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

refactor: Add other search types to notebook

Browse source 
Added other search types and explanations to jupyter notebook

refactor #COG-387
This commit is contained in:
Igor Ilic 2024-10-09 17:52:29 +02:00
parent eab6bda2d3
commit 9ec292aac5
1 changed files with 69 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

70
notebooks/cognee_demo.ipynb
View file

@ -712,7 +712,75 @@
"id": "81fa2b00",
"metadata": {},
"source": [
"#### We normalize search output scores so the lower the score of the search result is the higher the chance that it's what you're looking for."
"#### We normalize search output scores so the lower the score of the search result is the higher the chance that it's what you're looking for. In the example above we have searched for node entities in the knowledge graph related to \"sarah.nguyen@example.com\""
]
},
{
"cell_type": "markdown",
"id": "1b94ff96",
"metadata": {},
"source": [
"#### In the example bellow we'll use cognee search to summarize information regarding the node most related to \"sarah.nguyen@example.com\" in the knowledge graph"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "21a3e9a6",
"metadata": {},
"outputs": [],
"source": [
"from cognee.api.v1.search import SearchType\n",
"\n",
"node = (await vector_engine.search(\"entities\", \"sarah.nguyen@example.com\"))[0]\n",
"node_name = node.payload[\"name\"]\n",
"\n",
"search_results = await cognee.search(SearchType.SUMMARIES, query = random_node_name)\n",
"print(\"\\n\\Extracted summaries are:\\n\")\n",
"for result in search_results:\n",
" print(f\"{result}\\n\")"
]
},
{
"cell_type": "markdown",
"id": "fd6e5fe2",
"metadata": {},
"source": [
"#### In this example we'll use cognee search to find chunks in which the node most related to \"sarah.nguyen@example.com\" is a part of"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c7a8abff",
"metadata": {},
"outputs": [],
"source": [
"search_results = await cognee.search(SearchType.CHUNKS, query = random_node_name)\n",
"print(\"\\n\\nExtracted chunks are:\\n\")\n",
"for result in search_results:\n",
" print(f\"{result}\\n\")"
]
},
{
"cell_type": "markdown",
"id": "47f0112f",
"metadata": {},
"source": [
"#### In this example we'll use cognee search to give us insights from the knowledge graph related to the node most related to \"sarah.nguyen@example.com\""
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "706a3954",
"metadata": {},
"outputs": [],
"source": [
"search_results = await cognee.search(SearchType.INSIGHTS, query = random_node_name)\n",
"print(\"\\n\\nExtracted sentences are:\\n\")\n",
"for result in search_results:\n",
" print(f\"{result}\\n\")"
]
},
{