fix:issue2484 (#2488)

Close #issue2484
# Description
Fix  Chroma Collection name rules
"(1) contains 3-63 characters, "
"(2) starts and ends with an alphanumeric character, "
"(3) otherwise contains only alphanumeric characters, underscores or
hyphens (-), "
"(4) contains no two consecutive periods (..) and "
"(5) is not a valid IPv4 address, "
# How Has This Been Tested?

# Snapshots:

create knowledge name rule as below.
"(1) contains 3-63 characters, "
"(2) starts and ends with an alphanumeric character, "
"(3) otherwise contains only alphanumeric characters, underscores or
hyphens (-), "
"(4) contains no two consecutive periods (..) and "
"(5) is not a valid IPv4 address, "

# Checklist:

- [ ] My code follows the style guidelines of this project
- [ ] I have already rebased the commits and make the commit message
conform to the project standard.
- [ ] I have performed a self-review of my own code
- [ ] I have commented my code, particularly in hard-to-understand areas
- [ ] I have made corresponding changes to the documentation
- [ ] Any dependent changes have been merged and published in downstream
modules

packages/dbgpt-core/src/dbgpt/util/string_utils.py

@@ -41,6 +41,17 @@ def is_scientific_notation(string):
         return False
 
 
+def is_valid_ipv4(address):
+    """Check if the address is a valid IPv4 address."""
+    pattern = re.compile(
+        r"^(25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\."
+        r"(25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\."
+        r"(25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\."
+        r"(25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)$"
+    )
+    return pattern.match(address) is not None
+
+
 def extract_content(long_string, s1, s2, is_include: bool = False) -> Dict[int, str]:
     # extract text
     match_map = {}

packages/dbgpt-ext/src/dbgpt_ext/storage/vector_store/chroma_store.py

@@ -1,7 +1,9 @@
 """Chroma vector store."""
 
+import hashlib
 import logging
 import os
+import re
 from dataclasses import dataclass, field
 from typing import Any, Dict, Iterable, List, Mapping, Optional, Union
 
@@ -112,10 +114,11 @@ class ChromaStore(VectorStoreBase):
         if not self.embeddings:
             raise ValueError("Embeddings is None")
         self._collection_name = name
-        if string_utils.contains_chinese(name):
+        if not _valid_chroma_collection_name(name):
-            bytes_str = self._collection_name.encode("utf-8")
+            hash_object = hashlib.sha256(name.encode("utf-8"))
-            hex_str = bytes_str.hex()
+            hex_hash = hash_object.hexdigest()
-            self._collection_name = hex_str
+            # ensure the collection name is less than 64 characters
+            self._collection_name = hex_hash[:63] if len(hex_hash) > 63 else hex_hash
         chroma_settings = Settings(
             # chroma_db_impl="duckdb+parquet", => deprecated configuration of Chroma
             persist_directory=self.persist_dir,
@@ -420,3 +423,31 @@ def _transform_chroma_metadata(
         if isinstance(value, (str, int, float, bool)):
             transformed[key] = value
     return transformed
+
+
+def _valid_chroma_collection_name(name):
+    """Check if the collection name is valid."""
+    # ensure the collection name is less than 64 characters
+    if not (3 <= len(name) <= 63):
+        return False
+
+    # ensure the collection name starts and ends with an alphanumeric character
+    if not re.match(r"^[a-zA-Z0-9].*[a-zA-Z0-9]$", name):
+        return False
+
+    # ensure the collection name contains only alphanumeric characters,
+    # hyphens, underscores, and dots
+    if not re.match(r"^[a-zA-Z0-9_][-a-zA-Z0-9_.]*$", name):
+        return False
+
+    # ensure the collection name does not contain the '..' substring
+    if ".." in name:
+        return False
+
+    if string_utils.is_valid_ipv4(name):
+        return False
+
+    if string_utils.contains_chinese(name):
+        return False
+
+    return True