Semarchy GenAI Amazon Bedrock Cohere structured enricher

The Semarchy GenAI Amazon Bedrock Cohere structured enricher extracts structured data from unstructured text to enhance data completeness and streamline the data entry process.

Plugin ID

Semarchy GenAI Amazon Bedrock Cohere Structured Enricher - com.semarchy.engine.plugins.genai.amazon.bedrock.cohere.structured

Description

The GenAI Amazon Bedrock Cohere structured enricher is designed to extract structured data from unstructured text using Cohere language models available through the Amazon Bedrock service. It can generate or extract up to 20 outputs in JSON format, including strings, booleans, numbers, and dates.

Plugin parameters

The following table lists the plugin parameters.

Parameter name Mandatory Type Description

Model Name

Yes

String

Language model to be used (e.g., cohere.command-text-v14).

Temperature

No

Number

Value ranging from 0 to 1 for balancing between conservative and coherent outputs (0) and creative variations (1) during text generation.
Default value: 0

Max Tokens

No

Integer

Maximum number of tokens allowed in the generated output during text generation.
Default value: 20

The total length of input and generated tokens is limited by the context length of the model.
Setting an insufficient number of tokens may result in a runtime error during response processing. Make sure to adjust the Max Tokens parameter to accommodate the number of generated tokens, considering your requirements and the terms of your OpenAI license.

Top P

No

Number

Value ranging from 0 to 1 for defining the cumulative probability threshold for nucleus sampling (i.e., token selection).
Default value: 0.75

Nucleus sampling is an alternative to temperature sampling. Ignore this parameter if you configured the Temperature parameter.

Top K

No

Number

Value ranging from 0 to 500 for limiting the model’s predictions to the most probable tokens at each step of generation.
Default value: 0

If both Top P and Top K are configured, the model first narrows down the tokens to the top k most probable ones, then applies the Top P filtering to this subset.

Stop Sequences

No

Integer

Number of predefined sequences (up to four) acting as signals for the model to halt the generation of further tokens.

The final returned text does not include the stop sequence itself.

Return Likelihoods

No

String

Choice of whether and how the model should return token likelihoods with the response. Possible values are:

  • GENERATION: only returns likelihoods for generated tokens.

  • ALL: returns likelihoods for all tokens.

  • NONE (default): does not return any likelihoods.

Token likelihoods provide a measure of the probability that a particular token appears in the output, which can be useful for analyzing the model’s confidence in its predictions.

Stream

No

Boolean

Choice of whether to return the response piece-by-piece in real-time (true) or to return the complete response after the process finishes (false). Setting this parameter is required to support streaming.

Logit Bias

No

String

Adjustment, formatted as {token_id: bias} where bias is a float between -10 and 10, for either preventing the model from generating unwanted tokens or encouraging the inclusion of desired tokens. For more information, see the official Cohere documentation.

Num Generations

No

Number

Maximum number of generations that the model should return. Possible values range from 1 to 5.
Default value: 1

Truncate

No

String

Preferred approach to handling inputs longer than the maximum token length. Possible values are:

  • NONE: returns an error when the input exceeds the maximum input token length.

  • START: discards the start of the input.

  • END (default): discards the end of the input.

If you specify START or END, the model discards the input until the remaining input is exactly the maximum input token length for the model.

Boolean output <N> (BOOLEAN_OUT_<N>)

No

String

Descriptor for the Nth boolean output in the structured output generated by the enricher, providing a description for the extracted boolean data (from 1 to 5).

Date output <N> (DATE_OUT_<N>)

No

String

Descriptor for the Nth date output in the structured output generated by the enricher, providing a description for the extracted date data (from 1 to 5).

Number output <N> (NUMBER_OUT_<N>)

No

String

Descriptor for the Nth number output in the structured output generated by the enricher, providing a description for the extracted number data (from 1 to 5).

String output <N> (STRING_OUT_<N>)

No

String

Descriptor for the Nth string output in the structured output generated by the enricher, providing a description for the extracted string data (from 1 to 5).
The enricher can return up to 20 outputs (five of each type).
The output descriptors are specifically designed to match the corresponding attribute types, whether they are dates, strings, numbers, or boolean values. For example, the Date output 1 descriptor exclusively matches date attributes. This matching process is automatically handled by the plugin.

Language models

Language models are AI systems trained on vast amounts of text data to understand and generate human-like language, enabling tasks like text completion, translation, summarization, and sentiment analysis.

Amazon Bedrock offers a range of models with distinct capabilities. For more information on Cohere models and a list of stable model versions available on Amazon Bedrock, see the official Cohere documentation and official Amazon Bedrock documentation.

Tokens

Tokens are units of text that language models use to process and generate language. They can range from individual characters to entire words, depending on the language and the specific model being used.

For more information about tokens, see the official AWS documentation or this video from the official AWS Developers channel on YouTube.

Plugin inputs

The following table lists the plugin inputs.

Input name Mandatory Type Description

User Prompt

No

String

Instructions specifying the information to be extracted and the method for structuring the outputs accordingly.

Source Text for Extraction

No

String

Unstructured text from which structured data is extracted.

System Prompt

No

String

Initial instruction designed to guide the model towards specific topics, styles, tones, or formats of generated text.
If you choose not to set a user prompt, you must enter a source text for extraction, and vice-versa. Defining either a user prompt or a source text for extraction is mandatory.

When opting for the Source Text for Extraction method, the enricher injects the provided text along with the configured descriptors (i.e., String output 1, Number output 1, etc.) into a standard user prompt. The pieces of information specified by the descriptors are then extracted from the text content.

When opting for the User Prompt method, model designers construct a user prompt containing unstructured values and output keys (i.e., STRING_OUT_1, NUMBER_OUT_1, etc.). These keys are then mapped to the relevant attributes in the plugin output properties.

When formulating a user prompt, make sure to instruct the enricher to extract data in a structured JSON format.

For a detailed demonstration of these methods, see Examples and use cases.

Plugin outputs

The following table lists the plugin outputs.

Output name Type Description

Boolean output <N> (BOOLEAN_OUT_<N>)

String

Extracted boolean corresponding to the Nth boolean output descriptor, numbered from 1 to 5, and applied to a designated attribute.

Date output <N> (DATE_OUT_<N>)

String

Extracted date corresponding to the Nth date output descriptor, numbered from 1 to 5, and applied to a designated attribute.

Number output <N> (NUMBER_OUT_<N>)

String

Extracted number corresponding to the Nth number output descriptor, numbered from 1 to 5, and applied to a designated attribute.

String output <N> (STRING_OUT_<N>)

String

Extracted string corresponding to the Nth string output descriptor, numbered from 1 to 5, and applied to a designated attribute.

Examples and use cases

AI-powered product data extraction: streamlining record creation

Imagine a scenario where a user wants to expedite product record creation by automatically extracting a product’s name, price, and country of origin from a detailed description. In practice, the user wants the Product Name, Price, and Country of Origin fields to be automatically populated based on the Description field’s content.

For instance, consider a new product record with the following description:
"The Aerodynamic Helmet by Velocity Bikes is expertly crafted in France for speed, style, and safety. Its sleek profile reduces drag while prioritizing rider protection. Priced at $129.99, it’s the ultimate choice for safety-conscious cyclists."

Two methods can be employed to achieve the desired result.

  • Using the Source Text for Extraction method, a model designer can configure the enricher as follows:

    • In the plugin properties:

      • String output 1 (STRING_OUT_1): Name of the product

      • String output 2 (STRING_OUT_2): Country of origin of the product

      • Number output 1 (NUMBER_OUT_1): Price of the product

    • In the plugin input properties:

      • Source Text for Extraction: Description

    • In the plugin output properties:

      • ProductName: String output 1 (STRING_OUT_1)

      • Origin: String output 2 (STRING_OUT_2)

      • Price: Number output 1 (NUMBER_OUT_1)

  • Using the User Prompt method, the model designer can configure the enricher as follows:

    • In the plugin input properties:

      • User Prompt: 'From ' || Description || ' extract the following information in a structured JSON format: STRING_OUT_1: the product name, STRING_OUT_2: the country of origin, NUMBER_OUT_1: the product price.'

    • In the plugin output properties:

      • ProductName: String output 1 (STRING_OUT_1)

      • Origin: String output 2 (STRING_OUT_2)

      • Price: Number output 1 (NUMBER_OUT_1)

Regardless of the method selected, the enricher’s response populates the Product Name, Country of Origin, and Price fields in the new record with the following information:

  • Product Name: Aerodynamic Helmet

  • Country of Origin: France

  • Price: 129.99