apunkt/trustgraph
1
0
Fork 0
mirror of https://github.com/trustgraph-ai/trustgraph.git synced 2026-04-26 08:56:21 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix hard coded vector size (#555)

Browse source 
* Fixed hard-coded embeddings store size

* Vector store lazy-creates collections, different collections for
  different dimension lengths.

* Added tech spec for vector store lifecycle

* Fixed some tests for the new spec
This commit is contained in:
cybermaggedon 2025-11-10 16:56:51 +00:00 • committed by GitHub
parent 05b9063fea
commit 6129bb68c1
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
22 changed files with 793 additions and 572 deletions
Download patch file Download diff file Expand all files Collapse all files

12
tests/unit/test_query/test_doc_embeddings_pinecone_query.py
View file

@ -119,8 +119,8 @@ class TestPineconeDocEmbeddingsQueryProcessor:
chunks = await processor.query_document_embeddings(message)
# Verify index was accessed correctly
expected_index_name = "d-test_user-test_collection"
# Verify index was accessed correctly (with dimension suffix)
expected_index_name = "d-test_user-test_collection-3" # 3 dimensions
processor.pinecone.Index.assert_called_once_with(expected_index_name)
# Verify query parameters
@ -264,10 +264,12 @@ class TestPineconeDocEmbeddingsQueryProcessor:
chunks = await processor.query_document_embeddings(message)
# Verify same index used for both vectors
expected_index_name = "d-test_user-test_collection"
# Verify different indexes used for different dimensions
assert processor.pinecone.Index.call_count == 2
processor.pinecone.Index.assert_called_with(expected_index_name)
index_calls = processor.pinecone.Index.call_args_list
index_names = [call[0][0] for call in index_calls]
assert "d-test_user-test_collection-2" in index_names # 2D vector
assert "d-test_user-test_collection-4" in index_names # 4D vector
# Verify both queries were made
assert mock_index.query.call_count == 2

18
tests/unit/test_query/test_doc_embeddings_qdrant_query.py
View file

@ -103,8 +103,8 @@ class TestQdrantDocEmbeddingsQuery(IsolatedAsyncioTestCase):
result = await processor.query_document_embeddings(mock_message)
# Assert
# Verify query was called with correct parameters
expected_collection = 'd_test_user_test_collection'
# Verify query was called with correct parameters (with dimension suffix)
expected_collection = 'd_test_user_test_collection_3' # 3 dimensions
mock_qdrant_instance.query_points.assert_called_once_with(
collection_name=expected_collection,
query=[0.1, 0.2, 0.3],
@ -164,9 +164,9 @@ class TestQdrantDocEmbeddingsQuery(IsolatedAsyncioTestCase):
# Assert
# Verify query was called twice
assert mock_qdrant_instance.query_points.call_count == 2
# Verify both collections were queried
expected_collection = 'd_multi_user_multi_collection'
# Verify both collections were queried (both 2-dimensional vectors)
expected_collection = 'd_multi_user_multi_collection_2' # 2 dimensions
calls = mock_qdrant_instance.query_points.call_args_list
assert calls[0][1]['collection_name'] == expected_collection
assert calls[1][1]['collection_name'] == expected_collection
@ -301,13 +301,13 @@ class TestQdrantDocEmbeddingsQuery(IsolatedAsyncioTestCase):
# Verify query was called twice with different collections
assert mock_qdrant_instance.query_points.call_count == 2
calls = mock_qdrant_instance.query_points.call_args_list
# First call should use 2D collection
assert calls[0][1]['collection_name'] == 'd_dim_user_dim_collection'
assert calls[0][1]['collection_name'] == 'd_dim_user_dim_collection_2' # 2 dimensions
assert calls[0][1]['query'] == [0.1, 0.2]
# Second call should use 3D collection
assert calls[1][1]['collection_name'] == 'd_dim_user_dim_collection'
assert calls[1][1]['collection_name'] == 'd_dim_user_dim_collection_3' # 3 dimensions
assert calls[1][1]['query'] == [0.3, 0.4, 0.5]
# Verify results

12
tests/unit/test_query/test_graph_embeddings_pinecone_query.py
View file

@ -147,8 +147,8 @@ class TestPineconeGraphEmbeddingsQueryProcessor:
entities = await processor.query_graph_embeddings(message)
# Verify index was accessed correctly
expected_index_name = "t-test_user-test_collection"
# Verify index was accessed correctly (with dimension suffix)
expected_index_name = "t-test_user-test_collection-3" # 3 dimensions
processor.pinecone.Index.assert_called_once_with(expected_index_name)
# Verify query parameters
@ -290,10 +290,12 @@ class TestPineconeGraphEmbeddingsQueryProcessor:
entities = await processor.query_graph_embeddings(message)
# Verify same index used for both vectors
expected_index_name = "t-test_user-test_collection"
# Verify different indexes used for different dimensions
assert processor.pinecone.Index.call_count == 2
processor.pinecone.Index.assert_called_with(expected_index_name)
index_calls = processor.pinecone.Index.call_args_list
index_names = [call[0][0] for call in index_calls]
assert "t-test_user-test_collection-2" in index_names # 2D vector
assert "t-test_user-test_collection-4" in index_names # 4D vector
# Verify both queries were made
assert mock_index.query.call_count == 2

18
tests/unit/test_query/test_graph_embeddings_qdrant_query.py
View file

@ -175,8 +175,8 @@ class TestQdrantGraphEmbeddingsQuery(IsolatedAsyncioTestCase):
result = await processor.query_graph_embeddings(mock_message)
# Assert
# Verify query was called with correct parameters
expected_collection = 't_test_user_test_collection'
# Verify query was called with correct parameters (with dimension suffix)
expected_collection = 't_test_user_test_collection_3' # 3 dimensions
mock_qdrant_instance.query_points.assert_called_once_with(
collection_name=expected_collection,
query=[0.1, 0.2, 0.3],
@ -234,9 +234,9 @@ class TestQdrantGraphEmbeddingsQuery(IsolatedAsyncioTestCase):
# Assert
# Verify query was called twice
assert mock_qdrant_instance.query_points.call_count == 2
# Verify both collections were queried
expected_collection = 't_multi_user_multi_collection'
# Verify both collections were queried (both 2-dimensional vectors)
expected_collection = 't_multi_user_multi_collection_2' # 2 dimensions
calls = mock_qdrant_instance.query_points.call_args_list
assert calls[0][1]['collection_name'] == expected_collection
assert calls[1][1]['collection_name'] == expected_collection
@ -372,13 +372,13 @@ class TestQdrantGraphEmbeddingsQuery(IsolatedAsyncioTestCase):
# Verify query was called twice with different collections
assert mock_qdrant_instance.query_points.call_count == 2
calls = mock_qdrant_instance.query_points.call_args_list
# First call should use 2D collection
assert calls[0][1]['collection_name'] == 't_dim_user_dim_collection'
assert calls[0][1]['collection_name'] == 't_dim_user_dim_collection_2' # 2 dimensions
assert calls[0][1]['query'] == [0.1, 0.2]
# Second call should use 3D collection
assert calls[1][1]['collection_name'] == 't_dim_user_dim_collection'
assert calls[1][1]['collection_name'] == 't_dim_user_dim_collection_3' # 3 dimensions
assert calls[1][1]['query'] == [0.3, 0.4, 0.5]
# Verify results