Fix poetry deps

This commit is contained in:
Vasilije 2024-03-13 12:42:25 +01:00
parent ee108f039d
commit 84cab02c34

View file

@ -192,63 +192,92 @@
"We load the data from a local folder"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "3a64a838-d02a-4f72-ad30-8732f4445930",
"metadata": {},
"outputs": [],
"source": [
"import iso639"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "5dffa4ac-9c10-4b88-a324-eac390294224",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 4,
"id": "5b3954c1-f537-4be7-a578-1d5037c21374",
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"[nltk_data] Downloading package punkt to /Users/vasa/nltk_data...\n",
"[nltk_data] Unzipping tokenizers/punkt.zip.\n",
"[nltk_data] Downloading package averaged_perceptron_tagger to\n",
"[nltk_data] /Users/vasa/nltk_data...\n",
"[nltk_data] Unzipping taggers/averaged_perceptron_tagger.zip.\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Pipeline file_load_from_filesystem load step completed in 0.38 seconds\n",
"1 load package(s) were loaded to destination duckdb and into dataset izmene\n",
"The duckdb destination used duckdb:///:external: location to store data\n",
"Load package 1710323687.737153 is LOADED and contains no failed jobs\n"
]
}
],
"source": [
"from os import listdir, path\n",
"from uuid import uuid5, UUID\n",
"from cognitive_architecture import add\n",
"\n",
"# we define the folder where our data is\n",
"data_path = path.abspath(\".data\")\n",
"pdf_files = [file for file in listdir(data_path) if path.isfile(path.join(data_path, file))]\n",
"\n",
"await add(\n",
" list(map(\n",
" lambda file_path: f\"file://{path.join(data_path, file_path)}\",\n",
" pdf_files\n",
" ))[:3],\n",
" uuid5(UUID(\"00000000-0000-0000-0000-000000000000\"), \"pdf_files_cognee\"),\n",
" \"test-dataset\"\n",
")\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a0732b21-5c41-4427-ad1c-7df86245217d",
"metadata": {},
"outputs": [],
"source": [
"from os import listdir, path\n",
"from uuid import uuid5, UUID\n",
"from cognitive_architecture import add\n",
"\n",
"data_path = path.abspath(\".data\")\n",
"# pdf_files = [file for file in listdir(data_path) if path.isfile(path.join(data_path, file))]\n",
"\n",
"# await add_dlt(\n",
"# list(map(\n",
"# lambda file_path: f\"file://{path.join(data_path, file_path)}\",\n",
"# pdf_files\n",
"# ))[:5],\n",
"# \"pdf_files\"\n",
"# )\n",
"\n",
"results = await add(data_path, \"pravilnik.energetska_efikasnost\")\n",
"# and then we simply add the data to cognee\n",
"results = await add(data_path, \"izmene\")\n",
"for result in results:\n",
" print(result)\n"
" print(result)\n",
"\n",
"# data gets processed with unstructured and dlt"
]
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 6,
"id": "39df49ca-06f0-4b86-ae27-93c68ddceac3",
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"/Users/vasa/Projects/cognee/cognitive_architecture/data/cognee/cognee.duckdb\n",
"['izmene']\n",
"┌──────────────────────┬──────────────────────┬──────────────────────┬───┬───────────────────┬────────────────┐\n",
"│ id │ name │ file_path │ … │ _dlt_load_id │ _dlt_id │\n",
"│ varchar │ varchar │ varchar │ │ varchar │ varchar │\n",
"├──────────────────────┼──────────────────────┼──────────────────────┼───┼───────────────────┼────────────────┤\n",
"│ 881ecb36-2819-54c3… │ Izmenjen-clan-17-P… │ /Users/vasa/Projec… │ … │ 1710323687.737153 │ hvdIIsqChgxUUg │\n",
"├──────────────────────┴──────────────────────┴──────────────────────┴───┴───────────────────┴────────────────┤\n",
"│ 1 rows 8 columns (5 shown) │\n",
"└─────────────────────────────────────────────────────────────────────────────────────────────────────────────┘\n",
"\n"
]
}
],
"source": [
"import duckdb\n",
"from cognitive_architecture.root_dir import get_absolute_path\n",