fix: Resolve issue with table names in SQL commands (#13)

Some SQL commands require lowercase characters in table names unless
table name is wrapped in quotes. Renamed all new tables to use lowercase

Fix COG-677

cognee/infrastructure/engine/models/DataPoint.py

@@ -8,6 +8,7 @@ class MetaData(TypedDict):
     index_fields: list[str]
 
 class DataPoint(BaseModel):
+    __tablename__ = "data_point"
     id: UUID = Field(default_factory = uuid4)
     updated_at: Optional[datetime] = datetime.now(timezone.utc)
     _metadata: Optional[MetaData] = {

cognee/modules/chunking/models/DocumentChunk.py

@@ -3,6 +3,7 @@ from cognee.infrastructure.engine import DataPoint
 from cognee.modules.data.processing.document_types import Document
 
 class DocumentChunk(DataPoint):
+    __tablename__ = "document_chunk"
     text: str
     word_count: int
     chunk_index: int

cognee/modules/engine/models/Entity.py

@@ -3,6 +3,7 @@ from cognee.modules.chunking.models.DocumentChunk import DocumentChunk
 from .EntityType import EntityType
 
 class Entity(DataPoint):
+    __tablename__ = "entity"
     name: str
     is_a: EntityType
     description: str

cognee/modules/engine/models/EntityType.py

@@ -2,6 +2,7 @@ from cognee.infrastructure.engine import DataPoint
 from cognee.modules.chunking.models.DocumentChunk import DocumentChunk
 
 class EntityType(DataPoint):
+    __tablename__ = "entity_type"
     name: str
     type: str
     description: str

cognee/tasks/chunks/query_chunks.py

@@ -10,7 +10,7 @@ async def query_chunks(query: str) -> list[dict]:
     """
     vector_engine = get_vector_engine()
 
-    found_chunks = await vector_engine.search("DocumentChunk_text", query, limit = 5)
+    found_chunks = await vector_engine.search("document_chunk_text", query, limit = 5)
 
     chunks = [result.payload for result in found_chunks]
 

cognee/tasks/graph/query_graph_connections.py

@@ -27,8 +27,8 @@ async def query_graph_connections(query: str, exploration_levels = 1) -> list[(s
     else:
         vector_engine = get_vector_engine()
         results = await asyncio.gather(
-            vector_engine.search("Entity_name", query_text = query, limit = 5),
-            vector_engine.search("EntityType_name", query_text = query, limit = 5),
+            vector_engine.search("entity_name", query_text = query, limit = 5),
+            vector_engine.search("entity_type_name", query_text = query, limit = 5),
         )
         results = [*results[0], *results[1]]
         relevant_results = [result for result in results if result.score < 0.5][:5]

cognee/tasks/storage/index_data_points.py

@@ -16,10 +16,10 @@ async def index_data_points(data_points: list[DataPoint]):
         data_point_type = type(data_point)
 
         for field_name in data_point._metadata["index_fields"]:
-            index_name = f"{data_point_type.__name__}.{field_name}"
+            index_name = f"{data_point_type.__tablename__}.{field_name}"
 
             if index_name not in created_indexes:
-                await vector_engine.create_vector_index(data_point_type.__name__, field_name)
+                await vector_engine.create_vector_index(data_point_type.__tablename__, field_name)
                 created_indexes[index_name] = True
 
             if index_name not in index_points:

cognee/tasks/summarization/models.py

@@ -3,6 +3,7 @@ from cognee.modules.chunking.models.DocumentChunk import DocumentChunk
 from cognee.modules.data.processing.document_types import Document
 
 class TextSummary(DataPoint):
+    __tablename__ = "text_summary"
     text: str
     made_from: DocumentChunk
 

cognee/tasks/summarization/query_summaries.py

@@ -10,7 +10,7 @@ async def query_summaries(query: str) -> list:
     """
     vector_engine = get_vector_engine()
 
-    summaries_results = await vector_engine.search("TextSummary_text", query, limit = 5)
+    summaries_results = await vector_engine.search("text_summary_text", query, limit = 5)
 
     summaries = [summary.payload for summary in summaries_results]
 

cognee/tests/test_library.py

@@ -32,7 +32,7 @@ async def  main():
 
     from cognee.infrastructure.databases.vector import get_vector_engine
     vector_engine = get_vector_engine()
-    random_node = (await vector_engine.search("Entity_name", "AI"))[0]
+    random_node = (await vector_engine.search("entity_name", "AI"))[0]
     random_node_name = random_node.payload["text"]
 
     search_results = await cognee.search(SearchType.INSIGHTS, query_text = random_node_name)

cognee/tests/test_neo4j.py

@@ -36,7 +36,7 @@ async def main():
 
     from cognee.infrastructure.databases.vector import get_vector_engine
     vector_engine = get_vector_engine()
-    random_node = (await vector_engine.search("Entity_name", "Quantum computer"))[0]
+    random_node = (await vector_engine.search("entity_name", "Quantum computer"))[0]
     random_node_name = random_node.payload["text"]
 
     search_results = await cognee.search(SearchType.INSIGHTS, query_text = random_node_name)

cognee/tests/test_pgvector.py

@@ -65,7 +65,7 @@ async def main():
     from cognee.infrastructure.databases.vector import get_vector_engine
 
     vector_engine = get_vector_engine()
-    random_node = (await vector_engine.search("Entity_name", "Quantum computer"))[0]
+    random_node = (await vector_engine.search("entity_name", "Quantum computer"))[0]
     random_node_name = random_node.payload["text"]
 
     search_results = await cognee.search(SearchType.INSIGHTS, query_text = random_node_name)

cognee/tests/test_qdrant.py

@@ -37,7 +37,7 @@ async def main():
 
     from cognee.infrastructure.databases.vector import get_vector_engine
     vector_engine = get_vector_engine()
-    random_node = (await vector_engine.search("Entity_name", "Quantum computer"))[0]
+    random_node = (await vector_engine.search("entity_name", "Quantum computer"))[0]
     random_node_name = random_node.payload["text"]
 
     search_results = await cognee.search(SearchType.INSIGHTS, query_text = random_node_name)

cognee/tests/test_weaviate.py

@@ -35,7 +35,7 @@ async def main():
 
     from cognee.infrastructure.databases.vector import get_vector_engine
     vector_engine = get_vector_engine()
-    random_node = (await vector_engine.search("Entity_name", "Quantum computer"))[0]
+    random_node = (await vector_engine.search("entity_name", "Quantum computer"))[0]
     random_node_name = random_node.payload["text"]
 
     search_results = await cognee.search(SearchType.INSIGHTS, query_text = random_node_name)

notebooks/cognee_demo.ipynb

@@ -758,7 +758,7 @@
     "from cognee.infrastructure.databases.vector import get_vector_engine\n",
     "\n",
     "vector_engine = get_vector_engine()\n",
-    "results = await search(vector_engine, \"Entity_name\", \"sarah.nguyen@example.com\")\n",
+    "results = await search(vector_engine, \"entity_name\", \"sarah.nguyen@example.com\")\n",
     "for result in results:\n",
     "    print(result)"
    ]
@@ -788,7 +788,7 @@
    "source": [
     "from cognee.api.v1.search import SearchType\n",
     "\n",
-    "node = (await vector_engine.search(\"Entity_name\", \"sarah.nguyen@example.com\"))[0]\n",
+    "node = (await vector_engine.search(\"entity_name\", \"sarah.nguyen@example.com\"))[0]\n",
     "node_name = node.payload[\"text\"]\n",
     "\n",
     "search_results = await cognee.search(SearchType.SUMMARIES, query_text = node_name)\n",
@@ -881,7 +881,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.8"
+   "version": "3.9.6"
   }
  },
  "nbformat": 4,