Create a Prompt

You are a document classification expert.

Analyze the following document and classify it as exactly one of:
{{CATEGORIES}}

Document filename: {{FILENAME}}

Rules:
1. Respond with ONLY the document type label.
2. Do not include any explanation or punctuation.
3. If the document does not match any category, respond with "unknown".

POST /prompts
Authorization: Bearer <your-jwt-token>
Content-Type: multipart/form-data

Query parameters:
- name: "Invoice Classification"  (required)
- description: "Classifies documents as invoices"  (optional)
- scope: "tenant"  (optional, default: "tenant")
- purpose: "classification"  (optional, for model-aware resolution)
- model_affinity: "gemini_3"  (optional, null = universal)

Form fields:
- prompt_file: invoice_classification.txt

curl -X POST "https://api.bizsupply.ai/prompts?name=Invoice%20Classification&description=Classifies%20documents%20as%20invoices&scope=tenant" \
  -H "Authorization: Bearer YOUR_JWT_TOKEN" \
  -F "prompt_file=@invoice_classification.txt"

="color:#5c6370;font-style:italic"># Gemini 3 variant
curl -X POST "https://api.bizsupply.ai/prompts?name=Classification%20(Gemini%203)&purpose=classification&model_affinity=gemini_3&scope=global" \
  -H "Authorization: Bearer YOUR_JWT_TOKEN" \
  -F "prompt_file=@classification_gemini3.txt"

="color:#5c6370;font-style:italic"># Gemini 2 variant (same purpose, different affinity)
curl -X POST "https://api.bizsupply.ai/prompts?name=Classification%20(Gemini%202)&purpose=classification&model_affinity=gemini_2&scope=global" \
  -H "Authorization: Bearer YOUR_JWT_TOKEN" \
  -F "prompt_file=@classification_gemini2.txt"

{
  "prompt_id": "550e8400-e29b-41d4-a716-446655440000"
}

GET /prompts
Authorization: Bearer <your-jwt-token>

{
  "count": 1,
  "prompts": [
    {
      "prompt_id": "550e8400-e29b-41d4-a716-446655440000",
      "name": "Invoice Classification",
      "description": "Classifies documents as invoices",
      "scope": "tenant",
      "purpose": "classification",
      "model_affinity": "gemini_3",
      "created_at": "2025-01-12T10: 00: 00Z",
      "updated_at": "2025-01-12T10: 00: 00Z"
    }
  ]
}

from bizsupply_sdk import ClassificationPlugin, ConfigurableParameter


class FinancialClassifier(ClassificationPlugin):
    """Classifies documents using a platform-managed prompt."""

    configurable_parameters = [
        ConfigurableParameter(
            parameter_name="classification_prompt_id",
            parameter_type="str",
            default_value=None,
            description="Prompt ID for classification instructions",
        ),
    ]

    async def classify(
        self, document, file_data, mime_type, available_labels, current_path, configs
    ) -> str | None:
        # Resolve the prompt ID from the runtime configuration
        prompt_id = configs.get("classification_prompt_id")

        # Load the template (model-affinity variant resolved automatically)
        template = await self.get_prompt(prompt_id)

        # Substitute placeholders with runtime values
        prompt = template.replace(
            "{{CATEGORIES}}",
            "\n".join(f"- {label}" for label in available_labels),
        ).replace(
            "{{FILENAME}}",
            document.filename,
        )

        # The LLM reads the attached file bytes directly
        result = await self.prompt_llm(
            prompt=prompt,
            file_data=file_data,
            mime_type=mime_type,
        )

        if not isinstance(result, dict):
            return None

        label = result.get("label")
        return label if label in available_labels else None

{
  "plugin_id": "your-plugin-id",
  "plugin_configs": {
    "classification_prompt_id": "550e8400-e29b-41d4-a716-446655440000"
  }
}

GET /prompts/{prompt_id}
Authorization: Bearer <your-jwt-token>

PATCH /prompts/{prompt_id}
Authorization: Bearer <your-jwt-token>
Content-Type: multipart/form-data

Query parameters (all optional):
- name: "New Name"
- description: "New description"
- purpose: "classification"   (use null to clear)
- model_affinity: "gemini_3"  (use null to clear, omit to keep unchanged)

Form fields (optional):
- prompt_file: updated_prompt.txt

DELETE /prompts/{prompt_id}
Authorization: Bearer <your-jwt-token>

You are a document classification expert.

Analyze the following document and classify it as exactly one of:
{{CATEGORIES}}

Document filename: {{FILENAME}}

Respond with ONLY a JSON object: {"label": "...", "confidence": 0.0-1.0}.

You are a document extraction expert.

Extract the following fields from this {{DOCUMENT_TYPE}} document:
{{FIELDS}}

Rules:
1. Return ONLY a JSON object with the field names as keys.
2. For each field, include a {field_name}_confidence key with a value from 0.0 to 1.0.
3. If a field cannot be found, set its value to null.
4. For date fields, use ISO 8601 format (YYYY-MM-DD).
5. For number fields, return raw numbers without currency symbols or commas.

You are a contract analysis expert specializing in {{CONTRACT_TYPE}} agreements.

Analyze the following contract and extract:
{{FIELDS}}

Pay special attention to:
- Renewal clauses and auto-renewal terms
- Termination conditions and notice periods
- Pricing escalation clauses
- Liability caps and indemnification

Return a JSON object with the extracted fields, plus a "risk_flags" array listing any concerning clauses.