Mistral AI connectors

Integrate Mistral AI models into Bonita processes for text generation, classification and data extraction with EU data residency.

The Mistral connector is part of the Bonita AI Connectors family.

Getting started

Import the bonita-connector-ai-mistral module as an extension dependency in your Bonita project. See the AI connectors overview for general setup instructions.

Connection configuration

Parameter Required Description Default

API Key

Yes

Mistral API key from Mistral Console

Resolved from env var AI_API_KEY if not set

Base URL

No

Custom endpoint URL

https://api.mistral.ai/v1

Model Name

No

Mistral model to use

pixtral-12b-2409

Temperature

No

Controls randomness (0.0 to 1.0)

Timeout

No

Request timeout in milliseconds

Available models

  • mistral-large-latest — Most capable, best reasoning and generation

  • mistral-medium-latest — Balanced quality and cost

  • mistral-small-latest — Fast and cost-effective

  • pixtral-12b-2409 (default) — Multimodal with vision support

Mistral AI is headquartered in France and offers EU data residency, making it an excellent choice for GDPR-sensitive workloads.

Image documents are not supported yet for the Mistral connector due to a limitation of the underlying library.

See Mistral Models documentation for the full list.

Operations

Ask

Send a user prompt (with optional system prompt and documents) to a Mistral model and return the generated response.

Parameter Required Description Default

User Prompt

Yes

The prompt to send to Mistral

System Prompt

No

System instructions to guide the model behavior

You are a polite assistant.

Output JSON Schema

No

JSON Schema to structure the response as JSON

Source Document Reference

No

Bonita process document to include as context

Source Document References

No

List of Bonita process documents to include as context
Parameter Type Description

output

String

The generated response from the model

Classify

Classify a document into one of the predefined categories.

Parameter Required Description Default

Categories

Yes

Comma-separated list of classification categories

Source Document Reference

Yes

Bonita process document to classify

Source Document References

No

List of documents to classify
Parameter Type Description

output

String

JSON with category and confidence fields
Sample classification result
{
  "category": "BILLING",
  "confidence": 0.88
}

Extract

Extract structured data from a document using field names or a JSON Schema.

Parameter Required Description Default

Fields to Extract

No

Comma-separated list of field names to extract

Output JSON Schema

No

JSON Schema defining the extraction structure

Source Document Reference

Yes

Bonita process document to extract from

Source Document References

No

List of documents to extract from
You must provide at least one of fieldsToExtract or outputJsonSchema parameters.
Parameter Type Description

output

String

JSON with extracted fields

Use cases

GDPR-compliant text processing

Process personal data documents while keeping all data within the EU. Mistral’s European infrastructure ensures data never leaves EU jurisdiction.

Process flow:

  1. An HR document containing employee personal data is uploaded

  2. A service task uses the Extract connector to parse the document

  3. All processing occurs on Mistral’s EU servers

  4. Extracted data is stored in the Bonita BDM for downstream processing

Configuration:

{
  "apiKey": "${AI_API_KEY}",
  "chatModelName": "mistral-large-latest",
  "fieldsToExtract": "employeeName,employeeId,department,position,startDate,salary,contractType",
  "outputJsonSchema": "{\"type\":\"object\",\"required\":[\"employeeName\",\"employeeId\",\"department\",\"position\",\"startDate\",\"contractType\"],\"properties\":{\"employeeName\":{\"type\":\"string\"},\"employeeId\":{\"type\":\"string\"},\"department\":{\"type\":\"string\"},\"position\":{\"type\":\"string\"},\"startDate\":{\"type\":\"string\"},\"salary\":{\"type\":\"number\"},\"contractType\":{\"type\":\"string\"}}}"
}

Expected output:

{
  "employeeName": "Marie Dupont",
  "employeeId": "EMP-2026-0042",
  "department": "Engineering",
  "position": "Senior Developer",
  "startDate": "2026-02-01",
  "salary": 55000,
  "contractType": "CDI"
}

Classify support tickets by department

Automatically route incoming support tickets to the correct department using Mistral classification.

Process flow:

  1. A support ticket is submitted through a Bonita form or email integration

  2. A service task uses the Classify connector to determine the department

  3. An exclusive gateway routes the ticket based on classification

  4. Each department queue receives only relevant tickets

Configuration:

{
  "apiKey": "${AI_API_KEY}",
  "chatModelName": "mistral-large-latest",
  "categories": "BILLING,TECHNICAL_SUPPORT,ACCOUNT_MANAGEMENT,FEATURE_REQUEST,SECURITY_INCIDENT,OTHER"
}

Expected output:

{
  "category": "TECHNICAL_SUPPORT",
  "confidence": 0.91
}

Use the result in an exclusive gateway:

  • category == "BILLING" → Finance department

  • category == "TECHNICAL_SUPPORT" → IT support team

  • category == "SECURITY_INCIDENT" → Security team (high priority)

  • Default → General support queue

Generate regulatory compliance reports

Use the Ask operation to generate structured compliance reports from audit findings.

Configuration:

{
  "apiKey": "${AI_API_KEY}",
  "chatModelName": "mistral-large-latest",
  "systemPrompt": "You are a regulatory compliance officer. Generate structured compliance reports from audit data. Be precise and reference specific regulations.",
  "userPrompt": "Generate a GDPR compliance summary for department ${departmentName} based on the following audit findings: ${auditFindings}",
  "outputJsonSchema": "{\"type\":\"object\",\"required\":[\"department\",\"complianceScore\",\"findings\",\"recommendations\"],\"properties\":{\"department\":{\"type\":\"string\"},\"complianceScore\":{\"type\":\"number\"},\"findings\":{\"type\":\"array\",\"items\":{\"type\":\"object\",\"required\":[\"area\",\"status\",\"details\"],\"properties\":{\"area\":{\"type\":\"string\"},\"status\":{\"type\":\"string\"},\"details\":{\"type\":\"string\"}}}},\"recommendations\":{\"type\":\"array\",\"items\":{\"type\":\"string\"}}}}"
}

Expected output:

{
  "department": "Human Resources",
  "complianceScore": 72,
  "findings": [
    {
      "area": "Data Retention",
      "status": "non-compliant",
      "details": "Employee records retained beyond the 5-year maximum without documented justification."
    },
    {
      "area": "Consent Management",
      "status": "compliant",
      "details": "All data processing activities have documented legal basis and consent records."
    }
  ],
  "recommendations": [
    "Implement automated data retention policies with expiration alerts",
    "Conduct quarterly reviews of retained employee data"
  ]
}

Configuration tips

  • Mistral provides EU data residency by default — ideal for organizations subject to GDPR and EU data sovereignty requirements.

  • Use mistral-small-latest for simple classification tasks to minimize costs.

  • For production workloads, prefer mistral-large-latest for the best quality.

  • Image document processing is not currently supported through the connector library. Use text-based documents or consider another provider for image analysis.

Source code

bonita-connector-ai on GitHub (module bonita-connector-ai-mistral)