Add code_graph_demo notebook

This commit is contained in:
Leon Luithlen 2024-11-11 13:03:50 +01:00
parent 0b3a94e90b
commit 9fe1b6c5fa
3 changed files with 140 additions and 1 deletions

1
.gitignore vendored
View file

@ -4,6 +4,7 @@
.prod.env
cognee/.data/
*.lance/
# Byte-compiled / optimized / DLL files
__pycache__/

View file

@ -270,7 +270,7 @@ class NetworkXAdapter(GraphDBInterface):
except:
pass
if "updated_at" in node:
if "updated_at" in edge:
edge["updated_at"] = datetime.strptime(edge["updated_at"], "%Y-%m-%dT%H:%M:%S.%f%z")
self.graph = nx.readwrite.json_graph.node_link_graph(graph_data)

View file

@ -0,0 +1,138 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"os.environ['GRAPHISTRY_USERNAME'] = input(\"Please enter your graphistry username\")\n",
"os.environ['GRAPHISTRY_PASSWORD'] = input(\"Please enter your graphistry password\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from cognee.modules.users.methods import get_default_user\n",
"\n",
"from cognee.modules.data.methods import get_datasets\n",
"from cognee.modules.data.methods.get_dataset_data import get_dataset_data\n",
"from cognee.modules.data.models import Data\n",
"\n",
"from cognee.modules.pipelines.tasks.Task import Task\n",
"from cognee.tasks.documents import classify_documents, check_permissions_on_documents, extract_chunks_from_documents\n",
"from cognee.tasks.graph import extract_graph_from_code\n",
"from cognee.tasks.storage import add_data_points\n",
"from cognee.shared.SourceCodeGraph import SourceCodeGraph\n",
"\n",
"from cognee.modules.pipelines import run_tasks\n",
"\n",
"from cognee.shared.utils import render_graph\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"user = await get_default_user()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"existing_datasets = await get_datasets(user.id)\n",
"\n",
"datasets = {}\n",
"for dataset in existing_datasets:\n",
" dataset_name = dataset.name.replace(\".\", \"_\").replace(\" \", \"_\")\n",
" data_documents: list[Data] = await get_dataset_data(dataset_id = dataset.id)\n",
" datasets[dataset_name] = data_documents\n",
"print(datasets.keys())"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"tasks = [\n",
" Task(classify_documents),\n",
" Task(check_permissions_on_documents, user = user, permissions = [\"write\"]),\n",
" Task(extract_chunks_from_documents), # Extract text chunks based on the document type.\n",
" Task(add_data_points, task_config = { \"batch_size\": 10 }),\n",
" Task(extract_graph_from_code, graph_model = SourceCodeGraph, task_config = { \"batch_size\": 10 }), # Generate knowledge graphs from the document chunks.\n",
"]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"async def run_codegraph_pipeline(tasks, data_documents):\n",
" pipeline = run_tasks(tasks, data_documents, \"code_graph_pipeline\")\n",
" results = []\n",
" async for result in pipeline:\n",
" results.append(result)\n",
" return(results)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"results = await run_codegraph_pipeline(tasks, datasets[\"main_dataset\"])"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"await render_graph(None, include_nodes = True, include_labels = True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "cognee",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.10"
}
},
"nbformat": 4,
"nbformat_minor": 2
}