ecommerce

Pipeline-Centric UI All operations moved to Pipeline tab
Domain
Ecommerce
Backend
Elasticsearch
triplets-ecommerce
LLM
gpt-4o-mini
text-embedding-3-small
Features
Incremental

Hold Ctrl/Cmd to select multiple

product_catalog

Unstructured Sources 0
No unstructured data sources configured

Structured Data Sources 1
Filters (5 defined)

🚪 Pipeline Stage Gates

🎮 Pipeline Controls

⚙️ Advanced Options

Systematic Foundation Discovery Step 0

RootFinder analyzes your document corpus to discover foundational types, tier assignments, and protected documents before extraction begins. This ensures proper ontology alignment.

Status
Not Started
No foundation analysis performed
Outputs
No outputs generated
GenClair Zone Discovery Step 1

GenClair analyzes your document corpus to discover knowledge zones using embedding clustering and domain-fit validation. This creates zone boundaries for focused extraction.

Status
Not Started
No zone discovery performed
Zones Discovered
0
No documents selected
Domain Profile ecommerce
Entity Types (10)
Product A product, item, or SKU for sale
Variant A size, color, style, or configuration option of a product
Category A product category or department
Brand A manufacturer or brand name
Policy A return, shipping, warranty, or store policy
Fee A price, shipping cost, tax, or surcharge
Promotion A sale, discount, coupon, or special offer
Review A customer review, rating, or feedback summary
Attribute A product characteristic such as dimensions, weight, materia
Inventory Stock status, quantity available, or warehouse location
Relationships (12)
COSTS Product has a price or price range
BELONGS_TO Product belongs to a category
MADE_BY Product is manufactured or sold by a brand
SHIPS_TO Product ships to a region or country
GOVERNED_BY Product or order is subject to a policy
COMPATIBLE_WITH Product is compatible with or works with another p
HAS_VARIANT Product has size, color, style, or configuration v
QUALIFIES_FOR Product qualifies for a promotion or discount
HAS_ATTRIBUTE Product has a specific measurable attribute or spe
IN_STOCK Product has available inventory at a location or f
SIMILAR_TO Product is functionally similar or frequently comp
REVIEWED_AS Product received a review, rating, or customer ver
Enrichment
Generate Comparison Chunks
Generate Eligibility Matrix
Generate Restriction Summary
Generate Policy Chains
Safety Critical
10 question templates
Guardrails
0 input checks
1 output checks
1 data checks
Step 0: Scrape ? Pending
Site Scrape

No scraped pages yet.

Class Scrape

No class data yet.

Step 1: Extract ? Pending

No extraction data yet. Run pipeline Step 1 (extract).

Step 2: Build ? Pending

No build data yet. Run pipeline Step 2 (build).

Step 3: Enrich ? Pending

No enrichment data yet. Run pipeline Step 3 (enrich).

Step 4: Policies ? Pending

No policy data yet. Run pipeline Step 4 (policies).

Step 5: Lookups ? Pending

No lookup data yet. Run pipeline Step 5 (lookups).

Steps 6-8: Upload / Parse / Configure ? Pending

Not uploaded yet. Run pipeline Steps 6-8 (upload/parse/configure).


Document Registry
Click to load document status

-

Total Tracked

-

New

-

Changed
FileStatusProcessedSteps
Entities & Relationships

Entity Roles

-

Core

-

Supporting

-

Noise

-

Uncertain
Domain - Core Types -
Entity Type Role Score ClusterCompareQAHeal Reason
Suppression Log

Entities blocked from one or more synthesis steps. All remain searchable via retrieval.

EntityTypeRoleBlocked FromReason
Test Questions
Test History
Latest Results

Pipeline Control Center

Manage pipeline execution, monitor progress, and control operations

Ready
Never
Pipeline Operations
Data Sources Configuration
Structured Data
product_catalog
Path: output_ecommerce/products.json
Type: Products data
Unstructured Data
No unstructured data sources configured
RootFinder Setup
Ready
Foundation discovery
393 total documents
1 structured (classes.json)
392 unstructured (.txt files)
Est. ~30 seconds
Outputs: 393 doc analysis
GenClair Discovery
Ready
Zone boundaries
RootFinder outputs ready
Est. ~2-3 minutes
Cost: ~$0.15 embeddings
Outputs: Zone manifest
Extract Data
Waiting
Extract entities & relationships
Needs GenClair zones
Est. ~5-10 minutes
Cost: ~$4.20 LLM calls
Outputs: Entity triplets
Pipeline Flow & Status
Overall Progress 0% Complete
Foundation & Discovery
RootFinder (Steps 0.10-0.55):
Source Intake
Pending
Doc Identity
Pending
Ontology Input
Pending
Tier Assignment
Pending
Schema Discovery
Pending
Roots Lock
Pending
GenClair
Pending
Extract
Pending
Promote
Pending
Build & Validate
Canonical
Pending
Build
Pending
Validate Facts
Pending
Enrich
Pending
Domain & Policies
Domain Enrich
Pending
Policies
Pending
Lookups
Pending
Upload
Pending
Index & Test
Index ES
Pending
Auto Tests
Pending
Test
Pending
Evaluate
Pending
Healing
Grader
Pending
Diagnosis
Pending
Heal
Pending
Execution Console
[System] Pipeline console ready. Select an operation to begin.
Run Eval & Patch
ES backend — no Chat ID or Dataset ID needed. Eval uses config settings automatically.
Admin Review Queue

No pending review items.

Scheduled Operations
ES backend — IDs not needed
Cron Setup

Add this line to your crontab (crontab -e):

0 */12 * * * cd /path/to/project && python pipeline/scheduled_ops.py --config clients/ecommerce/config.json
Pipeline Log

No pipeline log found.

Query Traces 0

No query traces found. Traces are captured when questions are routed through the RetrievalRouter.

Repair Ledger 0

No repair ledger entries. Run Eval & Patch to populate.

System Health
Repair Stats
Total repairs0
Positive0
Negative0
Neutral0
Query Performance
Traces captured0
Avg latency0ms
Data Freshness
product_catalog unknown
No risk report available. Run the pipeline to generate failure predictions.