Replaced md5 with xxhash64 for chunk id (#4009)

### What problem does this PR solve?

Replaced md5 with xxhash64 for chunk id

### Type of change

- [x] Refactoring

api/apps/chunk_app.py

@@ -31,7 +31,7 @@ from api.utils.api_utils import server_error_response, get_data_error_result, va
 from api.db.services.document_service import DocumentService
 from api import settings
 from api.utils.api_utils import get_json_result
-import hashlib
+import xxhash
 import re
 
 
@@ -208,9 +208,7 @@ def rm():
 @validate_request("doc_id", "content_with_weight")
 def create():
     req = request.json
-    md5 = hashlib.md5()
-    md5.update((req["content_with_weight"] + req["doc_id"]).encode("utf-8"))
-    chunck_id = md5.hexdigest()
+    chunck_id = xxhash.xxh64((req["content_with_weight"] + req["doc_id"]).encode("utf-8")).hexdigest()
     d = {"id": chunck_id, "content_ltks": rag_tokenizer.tokenize(req["content_with_weight"]),
          "content_with_weight": req["content_with_weight"]}
     d["content_sm_ltks"] = rag_tokenizer.fine_grained_tokenize(d["content_ltks"])

api/apps/sdk/doc.py

@@ -22,7 +22,7 @@ from rag.nlp import rag_tokenizer
 from api.db import LLMType, ParserType
 from api.db.services.llm_service import TenantLLMService
 from api import settings
-import hashlib
+import xxhash
 import re
 from api.utils.api_utils import token_required
 from api.db.db_models import Task
@@ -984,10 +984,7 @@ def add_chunk(tenant_id, dataset_id, document_id):
             return get_error_data_result(
                 "`questions` is required to be a list"
             )
-    md5 = hashlib.md5()
-    md5.update((req["content"] + document_id).encode("utf-8"))
-
-    chunk_id = md5.hexdigest()
+    chunk_id = xxhash.xxh64((req["content"] + document_id).encode("utf-8")).hexdigest()
     d = {
         "id": chunk_id,
         "content_ltks": rag_tokenizer.tokenize(req["content"]),