Search - Wood Wide AI Documentation

Search models build an index over the training data at training time. At inference time, each row in the inference data is matched to the most semantically similar row in the training dataset. This is useful for finding nearest-neighbor matches, deduplication, record linkage, or recommendation systems.

Training

Training embeds the entire training dataset and builds a nearest-neighbor index over those embeddings. No label_column is needed. No validation metrics are computed for search models.

Search is not available in the Python SDK yet. Use the HTTP examples below.

import os, time, requests

api_key = os.getenv("WOODWIDE_API_KEY")
base_url = "https://api.woodwide.ai"
headers = {"Authorization": f"Bearer {api_key}"}

# Upload the dataset to search against
with open("catalog.csv", "rb") as f:
    resp = requests.post(
        f"{base_url}/datasets",
        headers=headers,
        files={"file": ("catalog.csv", f, "text/csv")},
        data={"dataset_name": "product_catalog"},
    )
dataset_id = resp.json()["dataset"]["id"]

# Train a search model
resp = requests.post(
    f"{base_url}/models/train",
    headers=headers,
    json={
        "model_name": "catalog_search",
        "model_type": "search",
        "dataset_id": dataset_id,
    },
)
model_id = resp.json()["model"]["id"]

# Wait for training
while True:
    model = requests.get(
        f"{base_url}/models/{model_id}", headers=headers
    ).json()
    if model["status"] == "ready":
        break
    time.sleep(5)

const fs = require("fs");
const FormData = require("form-data");

const apiKey = process.env.WOODWIDE_API_KEY;
const baseUrl = "https://api.woodwide.ai";
const headers = { Authorization: `Bearer ${apiKey}` };

// Upload the dataset to search against
const uploadForm = new FormData();
uploadForm.append("file", fs.createReadStream("catalog.csv"), "catalog.csv");
uploadForm.append("dataset_name", "product_catalog");

const uploadResp = await fetch(`${baseUrl}/datasets`, {
  method: "POST",
  headers: { ...headers, ...uploadForm.getHeaders() },
  body: uploadForm,
});
const { dataset: { id: datasetId } } = await uploadResp.json();

// Train a search model
const trainResp = await fetch(`${baseUrl}/models/train`, {
  method: "POST",
  headers: { ...headers, "Content-Type": "application/json" },
  body: JSON.stringify({
    model_name: "catalog_search",
    model_type: "search",
    dataset_id: datasetId,
  }),
});
const { model: { id: modelId } } = await trainResp.json();

// Wait for training
while (true) {
  const modelResp = await fetch(`${baseUrl}/models/${modelId}`, { headers });
  const model = await modelResp.json();
  if (model.status === "ready") break;
  await new Promise((r) => setTimeout(r, 5000));
}

export WOODWIDE_API_KEY="your_api_key_here"
export BASE_URL="https://api.woodwide.ai"

# Upload the dataset to search against
DATASET_ID=$(curl -s -X POST "$BASE_URL/datasets" \
  -H "Authorization: Bearer $WOODWIDE_API_KEY" \
  -F "file=@catalog.csv" \
  -F "dataset_name=product_catalog" | jq -r '.dataset.id')

# Train a search model
MODEL_ID=$(curl -s -X POST "$BASE_URL/models/train" \
  -H "Authorization: Bearer $WOODWIDE_API_KEY" \
  -H "Content-Type: application/json" \
  -d "{
    \"model_name\": \"catalog_search\",
    \"model_type\": \"search\",
    \"dataset_id\": \"$DATASET_ID\"
  }" | jq -r '.model.id')

# Wait for training
while true; do
  STATUS=$(curl -s "$BASE_URL/models/$MODEL_ID" \
    -H "Authorization: Bearer $WOODWIDE_API_KEY" | jq -r '.status')

  if [ "$STATUS" = "ready" ]; then break; fi
  if [ "$STATUS" = "failed" ]; then echo "Training failed."; exit 1; fi

  sleep 5
done

Inference

Provide a CSV of query rows. For each query row, the model returns the row ID of the closest match in the training dataset.

# Find the closest catalog item for each query
with open("queries.csv", "rb") as f:
    resp = requests.post(
        f"{base_url}/models/{model_id}/infer",
        headers=headers,
        files={"file": ("queries.csv", f, "text/csv")},
        data={"output_type": "json"},
    )

results = resp.json()["data"]
print(results)

// Find the closest catalog item for each query
const form = new FormData();
form.append("file", fs.createReadStream("queries.csv"), "queries.csv");
form.append("output_type", "json");

const resp = await fetch(`${baseUrl}/models/${modelId}/infer`, {
  method: "POST",
  headers: { ...headers, ...form.getHeaders() },
  body: form,
});

const { data: results } = await resp.json();
console.log(results);

curl -s -X POST "$BASE_URL/models/$MODEL_ID/infer" \
  -H "Authorization: Bearer $WOODWIDE_API_KEY" \
  -F "file=@queries.csv" \
  -F "output_type=json" | jq '.data'

See Output Formats for the full output schema.

⌘I