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.

​
chat_file_reader

Allows for document upload within chatbots (often connected to the LLM node).
Platform docs: Allows for document upload within chatbots (often connected to the LLM node).
pipeline.add(name="node").chat_file_reader()
Parameters
​
chunk_overlap
int
default:"200"
​
chunk_size
int
default:"1000"
​
file_parser
str
default:"'default'"
One of: contextual_ai, default, docling, llama_parse, mistral_ocr, reducto, textract
​
max_docs_per_query
int
default:"10"
​
retrieval_unit
str
default:"'chunks'"
One of: chunks, documents, pages

​
chat_memory

Give connected nodes access to conversation history.
Platform docs: Give connected nodes access to conversation history.
pipeline.add(name="node").chat_memory()
Parameters
​
memory_type
str
default:"'Full - Formatted'"
The type of memory to use One of: Full - Formatted, Full - Raw, Message Buffer, Token Buffer, Vector Database
​
memory_window
int
default:"2048"
The number of tokens to store in memory

​
create_session

Create a new session with an agent and participants
Platform docs: Create a new session with an agent and participants
pipeline.add(name="node").create_session(agent_id=...)
Parameters
​
agent_id
AcceptsAgent
required
​
name
str
default:"''"

​
data_collector

Allows a chatbot to collect information by asking the user to provide specific pieces of information (e.g., name, email, etc.).
Platform docs: Allows a chatbot to collect information by asking the user to provide specific pieces of information (e.g., name, email, etc.).
pipeline.add(name="node").data_collector(provider="anthropic", query="...")
Parameters
​
auto_generate
bool
default:"True"
If checked, the node will output questions in successive order until all fields are successfully collected. If unchecked, the node will output the data that is collected (often passed to an LLM with a prompt to ask successive questions to the user, along with specific instructions after all fields are collected) - e.g., {‘Field1’: ‘Collected_Data’, ‘Field2’: ‘Collected_Data’}
​
provider
str
required
The model provider
​
model
str
default:"''"
The specific model for question generation
​
prompt
str
default:"''"
Specific instructions of how the LLM should collect the information
​
query
str
required
The query to be analysed for data collection (passed to the LLM)
​
data_collector_node_id
str
default:"''"
The ID of the data collector node
​
fields
ListType | list[FieldDefinition] | list[List[Dict[str, Any]]]
default:"[]"
The fields to be collected

​
listen

Listen for user input at a stage in the conversation.
Platform docs: Listen for user input at a stage in the conversation.
pipeline.add(name="node").listen()
Parameters
​
variant
str
default:"''"
One of: button, capture
​
allow_user_message
bool
default:"False"
​
buttons
ListType | list[List[Dict[str, Any]]] | list[NameItem]
default:"[]"
​
processed_outputs
dict
default:"{}"

​
post_message

Post a message to a session
Platform docs: Post a message to a session
pipeline.add(name="node").post_message(message="...", session_id="...")
Parameters
​
message
str
required
​
session_id
str
required

​
read_memory

Load the full content of a memory entry. Use this when: 
pipeline.add(name="node").read_memory(memory_id="...")
Parameters
​
memory_id
str
required

​
read_session_messages

Read all messages from a session with derived metadata
Platform docs: Read all messages from a session with derived metadata
pipeline.add(name="node").read_session_messages(session_id="...")
Parameters
​
message_type_filter
str
default:"'none'"
​
offset
int
default:"0"
​
session_id
str
required

​
talk

Send a given message at a stage in a conversation.
Platform docs: Send a given message at a stage in a conversation.
pipeline.add(name="node").talk(content="...", description="...", image_url=..., title="...")
Parameters
​
variant
str
default:"''"
One of: card, carousel, image, message
​
is_iframe
bool
default:"False"
​
content
str
required
The text to send to the user.
​
button
dict
default:"{}"
​
description
str
required
The card’s description.
​
image_url
AcceptsImage
required
The image to be sent at this step in the conversation.
​
title
str
required
The card’s title.
​
cards
ListType | list[CarouselCard] | list[List[Dict[str, Any]]]
default:"[]"

​
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. 
pipeline.add(name="node").write_memory(content=..., name="...")
Parameters
​
content
list[str]
required
​
memory_description
str
default:"''"
​
memory_id
str
default:"''"
​
name
str
required
​
scope_user_id
str
default:"''"
​
scopes
list[str]
default:"[]"