UPDATE

rag/ingest.py

@@ -12,6 +12,7 @@ from pathlib import Path
 from .chunker import chunk_text, chunk_texts
 from .config import load_rag_config, RAGConfig
 from .embedding import embed_texts
+from .observability import classify_exception, log_event, observe_operation, record_metric
 from .user_data import load_user_sources, build_user_weather_text
 from .vector_store import QdrantVectorStore
 
@@ -36,7 +37,19 @@ def _load_file(path: Path) -> str | None:
         return None
     try:
         return path.read_text(encoding="utf-8").strip()
-    except Exception:
+    except Exception as exc:
+        failure = classify_exception(exc)
+        log_event(
+            level=40,
+            message="rag ingest file load failed",
+            source="rag.ingest",
+            provider=None,
+            operation="load_file",
+            result_status="error",
+            error_code=failure.error_code,
+            path=str(path),
+        )
+        record_metric("rag.ingest.file_load_failure", error_code=failure.error_code)
         return None
 
 
@@ -122,12 +135,14 @@ def ingest(
     """
     cfg = config or load_rag_config()
     store = QdrantVectorStore(config=cfg)
-    if recreate:
-        store.ensure_collection(recreate=True)
+    with observe_operation(source="rag.ingest", provider=cfg.embedding.provider, operation="ingest"):
+        if recreate:
+            store.ensure_collection(recreate=True)
 
-    sources = load_sources(config=cfg, kb_name=kb_name)
-    if not sources:
-        return {"chunks_added": 0, "sources": [], "error": "هیچ منبعی یافت نشد"}
+        sources = load_sources(config=cfg, kb_name=kb_name)
+        if not sources:
+            record_metric("rag.ingest.empty_sources", kb_name=kb_name)
+            return {"chunks_added": 0, "sources": [], "error": "هیچ منبعی یافت نشد"}
 
     all_chunks: list[str] = []
     all_metas: list[dict] = []
@@ -146,24 +161,27 @@ def ingest(
                 "kb_name": src_kb,
             })
 
-    if not all_chunks:
-        return {"chunks_added": 0, "sources": [s[0] for s in sources], "error": "هیچ چانکی ساخته نشد"}
+        if not all_chunks:
+            record_metric("rag.ingest.empty_chunks", kb_name=kb_name)
+            return {"chunks_added": 0, "sources": [s[0] for s in sources], "error": "هیچ چانکی ساخته نشد"}
 
-    embeddings = embed_texts(all_chunks, config=cfg)
-    if len(embeddings) != len(all_chunks):
+        embeddings = embed_texts(all_chunks, config=cfg)
+        if len(embeddings) != len(all_chunks):
+            record_metric("rag.ingest.embedding_mismatch", kb_name=kb_name)
+            return {
+                "chunks_added": 0,
+                "sources": [s[0] for s in sources],
+                "error": f"تعداد embed با چانک‌ها مطابقت ندارد: {len(embeddings)} vs {len(all_chunks)}",
+            }
+
+        store.add_documents(
+            ids=all_ids,
+            embeddings=embeddings,
+            documents=all_chunks,
+            metadatas=all_metas,
+        )
+        record_metric("rag.ingest.success", kb_name=kb_name, chunks=len(all_chunks))
         return {
-            "chunks_added": 0,
+            "chunks_added": len(all_chunks),
             "sources": [s[0] for s in sources],
-            "error": f"تعداد embed با چانک‌ها مطابقت ندارد: {len(embeddings)} vs {len(all_chunks)}",
         }
-
-    store.add_documents(
-        ids=all_ids,
-        embeddings=embeddings,
-        documents=all_chunks,
-        metadatas=all_metas,
-    )
-    return {
-        "chunks_added": len(all_chunks),
-        "sources": [s[0] for s in sources],
-    }