sparkient-edge 0.1.0

Sub-10ms local decisions from Sparkient edge bundles — zero cloud dependencies

sparkient-edge

Sub-10ms local decisions from Sparkient edge bundles — zero cloud dependencies.

Train your decision model on Sparkient, export an edge bundle, and run predictions locally with no network, no database, and no API calls.

Quick Start

pip install sparkient-edge

from sparkient_edge import EdgePredictor

# Load a bundle exported from the Sparkient dashboard or API
predictor = EdgePredictor.from_bundle("my_decision_type.zip")

# Make a local decision — sub-10ms, no network
result = predictor.predict({
    "amount": 750,
    "account_age_days": 45,
    "risk_score": 0.55,
})

print(result.decision)            # "review"
print(result.confidence)          # 0.9985
print(result.stage)               # "classifier"
print(result.class_probabilities) # {"approve": 0.0006, "review": 0.9985, "block": 0.0009}

How It Works

1. Export an edge bundle from Sparkient (dashboard or GET /api/v1/decision-types/{id}/export)
2. Load the bundle with EdgePredictor.from_bundle("path/to/bundle.zip")
3. Predict with predictor.predict(your_input) — runs CEL rules then ONNX classifier locally

The bundle contains everything needed: an ONNX model, feature configuration, CEL rules, and metadata. Typical bundle size is 1–10 KB.

Optional Dependencies

The base install includes only onnxruntime and numpy. Install extras for additional features:

pip install sparkient-edge[all]    # Everything
pip install sparkient-edge[rules]  # CEL rule evaluation
pip install sparkient-edge[text]   # Text field embeddings (model2vec)
pip install sparkient-edge[mcp]    # MCP server support

Extra	Adds	When needed
rules	cel-expr-python	Decision types with CEL hard rules
text	model2vec	Decision types with free-text input fields
mcp	mcp	Running as a local MCP server
all	All of the above	Recommended for full functionality

MCP Server

Run as a local Model Context Protocol server for AI assistant integration:

sparkient-edge                    # Uses the CLI entry point
python -m sparkient_edge          # Or run as a module

Add to your MCP client config (Claude Desktop, Cursor, etc.):

{
  "mcpServers": {
    "sparkient-edge": {
      "command": "sparkient-edge",
      "args": []
    }
  }
}

EdgeDecision Fields

Field	Type	Description
decision	str	The chosen outcome (e.g., "approve")
confidence	float	Confidence score (0.0 to 1.0)
reason_codes	list[str]	Why this decision was made
stage	str	Which stage decided: "rules", "classifier", or "fallback"
class_probabilities	dict[str, float]	Probability for each option
rules_triggered	list[str]	Names of rules that fired

Links

• Documentation
• Sparkient Platform
• API Reference