xinyin025/LangBot
1
0
Fork 0
mirror of https://github.com/langbot-app/LangBot.git synced 2026-09-16 14:57:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(vector): correct SeekDB adapter semantics (#2536)

Browse Source
This commit is contained in:
huanghuoguoguo
2026-09-12 19:40:30 +08:00
committed by GitHub
parent 58cde8c022
commit d26d0635c5
6 changed files with 323 additions and 102 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/langbot/pkg/vector/vdbs/seekdb.py
+25 -26
View File
@@ -101,18 +101,6 @@ class SeekDBVectorDatabase(VectorDatabase):
self._collection_configs: Dict[str, HNSWConfiguration] = {}
self._runtime_cache_limit = runtime_cache_limit(ap)
self._escape_table = str.maketrans(
{
'\x00': '',
'\\': '\\\\',
"'": "''", # Standard SQL escaping (OceanBase NO_BACKSLASH_ESCAPES)
'"': '\\"',
'\n': '\\n',
'\r': '\\r',
'\t': '\\t',
}
)
async def close(self) -> None:
self._collections.clear()
self._collection_configs.clear()
@@ -192,16 +180,22 @@ class SeekDBVectorDatabase(VectorDatabase):
return coll
def _clean_metadata(self, meta: Dict[str, Any]) -> Dict[str, Any]:
"""SeekDB metadata doesn't support \\ and ", insert will error 3104"""
return {
k: v.translate(self._escape_table)
if isinstance(v, str)
else v
if v is None or isinstance(v, (int, float, bool))
else str(v)
for k, v in meta.items()
if v is not None
}
"""Keep supported scalar metadata values without altering strings."""
return {k: v if isinstance(v, (str, int, float, bool)) else str(v) for k, v in meta.items() if v is not None}
@staticmethod
def _relevance_scores_to_distances(results: Dict[str, Any]) -> None:
"""Convert SeekDB hybrid relevance scores to lower-is-better distances."""
distances = results.get('distances')
if not isinstance(distances, list):
return
results['distances'] = [
[1.0 - float(score) if isinstance(score, (int, float)) else score for score in batch]
if isinstance(batch, list)
else batch
for batch in distances
]
async def get_or_create_collection(self, collection: str):
"""Get or create collection (without vector size - will use default)."""
@@ -236,10 +230,10 @@ class SeekDBVectorDatabase(VectorDatabase):
kwargs: Dict[str, Any] = dict(ids=ids, embeddings=embeddings_list, metadatas=cleaned_metadatas)
if documents is not None:
kwargs['documents'] = [doc.translate(self._escape_table) for doc in documents]
await asyncio.to_thread(coll.add, **kwargs)
kwargs['documents'] = documents
await asyncio.to_thread(coll.upsert, **kwargs)
self.ap.logger.info(f"Added {len(ids)} embeddings to SeekDB collection '{collection}'")
self.ap.logger.info(f"Upserted {len(ids)} embeddings into SeekDB collection '{collection}'")
async def search(
self,
@@ -287,7 +281,8 @@ class SeekDBVectorDatabase(VectorDatabase):
# Route by search type.
# pyseekdb's query() always requires embeddings, so full-text and
# hybrid modes use hybrid_search() which supports text-only queries
# and returns the same nested-list format with distances.
# and returns relevance scores in the nested ``distances`` field.
returns_relevance_scores = False
if search_type == SearchType.FULL_TEXT:
if not query_text:
return {'ids': [[]], 'metadatas': [[]], 'distances': [[]]}
@@ -309,6 +304,7 @@ class SeekDBVectorDatabase(VectorDatabase):
n_results=k,
include=['documents', 'metadatas'],
)
returns_relevance_scores = True
elif search_type == SearchType.HYBRID:
if not query_text:
@@ -352,6 +348,7 @@ class SeekDBVectorDatabase(VectorDatabase):
n_results=k,
include=['documents', 'metadatas'],
)
returns_relevance_scores = True
self.ap.logger.info(
f"SeekDB hybrid search in '{collection}' returned {len(results.get('ids', [[]])[0])} results."
)
@@ -363,6 +360,8 @@ class SeekDBVectorDatabase(VectorDatabase):
results = await asyncio.to_thread(coll.query, **query_kwargs)
results = self._json_safe(results)
if returns_relevance_scores:
self._relevance_scores_to_distances(results)
self.ap.logger.info(
f"SeekDB {search_type} search in '{collection}' returned {len(results.get('ids', [[]])[0])} results"
)