outputs after each execution step. Include an existing session id to keep executing code within the same session.
Platform docs: Code Interpreter
Any
The Python code to execute in the sandboxed environment
Any
Optional files to make available to the code (e.g., spreadsheets, CSV files). Pass an actual array of file references, such as [“history.69dd11a49033ae4d8e65ab33"] or ["object.knowledge_base_item.6875a39904d4beff85bdde61”]. Files passed here are mounted into /work/inputs/<exact filename>; continued sessions also restore prior session files.
create_skill — Create Skill
Create a new skill with a name, description, and content
str
default:"''"
The full content/instructions of the skill. Use markdown formatting: headings (##, ###) to organize sections, bullet points (- or *) for instructions and guidelines, numbered lists (1. 2. 3.) for sequential steps, bold for key terms and critical instructions, and
code for technical terms or placeholders. Add a <br> tag between major sections for visual spacing.str
default:"''"
The name of the skill
str
default:"''"
A brief description of what the skill does
custom_tool — OpenAI-native built-ins (code_interpreter, file_search)
OpenAI-native built-ins (code_interpreter, file_search)
generate_chart — Generate Chart
Use this to generate a chart from. Convert a tabular file, dataframe or table to a chart or graph visualization. Supports bar, line, pie, scatter, and donut charts/graphs.
str
required
The type of chart to generate (bar, line, pie, scatter, donut)
One of:
bar, donut, line, pie, scatter, time_seriesstr
required
The dataframe to visualize as a chart. In case of csv, the input should be a properly formatted valid csv string with appropriate headers. When chaining from a tool that returned a CSV file (e.g. fetch_ratios.table), set dataframe_type=“file” and pass $action.<id>.table — never paste the upstream formatted_text/XML here.
str
required
Actual column names from the dataframe. It should be a string representing the comma separated list of column names.
str
required
The type of dataframe to be used. Only available options are table, csv, md, json, file.
str
required
The title to display on the chart
str
required
The column name to use for the X-axis (categories). Must EXACTLY match (case-sensitive) one of the column names from the CSV header.
str
required
Column name(s) for Y-axis values. Must EXACTLY match (case-sensitive) column name(s) from the CSV header. For multi-series charts (multiple lines/bars), use comma-separated names like ‘revenue,profit,cost’.
str
How to aggregate values when there are multiple data points per category
str
A brief description or subtitle explaining what the chart shows
str
Where to display the chart legend
str
The order to sort the data
str
The label to display on the X-axis. Defaults to the field name if not provided.
str
The label to display on the Y-axis
str
Currency symbol (only used with currency format)
str
Initial time period tab selection
str
How to format values
str
Comma-separated icon URLs for each series (company logos, game art, product images, etc.), in same order as y_axis_fields. Leave empty for no icons.
str
Comma-separated display names for each Y-axis field, in same order as y_axis_fields (e.g. ‘MSFT,NVDA’ for tickers, ‘Halo,Fortnite’ for games, ‘US,EU,APAC’ for regions).
str
Set to ‘true’ to show Original/% Change toggle
str
Scale suffix for values
get_skill — Get Skill
Retrieve the full content of a skill by its ID
Any
default:"{}"
The skill to retrieve. Specify by its id like $object.prompt.id
knowledge_base — Knowledge Base Reader
Semantically query a knowledge base that can contain files, scraped URLs, and data from synced integrations (e.g., Google Drive).
Platform docs: Knowledge Base Reader
bool
required
Use additional LLM calls to analyze each document to improve answer correctness
str
required
The unit of retrieval. Chunks will return the most relevant chunks from the knowledge base as well as their text content. Documents will return the document metadata as well as most relevant snippets from the document. Pages will return complete pages with all chunks from pages containing relevant content
One of:
chunks, documents, pagesbool
required
Format the context for the LLM
bool
required
Whether to stream the LLM response
KnowledgeBase | str
required
Select an existing knowledge base, Use $object.knowledge_base.? syntax
str
required
The query will be used to search documents for relevant content semantically. Must not be empty, only include relevant information for retrieval or metadata filter generation. Generally expand any specific acronyms or abbreviations but include the original acronym or abbreviation as well
float
The alpha value for the retrieval. 1.0 is pure vector search and 0.0 is pure lexical search
bool
Extract separate questions from the query and retrieve content separately for each question to improve search performance
bool
Do a natural language metadata query
bool
Expand query to improve semantic search
bool
Expand query terms to improve semantic search
bool
Use an LLM to generate metadata filters to refine your query. Agents should usually leave this false and provide filters directly in the filter input.
float
The score cutoff
int
The number of relevant chunks to be returned
bool
Transform the query for better semantic search
str
The mode to use for the advanced search
str
The model to use for the QA
knowledge_base_agent — Knowledge Base Agent
Query a knowledge base using an agentic approach with tools.
Platform docs: Knowledge Base Agent
Any
Optional additional context to help the agent understand the query better (e.g., conversation history, user preferences)
KnowledgeBase | str
default:"\"{'object_type': 1, 'object_id': ''}\""
Select an existing knowledge base. You must provide the id in $.object.knowledge_base.id format
str
default:"'gemini-3-flash-preview'"
Select the LLM model to be used by the agent
str
default:"''"
The natural language query. The agent will use this to determine the best way to query the knowledge base. Include the key criteria needed to answer the query.
bool
default:"True"
If enabled, generates a synthesized answer from the knowledge base
str
default:"'google'"
Select the LLM provider to be used by the agent
str
default:"'focused'"
Controls the query effort: ‘fast’ for quick answers, ‘focused’ for balanced depth, ‘deep’ for thorough analysis
bool
default:"False"
If enabled, shows an additional context input to provide context to the agent
bool
default:"False"
If enabled, returns the relevant context/chunks used to generate the answer
knowledge_base_create — Create Knowledge Base
Dynamically create a Knowledge Base with configured options
Platform docs: Create Knowledge Base
bool
default:"False"
To analyze document contents and enrich them when parsing
str
default:"''"
Apify API Key for scraping URLs (optional)
int
default:"0"
The overlap of the chunks to store in the knowledge base
int
default:"400"
The size of the chunks to store in the knowledge base
str
default:"'voyage-4-lite'"
The name of the collection to store the knowledge base in
str
default:"'voyageai/voyage-4-lite'"
The embedding model to use for the knowledge base. Format: provider/model
str
default:"'voyageai'"
The embedding provider to use
str
default:"'default'"
The file processing implementation to use for parsing documents
bool
default:"False"
Whether to create a hybrid knowledge base
str
default:"''"
The name of the knowledge base to create
str
default:"'Uint8'"
The precision to use for the knowledge base
str
default:"'words'"
The method to break text into units before chunking. ‘words’: splits by word; ‘sentences’: splits by sentence boundary; ‘paragraphs’: splits by blank line/paragraph.
bool
default:"True"
Whether to shard the knowledge base
str
default:"'qdrant'"
The vector database provider to use
str
default:"'markdown'"
Strategy for grouping segmented text into final chunks. ‘sentence’: groups sentences; ‘markdown’: respects Markdown structure (headers, code); ‘dynamic’: optimizes breaks for size using chosen segmentation method.
knowledge_base_fetch_document_content — Knowledge Base Fetch Document Content
Fetch the full content of a specific document from a knowledge base by scrolling through all its chunks
Platform docs: Knowledge Base Fetch Document Content
str
default:"''"
item id of the item to fetch content from
KnowledgeBase | str
default:"\"{'object_type': 1, 'object_id': ''}\""
Select an existing knowledge base
int
default:"200"
Maximum number of chunks to include in the content
int
default:"0"
Number of chunks to skip for pagination.
str
default:"''"
Optional page ranges to fetch, e.g. ‘1-5,8,10-12’. If empty, fetches all pages.
knowledge_base_fetch_items — Knowledge Base Fetch Items
Advanced knowledge base item fetching with traversal, filtering, and output shaping capabilities
Platform docs: Knowledge Base Fetch Items
str
default:"''"
JSON filter object, example filter syntax: ’{“type”: “condition”, “field”: “file_extension”, “operator”: “eq”, “value”: “pdf”}’ or ’{“type”: “condition”, “field”: “title”, “operator”: “match”, “value”: “Pantheon”}’ only use filters if explicitly requested by the user. Do not use filters on fields other than file type. Available operators include are eq and neq, do not use filter operator contains
str
default:"'ALL'"
Type of items to return: FOLDERS, DOCUMENTS, or ALL
Any
Select an existing knowledge base
int
default:"50"
Maximum number of items to return, capped at 200
int
default:"0"
Maximum depth for descendants traversal, use 0 to traverse up as deep as possible to get to {{limit}} items, use 1 to get direct children etc
int
default:"0"
Number of items to skip for pagination
str
default:"''"
Filter to list items in specific folders by providing comma-separated root IDs
str
default:"''"
Comma-separated fields to sort by
str
default:"''"
Comma-separated sort orders: asc or desc
str
default:"'metadata'"
Output verbosity level: metadata (no summaries), short (short summaries), or long (short and long summaries), Use metadata for for simply finding folders/ documents, use short for understanding folder/document contents, use long with a lower limit for deep understanding of a particular folder/subfolder
knowledge_base_get_item_bboxes — Knowledge Base Get Item Bboxes
Fetch OCR bounding boxes for specific pages of a PDF document in a knowledge base
str
default:"''"
Item ID of the document to fetch bounding boxes for
KnowledgeBase | str
default:"\"{'object_type': 1, 'object_id': ''}\""
Select a knowledge base
str
default:"''"
Page ranges to fetch bounding boxes for, e.g. ‘1-5,8,12’
knowledge_base_loader — Knowledge Base Loader
Load data into an existing knowledge base.
Platform docs: Knowledge Base Loader
str
required
Select the type of data to load
One of:
File, URLlist[str]
required
The file to be added to the selected knowledge base. Note: to convert text to file, use the Text to File node
KnowledgeBase | str
required
The knowledge base to load data into
list_objects — List Objects
List VectorShift objects accessible to the current user
Include objects shared with you by other users
int
default:"0"
Maximum number of objects to return (0 = no limit)
str
default:"'pipeline'"
The type of VectorShift object to list
int
default:"0"
Number of objects to skip (0 = no offset)
bool
default:"False"
Return full object data instead of just id, name, and type
mcp_connector — Integration-backed MCP (Slack, GitHub, etc.)
Integration-backed MCP (Slack, GitHub, etc.)
mcp_server — Mcp Server
Bind an MCP server (created via web UI) as a tool source
pipeline — Pipeline
Platform docs: Pipeline
Pipeline | str
default:"\"{'object_type': 0, 'object_id': ''}\""
The ID of the pipeline to be used
read_memory — Read Memory
Load the full content of a memory entry. Use this when: - A memory shown in context appears truncated or abbreviated - A knowledge base memory needs its full document index (folder structure, document list) - You need the complete text of a memory that shows [content not loaded] Returns the full content as a string. Knowledge base memories: returns the KB’s document index and folder hierarchy (not document content). Use knowledge_base_query to search document content.
str
default:"''"
The memory_id shown in the context_memories section next to the memory name.
transformation — Transformation
Use Python code to create a custom node
Platform docs: Transformation
Transformation | str
default:"\"{'object_id': '', 'object_type': 14}\""
The ID of the transformation to be used
write_memory — Write Memory
Create or update a Memory object for use with context-aware agents. You can store text memory content and or references to object types like knowledge bases, knowledge base items, files and prompts.
list[str]
default:"[]"
Content to store in the memory. Each item can be plain text or an object reference using ‘object.knowledge_base.617’, ‘$object.file.718’). Allowed object types: KnowledgeBase, File, KnowledgeBaseItem, Prompt.
str
default:"''"
brief description of what this memory contains and when it should be used
str
default:"''"
Use this to update an existing memory instead of creating a new one.
str
default:"''"
Name of the memory entry
str
default:"''"
Optional explicit user ID to use for User scope. If empty, authenticated caller user ID is used. Provide the raw ObjectId only (e.g. ‘6875a39904d4beff85bdde61’), not prefixed with ‘user:’ or any other label.
list[str]
default:"[]"
Scopes to associate with this memory. Allowed values: User, Session, Agent, Org, Workspace. Memory will be accessible if all scopes are true. All listed scopes are required (AND). Example: Agent + Workspace means memory is only in scope for that agent inside that workspace.