Token Classification (NER)

This cookbook walks through building, deploying, and using a Named Entity Recognition (NER) model with Encoderfile. We'll use BERT fine-tuned for NER to identify people, organizations, and locations in text.

What You'll Learn

• Export a token classification model to ONNX

• Build a self-contained encoderfile binary

• Deploy as a REST API server

• Make predictions via HTTP

• Use CLI for batch processing

Prerequisites

• encoderfile CLI tool installed (Installation Guide)

• Python with optimum[exporters] for ONNX export

• curl for testing the API

---

Step 1: Export the Model

We'll use dslim/bert-base-NER, a BERT model fine-tuned for named entity recognition.

About the Model

This model recognizes 4 entity types:

• PER - Person names

• ORG - Organizations

• LOC - Locations

• MISC - Miscellaneous entities

Export to ONNX

# Install optimum if you haven't already
pip install optimum[exporters]

# Export the model
optimum-cli export onnx \
  --model dslim/bert-base-NER \
  --task token-classification \
  ./ner-model

What files are created?

The export creates:

ner-model/
├── config.json          # Model configuration
├── model.onnx          # ONNX weights
├── tokenizer.json      # Fast tokenizer
├── tokenizer_config.json
└── special_tokens_map.json

---

Step 2: Create Configuration

Create a YAML configuration file for building the encoderfile.

ner-config.yml

encoderfile:
  name: ner-tagger
  version: "1.0.0"
  path: ./ner-model
  model_type: token_classification
  output_path: ./build/ner-tagger.encoderfile

With Optional Transform

Configuration Options

• name - Model identifier used in API responses

• path - Directory containing ONNX model files

• model_type - Must be token_classification for NER

• output_path - Where to save the binary (optional)

• transform - Optional Lua script for post-processing

---

Step 3: Build the Binary

Build your self-contained encoderfile binary:

# Create output directory
mkdir -p build

# Build the encoderfile
encoderfile build -f ner-config.yml

Build Output

You should see output like:

Validating model...
Generating project...
Compiling binary...
✓ Build complete: ./build/ner-tagger.encoderfile

The resulting binary is completely self-contained - it includes:

• ONNX model weights

• Tokenizer

• Full inference runtime

• REST and gRPC servers

---

Step 4: Start the Server

Launch the encoderfile server:

# Make executable (if needed)
chmod +x ./build/ner-tagger.encoderfile

# Start server
./build/ner-tagger.encoderfile serve

Server Startup

Starting HTTP server on 0.0.0.0:8080
Starting gRPC server on [::]:50051
Model: ner-tagger v1.0.0

The server is now running with both HTTP and gRPC endpoints.

---

Step 5: Make Predictions

Now let's test the NER model with different types of text.

Example 1: Basic Entity Recognition

Request

curl -X POST http://localhost:8080/predict \
  -H "Content-Type: application/json" \
  -d '{
    "inputs": ["Mozilla is headquartered in San Fancisco, CA"]
  }'

Expected Response

Interpretation

Example 2: Multiple Sentences

Request

curl -X POST http://localhost:8080/predict \
  -H "Content-Type: application/json" \
  -d '{
    "inputs": [
      "Yvon Chouinard founded Patagonia in 1957.",
      "The Eiffel Tower is located in Paris, France."
    ]
  }'

Expected Entities

Step 6: CLI Inference

For batch processing or one-off predictions, use the CLI directly:

Single Input

./build/ner-tagger.encoderfile infer \
  "Tim Cook presented the new iPhone at Apple Park in California."

Batch Processing

./build/ner-tagger.encoderfile infer \
  "Amazon was founded by Jeff Bezos in Seattle." \
  "Mozilla's headquarters are in San Francisco, California." \
  "Marie Curie won the Nobel Prize in Physics." \
  -o results.json

This saves all results to results.json for further processing.

---

Advanced Usage

Custom Ports

./build/ner-tagger.encoderfile serve \
  --http-port 3000 \
  --grpc-port 50052

HTTP Only (Disable gRPC)

./build/ner-tagger.encoderfile serve --disable-grpc

Production Deployment

# Copy to system location
sudo cp ./build/ner-tagger.encoderfile /usr/local/bin/

# Run as a service (example with systemd)
/usr/local/bin/ner-tagger.encoderfile serve \
  --http-hostname 0.0.0.0 \
  --http-port 8080

---

Understanding the Output

Token Classification Labels

The model uses the IOB (Inside-Outside-Beginning) tagging scheme:

Prefix	Meaning	Example
B-	Beginning of entity	B-PER for "Barack" in "Barack Obama"
I-	Inside/continuation	I-PER for "Obama" in "Barack Obama"
O	Outside any entity	O for "is" or "the"

Entity Types

Label	Description	Examples
PER	Person names	"John Smith", "Marie Curie"
ORG	Organizations	"Apple Inc.", "United Nations"
LOC	Locations	"Paris", "California", "Mount Everest"
MISC	Miscellaneous	"iPhone", "Nobel Prize"

Response Format

{
  "results": [
    {
      "tokens": ["word1", "word2", ...],          // Tokenized input
      "logits": [[...], [...], ...],              // Raw model outputs
      "predicted_labels": ["B-PER", "O", ...]     // Predicted entity tags
    }
  ],
  "model_id": "ner-tagger"
}

---

Troubleshooting

Unexpected Entity Recognition

Model Limitations

The model may struggle with:

• Rare or domain-specific entities

• Ambiguous contexts (e.g., "Washington" as person vs. location)

• Non-English text

• Very long sequences (>512 tokens)

Solution: Fine-tune on domain-specific data or use a specialized model.

Performance Optimization

If inference is slow:

# Consider adding a transform to reduce output size
transform: |
  function Postprocess(arr)
    -- Only return top prediction per token
    return arr:argmax(3)
  end

Server Connection Issues

# Check if server is running
curl http://localhost:8080/health

# Try different port
./build/ner-tagger.encoderfile serve --http-port 8081

---

Next Steps

• Transforms Guide - Learn about custom post-processing with Lua scripts

• Transforms Reference - Complete transforms API documentation

• API Reference - REST, gRPC, and MCP endpoint specifications

• CLI Reference - Full documentation for build, serve, and infer commands

---

Summary

You've learned to:

• ✅ Export a token classification model to ONNX

• ✅ Build a self-contained encoderfile binary

• ✅ Deploy as a REST API server

• ✅ Make predictions via HTTP and CLI

• ✅ Understand NER output format

The encoderfile you built is production-ready and can be deployed anywhere without dependencies!