> ## Documentation Index
> Fetch the complete documentation index at: https://docs.odella.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Extract Data Block

> Leverage AI to extract structured data from unstructured text based on a flexible schema

## Overview

The Extract Data Block uses AI capabilities to extract structured data from unstructured text input. By defining a flexible schema, you can specify which fields to extract, their data types, and provide detailed descriptions to guide the AI model in accurately extracting the desired information.

<Frame>
  <img src="https://mintcdn.com/odella/I7v1Fbrp2kx7rLoj/block-reference/assets/extract_data_light.png?fit=max&auto=format&n=I7v1Fbrp2kx7rLoj&q=85&s=d711320d59edf5fc318cbcc25bdb018e" alt="Extract Data Block Screenshot" className="block dark:hidden" width="1018" height="454" data-path="block-reference/assets/extract_data_light.png" />

  <img src="https://mintcdn.com/odella/I7v1Fbrp2kx7rLoj/block-reference/assets/extract_data_dark.png?fit=max&auto=format&n=I7v1Fbrp2kx7rLoj&q=85&s=4f3bee9ab5101caaef95f4fcd51bcdaa" alt="Extract Data Block Screenshot" className="hidden dark:block" width="1024" height="494" data-path="block-reference/assets/extract_data_dark.png" />
</Frame>

## Inputs

<ParamField path="systemPrompt" type="string">
  The system prompt to send to the model. Optional. Used to provide high-level guidance to the AI model.
</ParamField>

<ParamField path="context" type="string" required>
  The context to extract the specified schema(s) from. Required.
</ParamField>

## Outputs

<ResponseField name="all" type="object[]">
  An array of objects containing all extracted data, structured according to the defined schema.
</ResponseField>

<ResponseField name="[schemaField]" type="any[]">
  For each field defined in the schema, an array containing the extracted values for that field. The type will match the schema field type.
</ResponseField>

<ResponseField name="duration" type="number">
  The time in milliseconds that the block took to execute.
</ResponseField>

## Editor Settings

<ParamField path="AI Model" type="string" default="gpt-3.5-turbo">
  The AI model to use for data extraction. Available models are dynamically populated based on the LLM provider configuration.
</ParamField>

<ParamField path="Schema" type="object">
  The schema defining what data to extract. Specify field names, types, and descriptions to guide the extraction.
</ParamField>

### Parameters

<ParamField path="Temperature" type="number" default={0} min={0} max={2} step={0.1}>
  What sampling temperature to use. Higher values like 0.8 make output more random, while lower values like 0.2 make it more focused and deterministic.
</ParamField>

<ParamField path="Top P" type="number" default={1} min={0} max={1} step={0.1}>
  Alternative to temperature sampling. Only tokens comprising the top P probability mass are considered. For example, 0.1 means only tokens in the top 10% probability are considered.
</ParamField>

<ParamField path="Use Top P" type="boolean" default={false}>
  Whether to use top p sampling instead of temperature sampling.
</ParamField>

<ParamField path="Max Tokens" type="number" default={8192}>
  The maximum number of tokens to generate in the completion.
</ParamField>

<ParamField path="Stop" type="string">
  A sequence where the API will stop generating further tokens.
</ParamField>

<ParamField path="Presence Penalty" type="number" min={-2} max={2} step={0.1}>
  Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.
</ParamField>

<ParamField path="Frequency Penalty" type="number" min={-2} max={2} step={0.1}>
  Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.
</ParamField>

<ParamField path="Seed" type="number" step={1}>
  If specified, OpenAI will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.
</ParamField>

### Advanced

<ParamField path="Cache Responses" type="boolean" default={false}>
  If enabled, requests with the same parameters and messages will be cached for immediate responses without an API call.
</ParamField>

<ParamField path="Use for subgraph partial output" type="boolean">
  If enabled, streaming responses from this node will be shown in Subgraph nodes that call this graph.
</ParamField>

<ParamField path="Error on invalid output(s)" type="boolean">
  If enabled, the node will error if any of the results returned do not conform to the schema.
</ParamField>

## Error Handling

The block will retry failed attempts up to 3 times with exponential backoff:

* Minimum retry delay: 500ms
* Maximum retry delay: 5000ms
* Retry factor: 2.5x
* Includes randomization
* Maximum retry time: 5 minutes

Error messages will be logged for:

* Invalid schema validation
* Missing LLM provider configuration
* API errors and timeouts
* Aborted requests

<Warning>
  Always validate the output of the Extract Data block, especially when working with critical data or making important decisions based on the extracted information.
</Warning>

## Example: Extracting Contact Information

1. Add an Extract Data block to your flow.
2. Connect your input text (e.g., an email or document) to the `Context` input.
3. Define a schema in the block settings, for example:
   ```json theme={"system"}
   {
     "name": {"type": "string", "description": "Full name of the person"},
     "email": {"type": "string", "description": "Email address"},
     "phone": {"type": "string", "description": "Phone number"},
     "company": {"type": "string", "description": "Company name"}
   }
   ```
4. Select your desired provider and model.
5. Run your flow. The block will output an object with the extracted information.

## See Also

* [Analyze Table Block](/block-reference/ai/analyze-table)
* [AI Filter Block](/block-reference/ai/ai-filter)
* [Ask AI Block](/block-reference/ai/ai)