neuer Importer mit eigenem Service
This commit is contained in:
1 parent
62aa24a4bc
commit
865b261294
2 files changed
+309
-575
No files matched your search
@@ -0,0 +1,264 @@
|
||||
"""
|
||||
app/core/ingestion.py
|
||||
|
||||
Zentraler Service für die Transformation von Markdown-Dateien in Qdrant-Objekte (Notes, Chunks, Edges).
|
||||
Dient als Shared Logic für:
|
||||
1. CLI-Imports (scripts/import_markdown.py)
|
||||
2. API-Uploads (WP-11)
|
||||
"""
|
||||
import os
|
||||
import json
|
||||
from typing import Dict, List, Optional, Tuple, Any, Set
|
||||
|
||||
from app.core.parser import (
|
||||
read_markdown,
|
||||
normalize_frontmatter,
|
||||
validate_required_frontmatter,
|
||||
)
|
||||
from app.core.note_payload import make_note_payload
|
||||
from app.core.chunker import assemble_chunks
|
||||
from app.core.chunk_payload import make_chunk_payloads
|
||||
# Fallback Imports wie im Original-Skript
|
||||
try:
|
||||
from app.core.derive_edges import build_edges_for_note
|
||||
except ImportError:
|
||||
from app.core.edges import build_edges_for_note # type: ignore
|
||||
|
||||
from app.core.qdrant import QdrantConfig, get_client, ensure_collections, ensure_payload_indexes
|
||||
from app.core.qdrant_points import (
|
||||
points_for_chunks,
|
||||
points_for_note,
|
||||
points_for_edges,
|
||||
upsert_batch,
|
||||
)
|
||||
|
||||
# Optionales Embedding
|
||||
try:
|
||||
from app.core.embed import embed_texts
|
||||
except ImportError:
|
||||
embed_texts = None
|
||||
|
||||
# --- Helper für Type-Registry (ausgelagert aus Script) ---
|
||||
def load_type_registry(custom_path: Optional[str] = None) -> dict:
|
||||
import yaml
|
||||
path = custom_path or os.getenv("MINDNET_TYPES_FILE", "config/types.yaml")
|
||||
if not os.path.exists(path):
|
||||
# Fallback auf Root-Ebene (für Tests/CLI)
|
||||
if os.path.exists("types.yaml"):
|
||||
path = "types.yaml"
|
||||
else:
|
||||
return {}
|
||||
try:
|
||||
with open(path, "r", encoding="utf-8") as f:
|
||||
return yaml.safe_load(f) or {}
|
||||
except Exception:
|
||||
return {}
|
||||
|
||||
def resolve_note_type(requested: Optional[str], reg: dict) -> str:
|
||||
types = reg.get("types", {})
|
||||
if requested and requested in types:
|
||||
return requested
|
||||
return "concept" # Default Fallback
|
||||
|
||||
def effective_chunk_profile(note_type: str, reg: dict) -> str:
|
||||
# 1. Specific Type
|
||||
t_cfg = reg.get("types", {}).get(note_type, {})
|
||||
if t_cfg and t_cfg.get("chunk_profile"):
|
||||
return t_cfg.get("chunk_profile")
|
||||
# 2. Defaults
|
||||
return reg.get("defaults", {}).get("chunk_profile", "default")
|
||||
|
||||
def effective_retriever_weight(note_type: str, reg: dict) -> float:
|
||||
t_cfg = reg.get("types", {}).get(note_type, {})
|
||||
if t_cfg and "retriever_weight" in t_cfg:
|
||||
return float(t_cfg["retriever_weight"])
|
||||
return float(reg.get("defaults", {}).get("retriever_weight", 1.0))
|
||||
|
||||
|
||||
class IngestionService:
|
||||
def __init__(self, collection_prefix: str = "mindnet"):
|
||||
self.prefix = collection_prefix
|
||||
self.cfg = QdrantConfig.from_env()
|
||||
self.cfg.prefix = collection_prefix # Override env if needed
|
||||
self.client = get_client(self.cfg)
|
||||
self.dim = self.cfg.dim
|
||||
|
||||
# Registry laden
|
||||
self.registry = load_type_registry()
|
||||
|
||||
# Init DB Checks
|
||||
ensure_collections(self.client, self.prefix, self.dim)
|
||||
ensure_payload_indexes(self.client, self.prefix)
|
||||
|
||||
def process_file(
|
||||
self,
|
||||
file_path: str,
|
||||
vault_root: str,
|
||||
force_replace: bool = False,
|
||||
apply: bool = False,
|
||||
purge_before: bool = False,
|
||||
note_scope_refs: bool = False,
|
||||
hash_mode: str = "body",
|
||||
hash_source: str = "parsed",
|
||||
hash_normalize: str = "canonical"
|
||||
) -> Dict[str, Any]:
|
||||
"""
|
||||
Verarbeitet eine einzelne Datei.
|
||||
Return: Summary Dict (Erfolg, Änderungen, Stats).
|
||||
"""
|
||||
result = {
|
||||
"path": file_path,
|
||||
"status": "skipped",
|
||||
"changed": False,
|
||||
"error": None
|
||||
}
|
||||
|
||||
# 1. Parse & Frontmatter
|
||||
try:
|
||||
parsed = read_markdown(file_path)
|
||||
if not parsed:
|
||||
return {**result, "error": "Empty or unreadable file"}
|
||||
|
||||
fm = normalize_frontmatter(parsed.frontmatter)
|
||||
validate_required_frontmatter(fm)
|
||||
except Exception as e:
|
||||
return {**result, "error": f"Validation failed: {str(e)}"}
|
||||
|
||||
# 2. Type & Config Resolution
|
||||
note_type = resolve_note_type(fm.get("type"), self.registry)
|
||||
fm["type"] = note_type
|
||||
fm["chunk_profile"] = effective_chunk_profile(note_type, self.registry)
|
||||
|
||||
# Weight Resolution (Frontmatter override > Registry)
|
||||
weight = fm.get("retriever_weight")
|
||||
if weight is None:
|
||||
weight = effective_retriever_weight(note_type, self.registry)
|
||||
fm["retriever_weight"] = float(weight)
|
||||
|
||||
# 3. Build Note Payload
|
||||
try:
|
||||
note_pl = make_note_payload(
|
||||
parsed,
|
||||
vault_root=vault_root,
|
||||
hash_mode=hash_mode,
|
||||
hash_normalize=hash_normalize,
|
||||
hash_source=hash_source,
|
||||
file_path=file_path
|
||||
)
|
||||
# Ensure fulltext & weight
|
||||
if not note_pl.get("fulltext"):
|
||||
note_pl["fulltext"] = getattr(parsed, "body", "") or ""
|
||||
note_pl["retriever_weight"] = fm["retriever_weight"]
|
||||
|
||||
note_id = note_pl["note_id"]
|
||||
except Exception as e:
|
||||
return {**result, "error": f"Payload build failed: {str(e)}"}
|
||||
|
||||
# 4. Change Detection (Hash Check)
|
||||
# Wir holen den alten Payload aus Qdrant, wenn wir nicht forcen
|
||||
old_payload = None
|
||||
if not force_replace:
|
||||
old_payload = self._fetch_note_payload(note_id)
|
||||
|
||||
has_old = old_payload is not None
|
||||
key_current = f"{hash_mode}:{hash_source}:{hash_normalize}"
|
||||
|
||||
old_hash = (old_payload or {}).get("hashes", {}).get(key_current)
|
||||
new_hash = note_pl.get("hashes", {}).get(key_current)
|
||||
|
||||
hash_changed = (old_hash != new_hash)
|
||||
|
||||
# Artefakte prüfen (Chunks/Edges)
|
||||
chunks_missing, edges_missing = self._artifacts_missing(note_id)
|
||||
|
||||
should_write = force_replace or (not has_old) or hash_changed or chunks_missing or edges_missing
|
||||
|
||||
if not should_write:
|
||||
return {**result, "status": "unchanged", "note_id": note_id}
|
||||
|
||||
if not apply:
|
||||
return {**result, "status": "dry-run", "changed": True, "note_id": note_id}
|
||||
|
||||
# 5. Processing (Chunking, Embedding, Edges)
|
||||
try:
|
||||
body_text = getattr(parsed, "body", "") or ""
|
||||
chunks = assemble_chunks(fm["id"], body_text, fm["type"])
|
||||
chunk_pls = make_chunk_payloads(fm, note_pl["path"], chunks, note_text=body_text)
|
||||
|
||||
# Embeddings
|
||||
vecs = []
|
||||
if embed_texts and chunk_pls:
|
||||
texts = [c.get("window") or c.get("text") or "" for c in chunk_pls]
|
||||
vecs = embed_texts(texts)
|
||||
else:
|
||||
vecs = [[0.0] * self.dim for _ in chunk_pls]
|
||||
|
||||
# Edges
|
||||
note_refs = note_pl.get("references") or []
|
||||
edges = build_edges_for_note(
|
||||
note_id,
|
||||
chunk_pls,
|
||||
note_level_references=note_refs,
|
||||
include_note_scope_refs=note_scope_refs
|
||||
)
|
||||
except Exception as e:
|
||||
return {**result, "error": f"Processing failed: {str(e)}"}
|
||||
|
||||
# 6. Upsert Action
|
||||
if purge_before and has_old:
|
||||
self._purge_artifacts(note_id)
|
||||
|
||||
# Upsert Note
|
||||
n_name, n_pts = points_for_note(self.prefix, note_pl, None, self.dim)
|
||||
upsert_batch(self.client, n_name, n_pts)
|
||||
|
||||
# Upsert Chunks
|
||||
if chunk_pls:
|
||||
c_name, c_pts = points_for_chunks(self.prefix, chunk_pls, vecs)
|
||||
upsert_batch(self.client, c_name, c_pts)
|
||||
|
||||
# Upsert Edges
|
||||
if edges:
|
||||
e_name, e_pts = points_for_edges(self.prefix, edges)
|
||||
upsert_batch(self.client, e_name, e_pts)
|
||||
|
||||
return {
|
||||
"path": file_path,
|
||||
"status": "success",
|
||||
"changed": True,
|
||||
"note_id": note_id,
|
||||
"chunks_count": len(chunk_pls),
|
||||
"edges_count": len(edges)
|
||||
}
|
||||
|
||||
# --- Interne Qdrant Helper ---
|
||||
|
||||
def _fetch_note_payload(self, note_id: str) -> Optional[dict]:
|
||||
from qdrant_client.http import models as rest
|
||||
col = f"{self.prefix}_notes"
|
||||
f = rest.Filter(must=[rest.FieldCondition(key="note_id", match=rest.MatchValue(value=note_id))])
|
||||
pts, _ = self.client.scroll(collection_name=col, scroll_filter=f, limit=1, with_payload=True)
|
||||
return pts[0].payload if pts else None
|
||||
|
||||
def _artifacts_missing(self, note_id: str) -> Tuple[bool, bool]:
|
||||
from qdrant_client.http import models as rest
|
||||
c_col = f"{self.prefix}_chunks"
|
||||
e_col = f"{self.prefix}_edges"
|
||||
f = rest.Filter(must=[rest.FieldCondition(key="note_id", match=rest.MatchValue(value=note_id))])
|
||||
|
||||
# Check Chunks
|
||||
c_pts, _ = self.client.scroll(collection_name=c_col, scroll_filter=f, limit=1)
|
||||
# Check Edges
|
||||
e_pts, _ = self.client.scroll(collection_name=e_col, scroll_filter=f, limit=1)
|
||||
|
||||
return (not bool(c_pts)), (not bool(e_pts))
|
||||
|
||||
def _purge_artifacts(self, note_id: str):
|
||||
from qdrant_client.http import models as rest
|
||||
f = rest.Filter(must=[rest.FieldCondition(key="note_id", match=rest.MatchValue(value=note_id))])
|
||||
selector = rest.FilterSelector(filter=f)
|
||||
for suffix in ["chunks", "edges"]:
|
||||
try:
|
||||
self.client.delete(collection_name=f"{self.prefix}_{suffix}", points_selector=selector)
|
||||
except Exception:
|
||||
pass
|
||||
Reference in new issue
Block a user