feat(ingestion): supporto multi-documento in unica collection ChromaDB

Aggiunge la possibilità di unire più documenti in una singola collection
ChromaDB, con chunk_id prefissati per stem e metadato source per filtrare.

- ingest.py: --stems doc1 doc2 --collection nome (nuovo), --stem (invariato)
- rag.py / retrieve.py: --collection, source nei chunk, verbose mostra [source]

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

retrieve.py

@@ -85,6 +85,7 @@ def retrieve(collection: chromadb.Collection, query: str, top_k: int) -> list[di
         chunks.append({
             "rank":       rank,
             "similarity": round(1 - dist, 4),
+            "source":     meta.get("source", ""),
             "sezione":    meta.get("sezione", ""),
             "titolo":     meta.get("titolo", ""),
             "text":       text,
@@ -97,10 +98,11 @@ def retrieve(collection: chromadb.Collection, query: str, top_k: int) -> list[di
 def print_results(chunks: list[dict], full: bool = False) -> None:
     print(f"── {len(chunks)} chunk recuperati ─────────────────────────────────\n")
     for c in chunks:
+        src = f"[{c['source']}] " if c.get("source") else ""
         loc = c["sezione"]
         if c["titolo"]:
             loc += f" > {c['titolo']}"
-        print(f"  [{c['rank']}] similarità: {c['similarity']:.4f}  |  {loc}")
+        print(f"  [{c['rank']}] similarità: {c['similarity']:.4f}  |  {src}{loc}")
         if full:
             print()
             print(c["text"])
@@ -177,8 +179,11 @@ def main() -> int:
     )
     parser.add_argument(
         "--stem",
-        required=True,
-        help="Nome della collection ChromaDB da interrogare.",
+        help="Collection di un singolo documento (retrocompatibile)",
+    )
+    parser.add_argument(
+        "--collection",
+        help="Collection multi-documento creata con: ingest.py --collection <nome> --stems ...",
     )
     parser.add_argument(
         "--top-k",
@@ -189,8 +194,12 @@ def main() -> int:
     )
     args = parser.parse_args()
 
+    collection_name = args.collection or args.stem
+    if not collection_name:
+        parser.error("specifica --stem <nome> oppure --collection <nome>")
+
     print("─── Retrieval puro ──────────────────────────────────────────\n")
-    print(f"  Documento    : {args.stem}")
+    print(f"  Collection   : {collection_name}")
     print(f"  Embed model  : {EMBED_MODEL}")
     print(f"  Top-K        : {args.top_k}")
     print()
@@ -201,13 +210,16 @@ def main() -> int:
 
     client = chromadb.PersistentClient(path=str(CHROMA_DIR))
     collections = [c.name for c in client.list_collections()]
-    if args.stem not in collections:
-        print(f"❌ Collection '{args.stem}' non trovata in chroma_db/", file=sys.stderr)
-        print(f"   → python ingestion/ingest.py --stem {args.stem}", file=sys.stderr)
+    if collection_name not in collections:
+        print(f"❌ Collection '{collection_name}' non trovata in chroma_db/", file=sys.stderr)
+        if args.stem:
+            print(f"   → python ingestion/ingest.py --stem {collection_name}", file=sys.stderr)
+        else:
+            print(f"   → python ingestion/ingest.py --collection {collection_name} --stems doc1 doc2 ...", file=sys.stderr)
         return 1
 
-    collection = client.get_collection(args.stem)
-    print(f"✅ Collection '{args.stem}' caricata ({collection.count()} chunk)\n")
+    collection = client.get_collection(collection_name)
+    print(f"✅ Collection '{collection_name}' caricata ({collection.count()} chunk)\n")
 
     run_loop(collection, args.top_k)
     return 0