gmakstutis/cognee
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Remove Memgraph and references to it

Browse source
This commit is contained in:
Daulet Amirkhanov 2025-09-04 15:20:42 +01:00
parent a4c48d1104
commit c8b2e1295d
4 changed files with 42 additions and 1267 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
cognee/infrastructure/databases/graph/get_graph_engine.py
View file

@ -179,5 +179,5 @@ def create_graph_engine(
raise EnvironmentError(
f"Unsupported graph database provider: {graph_database_provider}. "
f"Supported providers are: {', '.join(list(supported_databases.keys()) + ['neo4j', 'falkordb', 'kuzu', 'kuzu-remote', 'memgraph', 'neptune', 'neptune_analytics'])}"
f"Supported providers are: {', '.join(list(supported_databases.keys()) + ['neo4j', 'falkordb', 'kuzu', 'kuzu-remote', 'neptune', 'neptune_analytics'])}"
)

1116
cognee/infrastructure/databases/graph/memgraph/memgraph_adapter.py
View file

File diff suppressed because it is too large Load diff

109
cognee/tests/test_memgraph.py
View file

@ -1,109 +0,0 @@
import os
import pathlib
import cognee
from cognee.infrastructure.files.storage import get_storage_config
from cognee.modules.search.operations import get_history
from cognee.modules.users.methods import get_default_user
from cognee.shared.logging_utils import get_logger
from cognee.modules.search.types import SearchType
logger = get_logger()
async def main():
cognee.config.set_graph_database_provider("memgraph")
data_directory_path = str(
pathlib.Path(
os.path.join(pathlib.Path(__file__).parent, ".data_storage/test_memgraph")
).resolve()
)
cognee.config.data_root_directory(data_directory_path)
cognee_directory_path = str(
pathlib.Path(
os.path.join(pathlib.Path(__file__).parent, ".cognee_system/test_memgraph")
).resolve()
)
cognee.config.system_root_directory(cognee_directory_path)
await cognee.prune.prune_data()
await cognee.prune.prune_system(metadata=True)
dataset_name = "cs_explanations"
explanation_file_path = os.path.join(
pathlib.Path(__file__).parent, "test_data/Natural_language_processing.txt"
)
await cognee.add([explanation_file_path], dataset_name)
text = """A quantum computer is a computer that takes advantage of quantum mechanical phenomena.
At small scales, physical matter exhibits properties of both particles and waves, and quantum computing leverages this behavior, specifically quantum superposition and entanglement, using specialized hardware that supports the preparation and manipulation of quantum states.
Classical physics cannot explain the operation of these quantum devices, and a scalable quantum computer could perform some calculations exponentially faster (with respect to input size scaling) than any modern "classical" computer. In particular, a large-scale quantum computer could break widely used encryption schemes and aid physicists in performing physical simulations; however, the current state of the technology is largely experimental and impractical, with several obstacles to useful applications. Moreover, scalable quantum computers do not hold promise for many practical tasks, and for many important tasks quantum speedups are proven impossible.
The basic unit of information in quantum computing is the qubit, similar to the bit in traditional digital electronics. Unlike a classical bit, a qubit can exist in a superposition of its two "basis" states. When measuring a qubit, the result is a probabilistic output of a classical bit, therefore making quantum computers nondeterministic in general. If a quantum computer manipulates the qubit in a particular way, wave interference effects can amplify the desired measurement results. The design of quantum algorithms involves creating procedures that allow a quantum computer to perform calculations efficiently and quickly.
Physically engineering high-quality qubits has proven challenging. If a physical qubit is not sufficiently isolated from its environment, it suffers from quantum decoherence, introducing noise into calculations. Paradoxically, perfectly isolating qubits is also undesirable because quantum computations typically need to initialize qubits, perform controlled qubit interactions, and measure the resulting quantum states. Each of those operations introduces errors and suffers from noise, and such inaccuracies accumulate.
In principle, a non-quantum (classical) computer can solve the same computational problems as a quantum computer, given enough time. Quantum advantage comes in the form of time complexity rather than computability, and quantum complexity theory shows that some quantum algorithms for carefully selected tasks require exponentially fewer computational steps than the best known non-quantum algorithms. Such tasks can in theory be solved on a large-scale quantum computer whereas classical computers would not finish computations in any reasonable amount of time. However, quantum speedup is not universal or even typical across computational tasks, since basic tasks such as sorting are proven to not allow any asymptotic quantum speedup. Claims of quantum supremacy have drawn significant attention to the discipline, but are demonstrated on contrived tasks, while near-term practical use cases remain limited.
"""
await cognee.add([text], dataset_name)
await cognee.cognify([dataset_name])
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_name = random_node.payload["text"]
search_results = await cognee.search(
query_type=SearchType.INSIGHTS, query_text=random_node_name
)
assert len(search_results) != 0, "The search results list is empty."
print("\n\nExtracted sentences are:\n")
for result in search_results:
print(f"{result}\n")
search_results = await cognee.search(query_type=SearchType.CHUNKS, query_text=random_node_name)
assert len(search_results) != 0, "The search results list is empty."
print("\n\nExtracted chunks are:\n")
for result in search_results:
print(f"{result}\n")
search_results = await cognee.search(
query_type=SearchType.SUMMARIES, query_text=random_node_name
)
assert len(search_results) != 0, "Query related summaries don't exist."
print("\nExtracted results are:\n")
for result in search_results:
print(f"{result}\n")
search_results = await cognee.search(
query_type=SearchType.NATURAL_LANGUAGE,
query_text=f"Find nodes connected to node with name {random_node_name}",
)
assert len(search_results) != 0, "Query related natural language don't exist."
print("\nExtracted results are:\n")
for result in search_results:
print(f"{result}\n")
user = await get_default_user()
history = await get_history(user.id)
assert len(history) == 8, "Search history is not correct."
await cognee.prune.prune_data()
data_root_directory = get_storage_config()["data_root_directory"]
assert not os.path.isdir(data_root_directory), "Local data files are not deleted"
await cognee.prune.prune_system(metadata=True)
from cognee.infrastructure.databases.graph import get_graph_engine
graph_engine = await get_graph_engine()
nodes, edges = await graph_engine.get_graph_data()
assert len(nodes) == 0 and len(edges) == 0, "Memgraph graph database is not empty"
if __name__ == "__main__":
import asyncio
asyncio.run(main())

82
notebooks/neptune-analytics-example.ipynb vendored
View file

@ -83,16 +83,16 @@
]
},
{
"metadata": {},
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"import pathlib\n",
"from cognee import config, add, cognify, search, SearchType, prune, visualize_graph\n",
"from dotenv import load_dotenv"
],
"outputs": [],
"execution_count": null
]
},
{
"cell_type": "markdown",
@ -106,7 +106,9 @@
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# load environment variables from file .env\n",
"load_dotenv()\n",
@ -145,9 +147,7 @@
" \"vector_db_url\": f\"neptune-graph://{graph_identifier}\", # Neptune Analytics endpoint with the format neptune-graph://<GRAPH_ID>\n",
" }\n",
")"
],
"outputs": [],
"execution_count": null
]
},
{
"cell_type": "markdown",
@ -159,19 +159,19 @@
]
},
{
"metadata": {},
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Prune data and system metadata before running, only if we want \"fresh\" state.\n",
"await prune.prune_data()\n",
"await prune.prune_system(metadata=True)"
],
"outputs": [],
"execution_count": null
]
},
{
"metadata": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Setup data and cognify\n",
"\n",
@ -180,7 +180,9 @@
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Add sample text to the dataset\n",
"sample_text_1 = \"\"\"Neptune Analytics is a memory-optimized graph database engine for analytics. With Neptune\n",
@ -205,9 +207,7 @@
"\n",
"# Cognify the text data.\n",
"await cognify([dataset_name])"
],
"outputs": [],
"execution_count": null
]
},
{
"cell_type": "markdown",
@ -215,14 +215,16 @@
"source": [
"## Graph Memory visualization\n",
"\n",
"Initialize Memgraph as a Graph Memory store and save to .artefacts/graph_visualization.html\n",
"Initialize a Graph Memory store and save to .artefacts/graph_visualization.html\n",
"\n",
"![visualization](./neptune_analytics_demo.png)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Get a graphistry url (Register for a free account at https://www.graphistry.com)\n",
"# url = await render_graph()\n",
@ -235,9 +237,7 @@
" ).resolve()\n",
")\n",
"await visualize_graph(graph_file_path)"
],
"outputs": [],
"execution_count": null
]
},
{
"cell_type": "markdown",
@ -250,19 +250,19 @@
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Completion query that uses graph data to form context.\n",
"graph_completion = await search(query_text=\"What is Neptune Analytics?\", query_type=SearchType.GRAPH_COMPLETION)\n",
"print(\"\\nGraph completion result is:\")\n",
"print(graph_completion)"
],
"outputs": [],
"execution_count": null
]
},
{
"metadata": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## SEARCH: RAG Completion\n",
"\n",
@ -271,19 +271,19 @@
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Completion query that uses document chunks to form context.\n",
"rag_completion = await search(query_text=\"What is Neptune Analytics?\", query_type=SearchType.RAG_COMPLETION)\n",
"print(\"\\nRAG Completion result is:\")\n",
"print(rag_completion)"
],
"outputs": [],
"execution_count": null
]
},
{
"metadata": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## SEARCH: Graph Insights\n",
"\n",
@ -291,8 +291,10 @@
]
},
{
"metadata": {},
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Search graph insights\n",
"insights_results = await search(query_text=\"Neptune Analytics\", query_type=SearchType.INSIGHTS)\n",
@ -302,13 +304,11 @@
" tgt_node = result[2].get(\"name\", result[2][\"type\"])\n",
" relationship = result[1].get(\"relationship_name\", \"__relationship__\")\n",
" print(f\"- {src_node} -[{relationship}]-> {tgt_node}\")"
],
"outputs": [],
"execution_count": null
]
},
{
"metadata": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## SEARCH: Entity Summaries\n",
"\n",
@ -316,8 +316,10 @@
]
},
{
"metadata": {},
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Query all summaries related to query.\n",
"summaries = await search(query_text=\"Neptune Analytics\", query_type=SearchType.SUMMARIES)\n",
@ -326,13 +328,11 @@
" type = summary[\"type\"]\n",
" text = summary[\"text\"]\n",
" print(f\"- {type}: {text}\")"
],
"outputs": [],
"execution_count": null
]
},
{
"metadata": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## SEARCH: Chunks\n",
"\n",
@ -340,8 +340,10 @@
]
},
{
"metadata": {},
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"chunks = await search(query_text=\"Neptune Analytics\", query_type=SearchType.CHUNKS)\n",
"print(\"\\nChunk results are:\")\n",
@ -349,9 +351,7 @@
" type = chunk[\"type\"]\n",
" text = chunk[\"text\"]\n",
" print(f\"- {type}: {text}\")"
],
"outputs": [],
"execution_count": null
]
}
],
"metadata": {