fix: convert qdrant search results to ScoredPoint

README.md

@@ -109,24 +109,34 @@ import asyncio
 from cognee.api.v1.search import SearchType
 
 async def main():
-    await cognee.prune.prune_data()  # Reset cognee data
-    await cognee.prune.prune_system(metadata=True)  # Reset cognee system state
+    # Reset cognee data
+    await cognee.prune.prune_data()
+    # Reset cognee system state
+    await cognee.prune.prune_system(metadata=True)
 
     text = """
     Natural language processing (NLP) is an interdisciplinary
     subfield of computer science and information retrieval.
     """
 
-    await cognee.add(text)  # Add text to cognee
-    await cognee.cognify()  # Use LLMs and cognee to create knowledge graph
+    # Add text to cognee
+    await cognee.add(text)
 
-    search_results = await cognee.search(  # Search cognee for insights
+    # Use LLMs and cognee to create knowledge graph
+    await cognee.cognify()
+
+    # Search cognee for insights
+    search_results = await cognee.search(
         SearchType.INSIGHTS,
-        {'query': 'Tell me about NLP'}
+        "Tell me about NLP",
     )
 
-    for result_text in search_results:  # Display results
+    # Display results
+    for result_text in search_results:
         print(result_text)
+        # natural_language_processing is_a field
+        # natural_language_processing is_subfield_of computer_science
+        # natural_language_processing is_subfield_of information_retrieval
 
 asyncio.run(main())
 ```

cognee/infrastructure/databases/vector/qdrant/QDrantAdapter.py

@@ -1,7 +1,9 @@
 import logging
+from uuid import UUID
 from typing import List, Dict, Optional
 from qdrant_client import AsyncQdrantClient, models
 
+from cognee.infrastructure.databases.vector.models.ScoredResult import ScoredResult
 from cognee.infrastructure.engine import DataPoint
 from ..vector_db_interface import VectorDBInterface
 from ..embeddings.EmbeddingEngine import EmbeddingEngine
@@ -153,7 +155,7 @@ async def search(
 
         client = self.get_qdrant_client()
 
-        result = await client.search(
+        results = await client.search(
             collection_name = collection_name,
             query_vector = models.NamedVector(
                 name = "text",
@@ -165,7 +167,16 @@ async def search(
 
         await client.close()
 
-        return result
+        return [
+            ScoredResult(
+                id = UUID(result.id),
+                payload = {
+                    **result.payload,
+                    "id": UUID(result.id),
+                },
+                score = 1 - result.score,
+            ) for result in results
+        ]
 
 
     async def batch_search(self, collection_name: str, query_texts: List[str], limit: int = None, with_vectors: bool = False):

cognee/modules/engine/utils/__init__.py

@@ -1,2 +1,3 @@
 from .generate_node_id import generate_node_id
 from .generate_node_name import generate_node_name
+from .generate_edge_name import generate_edge_name

cognee/modules/engine/utils/generate_edge_name.py

@@ -0,0 +1,2 @@
+def generate_edge_name(name: str) -> str:
+    return name.lower().replace(" ", "_").replace("'", "")

cognee/modules/engine/utils/generate_node_name.py

@@ -1,2 +1,2 @@
 def generate_node_name(name: str) -> str:
-    return name.lower().replace(" ", "_").replace("'", "")
+    return name.lower().replace("'", "")

cognee/tasks/graph/extract_graph_from_data.py

@@ -5,7 +5,7 @@
 from cognee.modules.data.extraction.knowledge_graph import extract_content_graph
 from cognee.modules.chunking.models.DocumentChunk import DocumentChunk
 from cognee.modules.engine.models import EntityType, Entity
-from cognee.modules.engine.utils import generate_node_id, generate_node_name
+from cognee.modules.engine.utils import generate_edge_name, generate_node_id, generate_node_name
 from cognee.tasks.storage import add_data_points
 
 async def extract_graph_from_data(data_chunks: list[DocumentChunk], graph_model: Type[BaseModel]):
@@ -95,7 +95,7 @@ async def extract_graph_from_data(data_chunks: list[DocumentChunk], graph_model:
         for edge in graph.edges:
             source_node_id = generate_node_id(edge.source_node_id)
             target_node_id = generate_node_id(edge.target_node_id)
-            relationship_name = generate_node_name(edge.relationship_name)
+            relationship_name = generate_edge_name(edge.relationship_name)
 
             edge_key = str(source_node_id) + str(target_node_id) + relationship_name
 
@@ -105,7 +105,7 @@ async def extract_graph_from_data(data_chunks: list[DocumentChunk], graph_model:
                     target_node_id,
                     edge.relationship_name,
                     dict(
-                        relationship_name = generate_node_name(edge.relationship_name),
+                        relationship_name = generate_edge_name(edge.relationship_name),
                         source_node_id = source_node_id,
                         target_node_id = target_node_id,
                     ),

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", "AI"))[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 = 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", "AI"))[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 = random_node_name)