Skip to content
Flow Like logo Flow Like Docs

AI Extractor with Struct Schema Node

AI/Generative

Uses an LLM and a reference struct's schema to extract structured data from free-form text

llm_extractor_struct_schemallmLong running
Inputs6
Outputs3
Security exposure4/10
Packagellm

Ratings

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

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

Input Pins

6

Input

Execution
exec_in

Execution trigger to start the extraction

Model

Struct
model

Bit pointing to the LLM that will perform the extraction

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

Schema Reference

Struct
struct_shape

A reference struct whose schema defines the extracted data. Its value is never evaluated

objectobject0 fields
No named fields in this schema.

Text

String
text

Raw text that should be structured via the reference schema

Extraction Hint

String
hint

Optional hint to guide the extraction, such as selecting line items instead of totals

Max Tokens

Integer
max_tokens

Output token budget for the model. 0 leaves it to the provider. Raise this if large extractions come back empty because the model ran out of room before calling the tool

Default 0

Output Pins

3

Execution Output

Execution
exec_out

Executes after extraction succeeds

Json

Struct
response

Structured JSON value that matches the reference schema

objectobject0 fields
No named fields in this schema.

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
llm_extractor_struct_schema
Category
AI/Generative
Version
2