apunkt/trustgraph
1
0
Fork 0
mirror of https://github.com/trustgraph-ai/trustgraph.git synced 2026-04-28 09:56:22 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Collection delete pt. 3 (#542)

Browse source 
* Fixing collection deletion

* Fixing collection management param error

* Always test for collections

* Add Cassandra collection table

* Updated tech spec for explicit creation/deletion

* Remove implicit collection creation

* Fix up collection tracking in all processors
This commit is contained in:
cybermaggedon 2025-09-30 16:02:33 +01:00 • committed by GitHub
parent dc79b10552
commit 52b133fc86
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
31 changed files with 1761 additions and 843 deletions
Download patch file Download diff file Expand all files Collapse all files

37
trustgraph-flow/trustgraph/query/doc_embeddings/qdrant/service.py
View file

@ -38,24 +38,10 @@ class Processor(DocumentEmbeddingsQueryService):
)
self.qdrant = QdrantClient(url=store_uri, api_key=api_key)
self.last_collection = None
def ensure_collection_exists(self, collection, dim):
"""Ensure collection exists, create if it doesn't"""
if collection != self.last_collection:
if not self.qdrant.collection_exists(collection):
try:
self.qdrant.create_collection(
collection_name=collection,
vectors_config=VectorParams(
size=dim, distance=Distance.COSINE
),
)
logger.info(f"Created collection: {collection}")
except Exception as e:
logger.error(f"Qdrant collection creation failed: {e}")
raise e
self.last_collection = collection
def collection_exists(self, collection):
"""Check if collection exists (no implicit creation)"""
return self.qdrant.collection_exists(collection)
async def query_document_embeddings(self, msg):
@ -63,15 +49,16 @@ class Processor(DocumentEmbeddingsQueryService):
chunks = []
collection = (
"d_" + msg.user + "_" + msg.collection
)
# Check if collection exists - return empty if not
if not self.collection_exists(collection):
logger.info(f"Collection {collection} does not exist, returning empty results")
return []
for vec in msg.vectors:
dim = len(vec)
collection = (
"d_" + msg.user + "_" + msg.collection
)
self.ensure_collection_exists(collection, dim)
search_result = self.qdrant.query_points(
collection_name=collection,
query=vec,

36
trustgraph-flow/trustgraph/query/graph_embeddings/qdrant/service.py
View file

@ -38,24 +38,10 @@ class Processor(GraphEmbeddingsQueryService):
)
self.qdrant = QdrantClient(url=store_uri, api_key=api_key)
self.last_collection = None
def ensure_collection_exists(self, collection, dim):
"""Ensure collection exists, create if it doesn't"""
if collection != self.last_collection:
if not self.qdrant.collection_exists(collection):
try:
self.qdrant.create_collection(
collection_name=collection,
vectors_config=VectorParams(
size=dim, distance=Distance.COSINE
),
)
logger.info(f"Created collection: {collection}")
except Exception as e:
logger.error(f"Qdrant collection creation failed: {e}")
raise e
self.last_collection = collection
def collection_exists(self, collection):
"""Check if collection exists (no implicit creation)"""
return self.qdrant.collection_exists(collection)
def create_value(self, ent):
if ent.startswith("http://") or ent.startswith("https://"):
@ -70,15 +56,17 @@ class Processor(GraphEmbeddingsQueryService):
entity_set = set()
entities = []
collection = (
"t_" + msg.user + "_" + msg.collection
)
# Check if collection exists - return empty if not
if not self.collection_exists(collection):
logger.info(f"Collection {collection} does not exist, returning empty results")
return []
for vec in msg.vectors:
dim = len(vec)
collection = (
"t_" + msg.user + "_" + msg.collection
)
self.ensure_collection_exists(collection, dim)
# Heuristic hack, get (2*limit), so that we have more chance
# of getting (limit) entities
search_result = self.qdrant.query_points(