8fe5e62fee
Some checks failed
CI/CD Pipeline / Code Quality & Linting (push) Has been cancelled
CI/CD Pipeline / Policy Validation (push) Has been cancelled
CI/CD Pipeline / Test Suite (push) Has been cancelled
CI/CD Pipeline / Build Docker Images (svc-coverage) (push) Has been cancelled
CI/CD Pipeline / Build Docker Images (svc-extract) (push) Has been cancelled
CI/CD Pipeline / Build Docker Images (svc-firm-connectors) (push) Has been cancelled
CI/CD Pipeline / Build Docker Images (svc-forms) (push) Has been cancelled
CI/CD Pipeline / Build Docker Images (svc-hmrc) (push) Has been cancelled
CI/CD Pipeline / Build Docker Images (svc-ingestion) (push) Has been cancelled
CI/CD Pipeline / Build Docker Images (svc-kg) (push) Has been cancelled
CI/CD Pipeline / Build Docker Images (svc-normalize-map) (push) Has been cancelled
CI/CD Pipeline / Build Docker Images (svc-ocr) (push) Has been cancelled
CI/CD Pipeline / Build Docker Images (svc-rag-indexer) (push) Has been cancelled
CI/CD Pipeline / Build Docker Images (svc-rag-retriever) (push) Has been cancelled
CI/CD Pipeline / Build Docker Images (svc-reason) (push) Has been cancelled
CI/CD Pipeline / Build Docker Images (svc-rpa) (push) Has been cancelled
CI/CD Pipeline / Build Docker Images (ui-review) (push) Has been cancelled
CI/CD Pipeline / Security Scanning (svc-coverage) (push) Has been cancelled
CI/CD Pipeline / Security Scanning (svc-extract) (push) Has been cancelled
CI/CD Pipeline / Security Scanning (svc-kg) (push) Has been cancelled
CI/CD Pipeline / Security Scanning (svc-rag-retriever) (push) Has been cancelled
CI/CD Pipeline / Security Scanning (ui-review) (push) Has been cancelled
CI/CD Pipeline / Generate SBOM (push) Has been cancelled
CI/CD Pipeline / Deploy to Staging (push) Has been cancelled
CI/CD Pipeline / Deploy to Production (push) Has been cancelled
CI/CD Pipeline / Notifications (push) Has been cancelled
352 lines
12 KiB
JSON
352 lines
12 KiB
JSON
{
|
|
"collections": [
|
|
{
|
|
"name": "firm_knowledge",
|
|
"description": "Internal firm procedures, templates, and client-specific knowledge",
|
|
"dense": {
|
|
"size": 1024,
|
|
"distance": "Cosine"
|
|
},
|
|
"sparse": true,
|
|
"payload_schema": {
|
|
"type": "object",
|
|
"properties": {
|
|
"document_id": { "type": "string" },
|
|
"document_type": {
|
|
"type": "string",
|
|
"enum": ["procedure", "template", "memo", "guidance"]
|
|
},
|
|
"title": { "type": "string" },
|
|
"content": { "type": "string" },
|
|
"chunk_index": { "type": "integer" },
|
|
"total_chunks": { "type": "integer" },
|
|
"jurisdiction": { "type": "string", "enum": ["UK", "US", "EU"] },
|
|
"tax_years": { "type": "array", "items": { "type": "string" } },
|
|
"topic_tags": { "type": "array", "items": { "type": "string" } },
|
|
"client_types": {
|
|
"type": "array",
|
|
"items": {
|
|
"type": "string",
|
|
"enum": ["individual", "partnership", "company", "trust"]
|
|
}
|
|
},
|
|
"practice_areas": { "type": "array", "items": { "type": "string" } },
|
|
"version": { "type": "string" },
|
|
"created_at": { "type": "string", "format": "date-time" },
|
|
"updated_at": { "type": "string", "format": "date-time" },
|
|
"author": { "type": "string" },
|
|
"review_status": {
|
|
"type": "string",
|
|
"enum": ["draft", "reviewed", "approved", "archived"]
|
|
},
|
|
"access_level": {
|
|
"type": "string",
|
|
"enum": ["public", "internal", "restricted", "confidential"]
|
|
},
|
|
"pii_free": { "type": "boolean", "const": true },
|
|
"source_url": { "type": "string" },
|
|
"page_numbers": { "type": "array", "items": { "type": "integer" } },
|
|
"section_hierarchy": {
|
|
"type": "array",
|
|
"items": { "type": "string" }
|
|
},
|
|
"has_calculations": { "type": "boolean" },
|
|
"has_forms": { "type": "boolean" },
|
|
"confidence_score": { "type": "number", "minimum": 0, "maximum": 1 }
|
|
},
|
|
"required": [
|
|
"document_id",
|
|
"document_type",
|
|
"content",
|
|
"jurisdiction",
|
|
"pii_free"
|
|
]
|
|
},
|
|
"indexing_config": {
|
|
"replication_factor": 2,
|
|
"write_consistency_factor": 1,
|
|
"on_disk_payload": true,
|
|
"hnsw_config": {
|
|
"m": 16,
|
|
"ef_construct": 100,
|
|
"full_scan_threshold": 10000
|
|
},
|
|
"quantization_config": {
|
|
"scalar": {
|
|
"type": "int8",
|
|
"quantile": 0.99,
|
|
"always_ram": true
|
|
}
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"name": "legislation",
|
|
"description": "Tax legislation, regulations, and official guidance",
|
|
"dense": {
|
|
"size": 1024,
|
|
"distance": "Cosine"
|
|
},
|
|
"sparse": true,
|
|
"payload_schema": {
|
|
"type": "object",
|
|
"properties": {
|
|
"document_id": { "type": "string" },
|
|
"document_type": {
|
|
"type": "string",
|
|
"enum": ["act", "regulation", "guidance", "case_law", "circular"]
|
|
},
|
|
"title": { "type": "string" },
|
|
"content": { "type": "string" },
|
|
"chunk_index": { "type": "integer" },
|
|
"total_chunks": { "type": "integer" },
|
|
"jurisdiction": { "type": "string" },
|
|
"effective_from": { "type": "string", "format": "date" },
|
|
"effective_to": { "type": "string", "format": "date" },
|
|
"tax_years": { "type": "array", "items": { "type": "string" } },
|
|
"legislation_reference": { "type": "string" },
|
|
"section_number": { "type": "string" },
|
|
"subsection_number": { "type": "string" },
|
|
"topic_tags": { "type": "array", "items": { "type": "string" } },
|
|
"form_references": { "type": "array", "items": { "type": "string" } },
|
|
"calculation_methods": {
|
|
"type": "array",
|
|
"items": { "type": "string" }
|
|
},
|
|
"thresholds": { "type": "array", "items": { "type": "object" } },
|
|
"rates": { "type": "array", "items": { "type": "object" } },
|
|
"deadlines": {
|
|
"type": "array",
|
|
"items": { "type": "string", "format": "date" }
|
|
},
|
|
"version": { "type": "string" },
|
|
"source_authority": {
|
|
"type": "string",
|
|
"enum": ["HMRC", "Parliament", "Courts", "Treasury"]
|
|
},
|
|
"pii_free": { "type": "boolean", "const": true },
|
|
"source_url": { "type": "string" },
|
|
"page_numbers": { "type": "array", "items": { "type": "integer" } },
|
|
"cross_references": {
|
|
"type": "array",
|
|
"items": { "type": "string" }
|
|
},
|
|
"amendments": { "type": "array", "items": { "type": "object" } },
|
|
"precedence_level": { "type": "integer", "minimum": 1, "maximum": 10 }
|
|
},
|
|
"required": [
|
|
"document_id",
|
|
"document_type",
|
|
"content",
|
|
"jurisdiction",
|
|
"effective_from",
|
|
"pii_free"
|
|
]
|
|
},
|
|
"indexing_config": {
|
|
"replication_factor": 3,
|
|
"write_consistency_factor": 2,
|
|
"on_disk_payload": true,
|
|
"hnsw_config": {
|
|
"m": 32,
|
|
"ef_construct": 200,
|
|
"full_scan_threshold": 20000
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"name": "best_practices",
|
|
"description": "Industry best practices, professional standards, and methodologies",
|
|
"dense": {
|
|
"size": 1024,
|
|
"distance": "Cosine"
|
|
},
|
|
"sparse": true,
|
|
"payload_schema": {
|
|
"type": "object",
|
|
"properties": {
|
|
"document_id": { "type": "string" },
|
|
"document_type": {
|
|
"type": "string",
|
|
"enum": [
|
|
"standard",
|
|
"guideline",
|
|
"methodology",
|
|
"checklist",
|
|
"workflow"
|
|
]
|
|
},
|
|
"title": { "type": "string" },
|
|
"content": { "type": "string" },
|
|
"chunk_index": { "type": "integer" },
|
|
"total_chunks": { "type": "integer" },
|
|
"jurisdiction": { "type": "string" },
|
|
"applicable_years": {
|
|
"type": "array",
|
|
"items": { "type": "string" }
|
|
},
|
|
"topic_tags": { "type": "array", "items": { "type": "string" } },
|
|
"practice_areas": { "type": "array", "items": { "type": "string" } },
|
|
"complexity_level": {
|
|
"type": "string",
|
|
"enum": ["basic", "intermediate", "advanced", "expert"]
|
|
},
|
|
"client_types": { "type": "array", "items": { "type": "string" } },
|
|
"professional_body": {
|
|
"type": "string",
|
|
"enum": ["ICAEW", "ACCA", "CIOT", "ATT", "STEP"]
|
|
},
|
|
"version": { "type": "string" },
|
|
"last_reviewed": { "type": "string", "format": "date" },
|
|
"review_frequency": {
|
|
"type": "string",
|
|
"enum": ["annual", "biannual", "as_needed"]
|
|
},
|
|
"pii_free": { "type": "boolean", "const": true },
|
|
"source_url": { "type": "string" },
|
|
"related_forms": { "type": "array", "items": { "type": "string" } },
|
|
"risk_level": {
|
|
"type": "string",
|
|
"enum": ["low", "medium", "high", "critical"]
|
|
},
|
|
"automation_suitable": { "type": "boolean" },
|
|
"quality_score": { "type": "number", "minimum": 0, "maximum": 1 }
|
|
},
|
|
"required": [
|
|
"document_id",
|
|
"document_type",
|
|
"content",
|
|
"jurisdiction",
|
|
"pii_free"
|
|
]
|
|
},
|
|
"indexing_config": {
|
|
"replication_factor": 2,
|
|
"write_consistency_factor": 1,
|
|
"on_disk_payload": true,
|
|
"hnsw_config": {
|
|
"m": 16,
|
|
"ef_construct": 100,
|
|
"full_scan_threshold": 10000
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"name": "glossary",
|
|
"description": "Tax terminology, definitions, and concept explanations",
|
|
"dense": {
|
|
"size": 768,
|
|
"distance": "Cosine"
|
|
},
|
|
"sparse": true,
|
|
"payload_schema": {
|
|
"type": "object",
|
|
"properties": {
|
|
"document_id": { "type": "string" },
|
|
"document_type": { "type": "string", "const": "definition" },
|
|
"term": { "type": "string" },
|
|
"definition": { "type": "string" },
|
|
"content": { "type": "string" },
|
|
"chunk_index": { "type": "integer" },
|
|
"total_chunks": { "type": "integer" },
|
|
"jurisdiction": { "type": "string" },
|
|
"applicable_years": {
|
|
"type": "array",
|
|
"items": { "type": "string" }
|
|
},
|
|
"category": {
|
|
"type": "string",
|
|
"enum": [
|
|
"tax_concept",
|
|
"legal_term",
|
|
"accounting_term",
|
|
"form_field",
|
|
"calculation_method"
|
|
]
|
|
},
|
|
"complexity_level": {
|
|
"type": "string",
|
|
"enum": ["basic", "intermediate", "advanced"]
|
|
},
|
|
"synonyms": { "type": "array", "items": { "type": "string" } },
|
|
"related_terms": { "type": "array", "items": { "type": "string" } },
|
|
"form_references": { "type": "array", "items": { "type": "string" } },
|
|
"legislation_references": {
|
|
"type": "array",
|
|
"items": { "type": "string" }
|
|
},
|
|
"examples": { "type": "array", "items": { "type": "string" } },
|
|
"version": { "type": "string" },
|
|
"source_authority": { "type": "string" },
|
|
"pii_free": { "type": "boolean", "const": true },
|
|
"source_url": { "type": "string" },
|
|
"usage_frequency": {
|
|
"type": "string",
|
|
"enum": ["common", "occasional", "rare", "obsolete"]
|
|
},
|
|
"definition_quality": { "type": "number", "minimum": 0, "maximum": 1 }
|
|
},
|
|
"required": [
|
|
"document_id",
|
|
"term",
|
|
"definition",
|
|
"content",
|
|
"jurisdiction",
|
|
"category",
|
|
"pii_free"
|
|
]
|
|
},
|
|
"indexing_config": {
|
|
"replication_factor": 2,
|
|
"write_consistency_factor": 1,
|
|
"on_disk_payload": true,
|
|
"hnsw_config": {
|
|
"m": 16,
|
|
"ef_construct": 100,
|
|
"full_scan_threshold": 5000
|
|
}
|
|
}
|
|
}
|
|
],
|
|
"global_config": {
|
|
"default_segment_number": 4,
|
|
"max_segment_size_kb": 1048576,
|
|
"memmap_threshold_kb": 1048576,
|
|
"indexing_threshold_kb": 20480,
|
|
"payload_storage_type": "on_disk",
|
|
"enable_payload_index": true,
|
|
"wal_config": {
|
|
"wal_capacity_mb": 32,
|
|
"wal_segments_ahead": 0
|
|
},
|
|
"optimizer_config": {
|
|
"deleted_threshold": 0.2,
|
|
"vacuum_min_vector_number": 1000,
|
|
"default_segment_number": 0,
|
|
"max_segment_size_kb": 1048576,
|
|
"memmap_threshold_kb": 1048576,
|
|
"indexing_threshold_kb": 20480,
|
|
"flush_interval_sec": 5,
|
|
"max_optimization_threads": 1
|
|
}
|
|
},
|
|
"backup_config": {
|
|
"enabled": true,
|
|
"schedule": "0 2 * * *",
|
|
"retention_days": 30,
|
|
"compression": true,
|
|
"verify_integrity": true
|
|
},
|
|
"monitoring": {
|
|
"metrics_enabled": true,
|
|
"log_level": "INFO",
|
|
"telemetry_disabled": false,
|
|
"performance_tracking": {
|
|
"track_search_latency": true,
|
|
"track_indexing_throughput": true,
|
|
"track_memory_usage": true,
|
|
"track_disk_usage": true
|
|
}
|
|
}
|
|
}
|