feat: add knowledge base core api

backend/apps/knowledge/services.py

@@ -0,0 +1,87 @@
+import hashlib
+import math
+
+from apps.knowledge.models import KnowledgeChunk, KnowledgeDocument, KnowledgeItem
+
+DEFAULT_CHUNK_SIZE = 600
+
+
+def split_text(content: str, chunk_size: int = DEFAULT_CHUNK_SIZE) -> list[str]:
+    normalized = "\n".join(line.strip() for line in content.splitlines() if line.strip())
+    if not normalized:
+        return []
+    return [
+        normalized[index : index + chunk_size]
+        for index in range(0, len(normalized), chunk_size)
+    ]
+
+
+def embed_text(content: str, dimensions: int = 16) -> list[float]:
+    digest = hashlib.sha256(content.encode("utf-8")).digest()
+    values = [digest[index] / 255 for index in range(dimensions)]
+    length = math.sqrt(sum(value * value for value in values)) or 1
+    return [round(value / length, 6) for value in values]
+
+
+def rebuild_item_chunks(item: KnowledgeItem) -> list[KnowledgeChunk]:
+    item.chunks.all().delete()
+    content = "\n".join(
+        [
+            item.title,
+            item.problem,
+            item.applicable_scope,
+            item.error_code,
+            item.root_cause,
+            item.troubleshooting_steps,
+            item.solution,
+            item.risk_note,
+        ]
+    )
+    chunks = []
+    for index, chunk_text in enumerate(split_text(content)):
+        chunks.append(
+            KnowledgeChunk.objects.create(
+                knowledge_base=item.knowledge_base,
+                item=item,
+                chunk_index=index,
+                content=chunk_text,
+                embedding=embed_text(chunk_text),
+                metadata={
+                    "source_type": "knowledge_item",
+                    "title": item.title,
+                    "item_id": item.id,
+                },
+            )
+        )
+    return chunks
+
+
+def ingest_document_text(
+    knowledge_base_id: int,
+    file_name: str,
+    file_type: str,
+    content: str,
+    operator=None,
+) -> KnowledgeDocument:
+    document = KnowledgeDocument.objects.create(
+        knowledge_base_id=knowledge_base_id,
+        file_name=file_name,
+        file_type=file_type,
+        content_text=content,
+        parse_status="success",
+        created_by=operator,
+    )
+    for index, chunk_text in enumerate(split_text(content)):
+        KnowledgeChunk.objects.create(
+            knowledge_base=document.knowledge_base,
+            document=document,
+            chunk_index=index,
+            content=chunk_text,
+            embedding=embed_text(chunk_text),
+            metadata={
+                "source_type": "document",
+                "title": document.file_name,
+                "document_id": document.id,
+            },
+        )
+    return document