Skip to content
Flow Like logo Flow Like Docs

Invoke with Tools Node

AI/Generative

Invokes an LLM that can call Flow tools/functions and routes each call to execution pins.

invoke_llm_with_toolsllmLong running
Inputs5
Outputs4
Security exposure5/10
Packagellm

Ratings

Scores range from 0 to 10. Higher values mean more impact, exposure, or operational weight.

SecurityAttack surface and exposure impact.
5/10Medium
PrivacyPotential sensitivity of processed data.
4/10Medium
PerformanceRuntime or resource pressure.
7/10High
GovernancePolicy, audit, or compliance impact.
5/10Medium
ReliabilityOperational stability considerations.
6/10Medium
CostExternal or compute cost impact.
4/10Medium

Input Pins

5

Input

Execution
exec_in

Execution trigger to start the tool-enabled invocation

Model

Struct
model

Bit describing the provider/model to execute

BitBit19 fields
idstring
default ""
typeBitTypes
enum "Llm", "Vlm", "Tts", "Stt"...default "Other"
metaMap<string, Metadata>
default {}
*Metadatamap value
namestringrequired
descriptionstringrequired
long_descriptionstring | null
release_notesstring | null
tagsArray<string>required
itemsstringarray item
+11 more fields
authorsArray<string>
default []
itemsstringarray item
repositorystring | null
default null
download_linkstring | null
default null
file_namestring | null
default null
hashstring
default ""
sizeinteger | null
format uint64default nullmin 0
hubstring
default ""
parametersvalue
default null
versionstring | null
default null
licensestring | null
default null
dependenciesArray<string>
default []
itemsstringarray item
dependency_tree_hashstring
default ""
createdstring
default ""
updatedstring
default ""
model_slugstring | null
default null
+1 more fields
Schema enforced

History

Struct
history

Conversation history the model should continue from

HistoryHistory19 fields
modelstringrequired
messagesArray<HistoryMessage>required
itemsHistoryMessagearray item
roleRolerequired
enum "system", "user", "assistant", "function"...
contentMessageContentrequired
variant 1stringvariant
variant 2Array<Content>variant
namestring | null
tool_callsarray | null
itemsToolCallarray item
tool_call_idstring | null
+1 more fields
presetstring | null
streamboolean | null
stream_optionsanyOf (2)
variant 1StreamOptionsvariant
include_usagebooleanrequired
variant 2nullvariant
max_completion_tokensinteger | null
format uint32min 0
top_pnumber | null
format float
temperaturenumber | null
format float
thinkinganyOf (2)
variant 1HistoryThinkingvariant
enum "off", "low", "mid", "high"
variant 2nullvariant
seedinteger | null
format uint32min 0
presence_penaltynumber | null
format float
frequency_penaltynumber | null
format float
userstring | null
stoparray | null
itemsstringarray item
response_formatanyOf (2)
variant 1ResponseFormatvariant
variant 1stringvariant
variant 2nullvariant
ninteger | null
format uint32min 0
toolsarray | null
itemsToolarray item
typeToolTyperequired
enum "function"
functionHistoryFunctionrequired
namestringrequired
descriptionstring | null
parametersHistoryFunctionParametersrequired
tool_choiceanyOf (2)
variant 1ToolChoicevariant
variant 1nullvariant
variant 2nullvariant
variant 3nullvariant
variant 4objectvariant
typeToolTyperequired
enum "function"
functionHistoryFunctionrequired
variant 2nullvariant
+1 more fields
Schema enforced

Tools

String
tools

JSON array of tool/function definitions (OpenAI format)

Default []

Tool Choice

String
tool_choice

Controls whether the model must, may, or must not call tools

Default Auto
AutoRequiredNone

Output Pins

4

Done

Execution
exec_done

Signals when the invocation and tool routing finished

Response

Struct
response

LLM response if the model answered directly without tool calls

ResponseResponse8 fields
idstring | null
choicesArray<Choice>required
itemsChoicearray item
indexinteger:int32required
format int32
finish_reasonstringrequired
messageResponseMessagerequired
rolestringrequired
contentstring | null
content_partsArray<Content>

Ordered structured content returned by Rig when the assistant response contains media. Text-only responses continue to use `content` alone for OpenAI compatibility.

refusalstring | null
annotationsarray | null
+3 more fields
logprobsanyOf (2)
variant 1LogProbsvariant
variant 2nullvariant
createdinteger | null
format uint64min 0
modelstring | null
service_tierstring | null
system_fingerprintstring | null
objectstring | null
usageUsagerequired
completion_tokensinteger:uint32required
format uint32min 0
prompt_tokensinteger:uint32required
format uint32min 0
total_tokensinteger:uint32required
format uint32min 0
costnumber | null
format double
prompt_tokens_detailsanyOf (2)
variant 1PromptTokenDetailsvariant
cached_tokensinteger | null
format uint32min 0
audio_tokensinteger | null
format uint32min 0
variant 2nullvariant
+2 more fields
Schema enforced

Tool Call Args

Struct
tool_call_args

Parsed JSON arguments for the latest tool call

Stats

Struct
stats

Token usage, cost, and model statistics

LLMUsageStatsLLMUsageStats5 fields
usageUsagerequired
completion_tokensinteger:uint32required
format uint32min 0
prompt_tokensinteger:uint32required
format uint32min 0
total_tokensinteger:uint32required
format uint32min 0
costnumber | null
format double
prompt_tokens_detailsanyOf (2)
variant 1PromptTokenDetailsvariant
cached_tokensinteger | null
format uint32min 0
audio_tokensinteger | null
format uint32min 0
variant 2nullvariant
+2 more fields
modelstring | null
duration_msinteger | null
format uint64min 0
iterationsinteger | null
format uint32min 0
callsArray<ModelCallEntry>
itemsModelCallEntryarray item
modelstringrequired
usageUsagerequired
completion_tokensinteger:uint32required
format uint32min 0
prompt_tokensinteger:uint32required
format uint32min 0
total_tokensinteger:uint32required
format uint32min 0
costnumber | null
format double
prompt_tokens_detailsanyOf (2)
+2 more fields
duration_msinteger | null
format uint64min 0
Schema enforced

Node Info

Internal name
invoke_llm_with_tools
Category
AI/Generative
Version
4