igel-qe-core 1.0.5 → 1.0.8

package/knowledge_base/config/.env.example

@@ -1,75 +0,0 @@
-# IGEL EKG Knowledge Base — environment template
-# Copy to knowledge_base/config/.env and fill in values
-
-# PostgreSQL
-DB_HOST=192.168.204.65
-DB_PORT=5432
-DB_NAME=genai
-DB_USER=genai
-DB_PASSWORD=CHANGE_ME
-DB_SSLMODE=prefer
-
-# Azure OpenAI
-AZURE_API_KEY=CHANGE_ME
-AZURE_ENDPOINT=https://your-endpoint.cognitiveservices.azure.com/
-AZURE_DEPLOYMENT=gpt-4.1
-AZURE_EMBEDDING_DEPLOYMENT=text-embedding-3-large
-EMBEDDING_DIM=3072
-
-# API Security (Phase C)
-API_KEY_REQUIRED=true
-API_KEY=CHANGE_ME_ADMIN_KEY
-API_KEYS=read_key:read,write_key:write,admin_key:admin
-RATE_LIMIT_ENABLED=true
-JSON_LOGS=true
-
-# Retrieval (Phase D)
-FTS_LANGUAGE=english
-REDIS_URL=redis://localhost:6379/0
-EMBED_CACHE_TTL=3600
-RETRIEVAL_CACHE_TTL=300
-QUERY_TIMEOUT_SECONDS=60
-QUERY_GENERATION_TIMEOUT_SECONDS=90
-ASYNC_THREAD_LIMIT=16
-QUERY_EXTERNAL_ENABLED=true
-QUERY_MCP_SOURCES=jira,confluence
-WEB_RETRIEVAL_ENABLED=true
-CONFIDENCE_THRESHOLD=0.75
-WEB_SEARCH_BACKENDS=firecrawl,ddgs,searxng
-WEB_MAX_PAGES=5
-WEB_ALLOW_PRIVATE_HOSTS=false
-FIRECRAWL_BASE_URL=http://127.0.0.1:3002
-FIRECRAWL_API_KEY=
-CRAWL4AI_ENABLED=true
-CRAWL4AI_TIMEOUT=30
-DDGS_BACKEND=auto
-DDGS_REGION=wt-wt
-SEARXNG_BASE_URL=
-STRIP_PROMOTED_PATTERNS=ad,sponsored,promo,advertisement
-WEB_SEARCH_INCLUDE_DOMAINS=
-WEB_SEARCH_EXCLUDE_DOMAINS=
-
-# Connectors (Phase F)
-JIRA_ENABLED=false
-JIRA_URL=
-JIRA_USERNAME=
-JIRA_API_TOKEN=
-CONFLUENCE_ENABLED=false
-CONFLUENCE_URL=
-CONFLUENCE_USERNAME=
-CONFLUENCE_API_TOKEN=
-
-# Agentic pipeline
-AGENTIC_ENABLED=true
-EVAL_ENABLED=true
-CONFIDENCE_REJECT_THRESHOLD=0.4
-CONFIDENCE_WARN_THRESHOLD=0.6
-
-# Generation A/B (Phase I)
-DEFAULT_GENERATION_MODE=pipeline
-
-# Reranker (CPU)
-RERANKER_BACKEND=local
-RERANKER_DEVICE=cpu
-RERANKER_MODEL=cross-encoder/ms-marco-MiniLM-L-6-v2
-CHUNK_CHILD_MAX_TOKENS=220

package/knowledge_base/connectors/bitbucket_connector.py

@@ -1,25 +0,0 @@
-"""Bitbucket connector — Phase 8 stub."""
-from __future__ import annotations
-
-from datetime import datetime
-
-from knowledge_base.config import cfg
-from knowledge_base.connectors.base import BaseConnector
-
-
-class BitbucketConnector(BaseConnector):
-    name = "bitbucket"
-    enabled = cfg.BITBUCKET_ENABLED
-    supports_sync = False
-
-    def connect(self) -> bool:
-        return self.enabled
-
-    def sync(self, since: datetime | None = None) -> list[dict]:
-        return []
-
-    def ingest_to_kg(self, items: list[dict]) -> int:
-        return 0
-
-    def ingest_to_rag(self, items: list[dict]) -> int:
-        return 0

package/knowledge_base/db/migrations.py

@@ -1,22 +0,0 @@
-"""Run Alembic migrations programmatically."""
-
-from __future__ import annotations
-
-import logging
-from pathlib import Path
-
-from alembic import command
-from alembic.config import Config
-
-logger = logging.getLogger(__name__)
-
-
-def run_migrations(revision: str = "head") -> None:
-    """Apply Alembic migrations up to revision (default: head)."""
-    alembic_ini = Path(__file__).resolve().parent.parent.parent / "alembic.ini"
-    if not alembic_ini.exists():
-        logger.warning("alembic.ini not found at %s — skipping migrations", alembic_ini)
-        return
-    alembic_cfg = Config(str(alembic_ini))
-    command.upgrade(alembic_cfg, revision)
-    logger.info("Alembic migrations applied: %s", revision)

package/knowledge_base/ingestion/ingest.py

@@ -1,346 +0,0 @@
-"""
-IGEL Knowledge Base — Document Ingestion Pipeline
-==================================================
-Usage:
-  python -m knowledge_base.ingestion.ingest               # Ingest all new documents
-  python -m knowledge_base.ingestion.ingest --file x.pdf  # Single file
-  python -m knowledge_base.ingestion.ingest --reset       # Drop + rebuild schema, then ingest all
-  python -m knowledge_base.ingestion.ingest --dry-run     # Parse + chunk without writing to DB
-  python -m knowledge_base.ingestion.ingest --stats       # Show DB statistics and exit
-"""
-from __future__ import annotations
-import argparse
-import hashlib
-import logging
-import sys
-import time
-from pathlib import Path
-
-from rich.console import Console
-from rich.progress import Progress, SpinnerColumn, TextColumn, BarColumn, TaskProgressColumn, TimeElapsedColumn
-from rich.table import Table
-
-from knowledge_base.config import cfg
-from knowledge_base.db.client import init_pool, test_connection, close_pool
-from knowledge_base.db.schema import (
-    create_schema, drop_schema, document_exists,
-    get_stats, ingest_document_atomic,
-)
-from knowledge_base.parsers.pdf_parser import parse_pdf
-from knowledge_base.parsers.markdown_parser import parse_markdown_file
-from knowledge_base.parsers.doc_parser import parse_doc
-from knowledge_base.parsers.csv_parser import parse_csv
-from knowledge_base.chunking.chunker import chunk_sections
-from knowledge_base.chunking.validators import detect_product
-from knowledge_base.embeddings.azure_embedder import embed_texts, format_for_pgvector
-from knowledge_base.ingestion.kg_extractor import extract_for_document
-
-console = Console()
-logging.basicConfig(level=getattr(logging, cfg.LOG_LEVEL), format="%(levelname)s %(message)s")
-logger = logging.getLogger(__name__)
-
-
-# ── File discovery ────────────────────────────────────────────────────────────
-
-def discover_files(kb_dir: Path, single_file: str | None = None) -> list[Path]:
-    if single_file:
-        p = kb_dir / single_file
-        if not p.exists():
-            console.print(f"[red]File not found: {p}[/red]")
-            sys.exit(1)
-        return [p]
-
-    files = []
-    for f in sorted(kb_dir.iterdir()):
-        if not f.is_file():
-            continue
-        if f.name.startswith("~$") or f.name.startswith("."):
-            continue
-        if f.suffix.lower() in cfg.SUPPORTED_EXTENSIONS:
-            files.append(f)
-    return files
-
-
-def file_hash(path: Path) -> str:
-    h = hashlib.md5()
-    with open(path, "rb") as f:
-        for block in iter(lambda: f.read(65536), b""):
-            h.update(block)
-    return h.hexdigest()
-
-
-# ── Parsing dispatcher ────────────────────────────────────────────────────────
-
-def parse_file(path: Path) -> tuple[list, str]:
-    """Returns (sections, parse_method_label)."""
-    suffix = path.suffix.lower()
-
-    if suffix == ".pdf":
-        return parse_pdf(path, cfg.MARKDOWN_OUTPUT_DIR)
-
-    if suffix == ".md":
-        return parse_markdown_file(path), "markdown"
-
-    if suffix in (".doc", ".docx"):
-        return parse_doc(path), "docx"
-
-    if suffix in (".csv", ".xlsx", ".xls"):
-        return parse_csv(path), "csv"
-
-    if suffix == ".mht":
-        return _parse_mht(path), "mht"
-
-    raise ValueError(f"No parser for: {suffix}")
-
-
-def _parse_mht(path: Path) -> list:
-    """MHT = MIME HTML archive — extract readable text."""
-    from knowledge_base.parsers.markdown_parser import Section
-    import re
-
-    raw = path.read_bytes().decode("utf-8", errors="replace")
-    # Strip MIME headers and HTML tags
-    text = re.sub(r"<[^>]+>", " ", raw)
-    text = re.sub(r"&[a-z]+;", " ", text)
-    text = re.sub(r"\s{3,}", "\n\n", text).strip()
-    return [Section(title=path.stem, level=0, content=text)]
-
-
-# ── Core ingestion ────────────────────────────────────────────────────────────
-
-def ingest_file(path: Path, dry_run: bool = False, skip_kg: bool = False) -> dict:
-    result = {
-        "file": path.name,
-        "status": "ok",
-        "parse_method": "?",
-        "parents": 0,
-        "chunks": 0,
-        "kg_nodes": 0,
-        "kg_edges": 0,
-        "warnings": 0,
-        "validation_skipped": 0,
-        "skipped": False,
-        "error": None,
-        "elapsed": 0.0,
-    }
-    t0 = time.time()
-
-    try:
-        if path.name.startswith("~$") or path.name.startswith("."):
-            result["status"] = "skipped"
-            result["skipped"] = True
-            return result
-
-        # Deduplication check — re-ingest if prior run left an empty document
-        fhash = file_hash(path)
-        existing_id: str | None = None
-        if not dry_run:
-            existing_id = document_exists(fhash)
-            if existing_id:
-                from knowledge_base.db.schema import clear_document_chunks, document_has_chunks
-                if document_has_chunks(existing_id):
-                    result["status"] = "skipped"
-                    result["skipped"] = True
-                    return result
-                logger.warning("Re-ingesting %s (previous ingest had 0 chunks)", path.name)
-                clear_document_chunks(existing_id)
-
-        # Parse
-        sections, parse_method = parse_file(path)
-        result["parse_method"] = parse_method
-
-        if not sections:
-            result["status"] = "empty"
-            return result
-
-        # Chunk
-        product = detect_product("", path.name)
-        parents, warnings = chunk_sections(sections, path.name, product)
-        result["parents"] = len(parents)
-        result["warnings"] = len(warnings)
-
-        if warnings:
-            for w in warnings[:5]:   # log first 5 to avoid noise
-                logger.warning(w)
-
-        if dry_run:
-            total_children = sum(len(p.children) for p in parents)
-            result["chunks"] = total_children
-            return result
-
-        doc_id, parent_count, total_children, validation_skipped = ingest_document_atomic(
-            file_name=path.name,
-            file_path=str(path),
-            file_type=path.suffix.lower().lstrip("."),
-            file_hash=fhash,
-            product=product,
-            doc_metadata={"parse_method": parse_method, "section_count": len(sections)},
-            parents=parents,
-            existing_id=existing_id,
-            embed_fn=embed_texts,
-            format_fn=format_for_pgvector,
-            batch_size=cfg.BATCH_SIZE,
-        )
-        result["validation_skipped"] = validation_skipped
-        result["chunks"] = total_children
-
-        if not skip_kg:
-            try:
-                kg_n, kg_e = extract_for_document(doc_id)
-                result["kg_nodes"] = kg_n
-                result["kg_edges"] = kg_e
-            except Exception as kg_err:
-                logger.warning("KG extraction failed for %s: %s", path.name, kg_err)
-
-    except Exception as e:
-        result["status"] = "error"
-        result["error"] = str(e)
-        logger.exception("Failed to ingest %s", path.name)
-
-    result["elapsed"] = round(time.time() - t0, 1)
-    return result
-
-
-# ── Main ──────────────────────────────────────────────────────────────────────
-
-def main():
-    parser = argparse.ArgumentParser(description="IGEL Knowledge Base Ingestion Pipeline")
-    parser.add_argument("--file", type=str, help="Ingest a single file by name")
-    parser.add_argument("--reset", action="store_true", help="Drop and recreate schema before ingesting")
-    parser.add_argument("--dry-run", action="store_true", help="Parse + chunk without writing to DB")
-    parser.add_argument("--skip-kg", action="store_true", help="Skip knowledge graph extraction after ingestion")
-    parser.add_argument("--enrich-orphans", action="store_true", help="Run LLM KG enrichment on orphan parent chunks")
-    parser.add_argument("--stats", action="store_true", help="Print knowledge base statistics and exit")
-    args = parser.parse_args()
-
-    console.rule("[bold blue]IGEL Knowledge Base Ingestion Pipeline[/bold blue]")
-    console.print(f"  KB directory : {cfg.KB_DIR}")
-    console.print(f"  Database     : {cfg.DB_HOST}:{cfg.DB_PORT}/{cfg.DB_NAME}")
-    console.print(f"  Embeddings   : {cfg.AZURE_EMBEDDING_DEPLOYMENT} ({cfg.EMBEDDING_DIM}d)")
-    console.print(f"  Dry run      : {args.dry_run}")
-    console.print(f"  KG sync      : {'disabled' if args.skip_kg else 'automatic'}")
-    console.print()
-
-    if not args.dry_run:
-        console.print("[bold]Connecting to PostgreSQL...[/bold]")
-        init_pool()
-        if not test_connection():
-            console.print("[red]Cannot connect to database. Check .env settings.[/red]")
-            sys.exit(1)
-
-    if args.enrich_orphans and not args.dry_run:
-        from knowledge_base.ingestion.kg_extractor import enrich_orphan_parents
-        console.print("[bold]Enriching orphan parent chunks with LLM KG extraction...[/bold]")
-        init_pool()
-        n, e = enrich_orphan_parents(limit=500)
-        console.print(f"  Enriched: {n} nodes, {e} edges")
-        close_pool()
-        return
-
-    if args.stats:
-        stats = get_stats()
-        t = Table(title="Knowledge Base Statistics")
-        t.add_column("Metric")
-        t.add_column("Value", justify="right")
-        for k, v in stats.items():
-            t.add_row(k.replace("_", " ").title(), str(v))
-        console.print(t)
-        close_pool()
-        return
-
-    if args.reset and not args.dry_run:
-        console.print("[yellow]Resetting schema (drop + recreate)...[/yellow]")
-        drop_schema()
-
-    if not args.dry_run:
-        console.print("[bold]Initializing schema...[/bold]")
-        create_schema()
-
-    files = discover_files(cfg.KB_DIR, args.file)
-    console.print(f"\nFound [bold]{len(files)}[/bold] files to process\n")
-
-    results = []
-
-    with Progress(
-        SpinnerColumn(),
-        TextColumn("[progress.description]{task.description}"),
-        BarColumn(),
-        TaskProgressColumn(),
-        TimeElapsedColumn(),
-        console=console,
-    ) as progress:
-        task = progress.add_task("Ingesting...", total=len(files))
-
-        for path in files:
-            progress.update(task, description=f"[cyan]{path.name[:50]}[/cyan]")
-            r = ingest_file(path, dry_run=args.dry_run, skip_kg=args.skip_kg)
-            results.append(r)
-            progress.advance(task)
-
-    # ── Summary ───────────────────────────────────────────────────────────────
-    console.print()
-    console.rule("[bold green]Ingestion Complete[/bold green]")
-
-    summary = Table(title="Results Summary")
-    summary.add_column("File", style="cyan", max_width=45)
-    summary.add_column("Status", justify="center")
-    summary.add_column("Method")
-    summary.add_column("Parents", justify="right")
-    summary.add_column("Chunks", justify="right")
-    summary.add_column("KG", justify="right")
-    summary.add_column("Warnings", justify="right")
-    summary.add_column("Time(s)", justify="right")
-
-    ok = skipped = errors = total_parents = total_chunks = total_kg_nodes = total_kg_edges = 0
-    for r in results:
-        if r["skipped"]:
-            skipped += 1
-            status_str = "[yellow]SKIP[/yellow]"
-        elif r["status"] == "error":
-            errors += 1
-            status_str = f"[red]ERROR[/red]"
-        elif r["status"] == "empty":
-            status_str = "[dim]EMPTY[/dim]"
-        else:
-            ok += 1
-            status_str = "[green]OK[/green]"
-
-        total_parents += r["parents"]
-        total_chunks += r["chunks"]
-        total_kg_nodes += r.get("kg_nodes", 0)
-        total_kg_edges += r.get("kg_edges", 0)
-
-        kg_cell = f"{r.get('kg_nodes', 0)}n/{r.get('kg_edges', 0)}e" if r.get("kg_nodes") else ""
-        summary.add_row(
-            r["file"],
-            status_str,
-            r["parse_method"],
-            str(r["parents"]),
-            str(r["chunks"]),
-            kg_cell,
-            str(r["warnings"]) if r["warnings"] else "",
-            str(r["elapsed"]),
-        )
-
-    console.print(summary)
-    console.print()
-    console.print(f"  Processed : [green]{ok}[/green]  |  Skipped: [yellow]{skipped}[/yellow]  |  Errors: [red]{errors}[/red]")
-    console.print(f"  Total parent chunks : {total_parents}")
-    console.print(f"  Total child chunks  : {total_chunks} (these are vector-indexed)")
-    if total_kg_nodes or total_kg_edges:
-        console.print(f"  KG sync             : {total_kg_nodes} node ops, {total_kg_edges} edges created")
-
-    if not args.dry_run:
-        stats = get_stats()
-        console.print(f"\n  DB totals → docs: {stats['documents']}  |  parents: {stats['parent_chunks']}  |  chunks: {stats['chunks']}")
-        if stats["missing_embeddings"] > 0:
-            console.print(f"  [yellow]Warning: {stats['missing_embeddings']} chunks have no embedding[/yellow]")
-        close_pool()
-
-    if errors > 0:
-        console.print(f"\n[red]{errors} file(s) failed — check logs above for details[/red]")
-        sys.exit(1)
-
-
-if __name__ == "__main__":
-    main()