gtMay16

Pipeline-Centric UI All operations moved to Pipeline tab

Domain

Recreation

Backend

Elasticsearch

LLM

gpt-4o-mini

text-embedding-3-small

Features

Spatial Incremental

KB Backend

Embedding Model

LLM Model

Chat Name

Dataset ID

Chat ID

Similarity Threshold

Keywords Weight

Primary Domain

Secondary Domains

Hold Ctrl/Cmd to select multiple

Spatial

City/state resolution

Input Guardrails (trigger words → action)

Output Guardrails (checks → actions)

KB Website URLs (one per line)

Structured Data Sources

class_schedule

Unstructured Sources 1

Name

Source Type

Location

Entity Types

Scrape Depth

Enrichment Model

Batch Size

Facility Data

Booking URL

Booking Provider

Chunk Tokens

Top-K / Top-N

Structured Data Sources 1

Name

Data Path

Entity Label

Max Results

Trigger Tags (comma-separated)

Param Scope (comma-separated)

Items Key

Details Key

Require params

Filters (10 defined)

{
  "client": "gtMay16",
  "output_dir": "output_gtMay16",
  "season_mappings": {
    "Spring 2026": {
      "start": "2026-01-12",
      "end": "2026-05-01"
    },
    "Spring": {
      "start": "2026-01-12",
      "end": "2026-05-01"
    },
    "Summer 2026": {
      "start": "2026-05-19",
      "end": "2026-08-08"
    },
    "Summer": {
      "start": "2026-05-19",
      "end": "2026-08-08"
    },
    "Fall 2025": {
      "start": "2025-08-18",
      "end": "2025-12-12"
    },
    "Fall": {
      "start": "2025-08-18",
      "end": "2025-12-12"
    },
    "Winter 2026": {
      "start": "2026-01-05",
      "end": "2026-01-11"
    }
  },
  "embedding": {
    "model": "text-embedding-3-small",
    "dimensions": 1536
  },
  "es": {
    "kb_index": "gtmay16-kb"
  },
  "extraction": {
    "model": "claude-haiku-4-5-20251001",
    "max_tokens_per_chunk": 1200,
    "discover_schema": true
  },
  "enrichment": {
    "model": "claude-haiku-4-5-20251001",
    "taxonomy_model": "claude-sonnet-4-20250514",
    "batch_size": 5,
    "cluster_chunks": true,
    "restriction_chunks": true,
    "comparison_chunks": true,
    "policy_chain_chunks": true,
    "eligibility_chunks": true
  },
  "eval": {
    "analysis_model": "claude-sonnet-4-20250514",
    "eval_model": "claude-haiku-4-5-20251001",
    "max_iterations": 5,
    "delay": 1,
    "index_wait": 10,
    "confidence_threshold": 0.6
  },
  "structured_data": [
    {
      "name": "class_schedule",
      "path": "output_gtMay16/structured/classes.json",
      "entity_label": "programs",
      "detail_label": "sections",
      "priority_fields": [
        "price",
        "availability",
        "schedule",
        "times",
        "dates",
        "spots"
      ],
      "param_scope": [
        "keyword",
        "category",
        "day",
        "time_after",
        "time_before",
        "max_price",
        "min_price",
        "available",
        "location",
        "instructor"
      ],
      "trigger_tags": [
        "aquatics_programs",
        "outdoor_recreation",
        "fitness_wellness",
        "certification_training",
        "group_activities",
        "specialty_services"
      ],
      "trigger_entity_types": [
        "Program"
      ],
      "stale_hours": 9000000,
      "scraper": {
        "adapter": "innosoft",
        "url": "https://mycrc.gatech.edu"
      },
      "schema": {
        "category_field": "classification",
        "keyword_fields": [
          "name",
          "description"
        ],
        "items_key": "programs",
        "details_key": "sections",
        "timestamp_key": "scraped_at",
        "filters": {
          "category": {
            "path": "classification",
            "match": "substring"
          },
          "keyword": {
            "paths": [
              "name",
              "description"
            ],
            "match": "substring"
          },
          "day": {
            "detail_path": "days",
            "match": "contains"
          },
          "time_after": {
            "detail_path": "time_start",
            "match": "gte"
          },
          "time_before": {
            "detail_path": "time_start",
            "match": "lte"
          },
          "max_price": {
            "path": "price_min",
            "match": "lte"
          },
          "min_price": {
            "path": "price_min",
            "match": "gte"
          },
          "available": {
            "detail_path": "spots_available",
            "match": "gt0"
          },
          "location": {
            "detail_path": "location",
            "match": "substring"
          },
          "instructor": {
            "detail_path": "instructor",
            "match": "substring"
          }
        }
      }
    }
  ],
  "unstructured_data": [
    {
      "name": "park_documents",
      "source_type": "file_path",
      "location": "output_gtMay16/unstructured",
      "entity_types": [
        "Park",
        "Facility",
        "Program",
        "Activity",
        "Organization",
        "Person"
      ]
    }
  ],
  "spatial": {
    "enabled": true,
    "data_source": "pipeline/spatial_data/national/us_cities.json",
    "resolve_cities": true
  },
  "genclair": {
    "enabled": true
  },
  "validation": {
    "enabled": true
  },
  "domain": "recreation",
  "kb_backend": "elasticsearch",
  "track": "structured",
  "_track_note": "Set to 'structured' during Day 3 migration (2026-05-24). apply_track_defaults() fills any unspecified keys at load time. Adjust via UI track-selector or by editing this field."
}

🚪 Pipeline Stage Gates

🎮 Pipeline Controls

⚙️ Advanced Options

Force re-run completed stages

Start from stage:

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

No documents selected

Domain Profile recreation

Entity Types (8)

Program A class, lesson, course, or structured activity

Facility A building, room, pool, court, or gym space

Policy A rule, requirement, restriction, or access policy

Fee A price, membership fee, or registration cost

Contact A phone number, email, office, or staff person

Person A person type or group (member, guest, minor, senior, alumni

Amenity Equipment, gear, or service available at a facility

Schedule Operating hours, class times, or semester dates

Relationships (12)

COSTS Entity has a fee or price

LOCATED_IN Entity is at a location or facility

OFFERS Facility or organization offers a program or servi

OFFERS_ACTIVITY Entity offers a specific activity

ELIGIBLE_FOR Person type is eligible for a program or facility

GOVERNED_BY Entity is subject to a policy or rule

REQUIRES Entity requires a prerequisite, certification, or

CONTACTS_VIA Entity can be reached through a contact method

CONTAINS Facility contains a sub-facility or amenity

HAS_AMENITY Facility has an amenity or feature

RESTRICTS Policy restricts or prohibits an action

HAS_SCHEDULE Entity operates on a schedule or time period

Enrichment

Generate Comparison Chunks

Generate Eligibility Matrix

Generate Restriction Summary

Generate Policy Chains

Safety Critical

5 question templates

Guardrails

1 input checks

2 output checks

1 data checks

Step 0: Scrape ? Pending

Site Scrape

No scraped pages yet.

Class Scrape

No class data yet.

Scraper: https://mycrc.gatech.edu (innosoft)

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

Upload Documents

File	Status	Processed	Steps

Entities & Relationships

Entity Roles

-

Core

-

Supporting

-

Noise

-

Uncertain

Domain - Core Types -

Entity	Type	Role	Score	Cluster	Compare	QA	Heal	Reason

Suppression Log

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

Entity	Type	Role	Blocked From	Reason

Test Questions

Test File

Test History

Latest Results

Run Eval & Patch

Full Loop

Failures Only

Test File

Max Iterations

ES backend — no Chat ID or Dataset ID needed. Eval uses config settings automatically.

Admin Review Queue

No pending review items.

Scheduled Operations

Enable Scheduled Ops

Scrape Interval (hours)

Test Interval (hours)

Auto-eval on failures

Alert on regression

Alert Threshold (score drop)

Test File

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/gtMay16/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

class_schedule unknown

No risk report available. Run the pipeline to generate failure predictions.

Claude Console

Ask a question to analyze KB coverage, suggest fixes, or explain chunk content.

Pipeline UI

gtMay16

Backend & Retrieval

Domain & Scope

Guardrails Domain defaults

Data Sources 1 structured

Unstructured Data Sources Documents, files, content

Pipeline Settings

gtMay16 — config.json

🚪 Pipeline Stage Gates

🎮 Pipeline Controls

⚙️ Advanced Options

🚀 Pipeline Execution

Status

Outputs

Process Output

Foundation Review

Status

Zones Discovered

Discovery Progress

Discovered Zones

Selected Documents

Entity Types (8)

Relationships (12)

Enrichment

Guardrails

Site Scrape

Class Scrape

Document Registry

-

-

-

Entities & Relationships

Entity Types

Filter

Entities

Relationships

Entity Roles

-

-

-

-

Suppression Log

Test Questions

Generated Questions

Test History

Test Output

Latest Results

Pipeline Control Center

Data Sources Configuration

Structured Data

Unstructured Data

RootFinder Setup

GenClair Discovery

Extract Data

Foundation & Discovery

Build & Validate

Domain & Policies

Index & Test

Healing

Run Eval & Patch

Admin Review Queue

Scheduled Operations

Cron Setup

Pipeline Log

Query Traces 0

Repair Ledger 0

System Health