This plugin is currently in beta. While it is considered safe for use, please be aware that its API could change in ways that are not compatible with earlier versions in future releases, or it might become unsupported.
Generate JSON-Structured Extraction with AI models.
The task is currently compatible with OpenAI, Ollama, and Gemini models.
type: "io.kestra.plugin.langchain4j.jsonstructuredextraction"JSON Structured Extraction using Gemini
id: json_structured_extraction
namespace: company.team
task:
id: json_structured_extraction
type: io.kestra.core.plugin.langchain4j.JSONStructuredExtraction
jsonFields:
- name
- City
schemaName: Person
prompt: Hello, my name is John, I live in Paris
provider:
type: io.kestra.plugin.langchain4j.provider.GoogleGemini
apiKey: "{{secret('GOOGLE_API_KEY')}}"
modelName: gemini-2.0-flash
JSON Fields
List of fields to extract from the text.
Text prompt
The input prompt for the AI model.
Language Model Provider
Schema Name
The name of the JSON schema for structured extraction.
{}Chat configuration
Extracted JSON
The structured JSON output.
STOPLENGTHTOOL_EXECUTIONCONTENT_FILTEROTHERFinish reason
Schema Name
The schema name used for the structured JSON extraction.
Token usage
seed
Temperature
topK
topP
Endpoint URL
Project location
Model name
Project ID
API endpoint
The Azure OpenAI endpoint in the format: https://{resource}.openai.azure.com/
Model name
API Key
Client ID
Client secret
API version
Tenant ID
API Key
Model name
https://api.deepseek.com/v1API base URL
API Key
Model name
AWS Access Key ID
Model name
AWS Secret Access Key
COHERECOHERETITANAmazon Bedrock Embedding Model Type
API Key
Model name
API base URL
API Key
Model name
API Key
Model name
API base URL
Model endpoint
Model name