Compare commits

...
14 Commits
25 changed files with 473 additions and 310 deletions
Generated
+1 -35
View File
@@ -251,23 +251,6 @@ files = [
{file = "dash_table-5.0.0.tar.gz", hash = "sha256:18624d693d4c8ef2ddec99a6f167593437a7ea0bf153aa20f318c170c5bc7308"}, {file = "dash_table-5.0.0.tar.gz", hash = "sha256:18624d693d4c8ef2ddec99a6f167593437a7ea0bf153aa20f318c170c5bc7308"},
] ]
[[package]]
name = "discord-webhook"
version = "1.3.1"
description = "Easily send Discord webhooks with Python"
optional = false
python-versions = ">=3.10,<4.0"
files = [
{file = "discord_webhook-1.3.1-py3-none-any.whl", hash = "sha256:ede07028316de76d24eb811836e2b818b2017510da786777adcb0d5970e7af79"},
{file = "discord_webhook-1.3.1.tar.gz", hash = "sha256:ee3e0f3ea4f3dc8dc42be91f75b894a01624c6c13fea28e23ebcf9a6c9a304f7"},
]
[package.dependencies]
requests = ">=2.28.1,<3.0.0"
[package.extras]
async = ["httpx (>=0.23.0,<0.24.0)"]
[[package]] [[package]]
name = "dnspython" name = "dnspython"
version = "2.6.1" version = "2.6.1"
@@ -806,23 +789,6 @@ files = [
[package.extras] [package.extras]
cli = ["click (>=5.0)"] cli = ["click (>=5.0)"]
[[package]]
name = "python-logging-discord-handler"
version = "0.1.4"
description = "Discord handler for Python logging framework"
optional = false
python-versions = ">=3.8,<4.0"
files = [
{file = "python_logging_discord_handler-0.1.4-py3-none-any.whl", hash = "sha256:b804b48e3f5af8c9c781a9afe8243c806f01521662e38a60fcda2c3631d27f4f"},
{file = "python_logging_discord_handler-0.1.4.tar.gz", hash = "sha256:8bfa839b6503b3b87e5851dd13bc5ff80bf2fadb496ac22c338ac10bd926f75a"},
]
[package.dependencies]
discord-webhook = ">=1.0.0,<2.0.0"
[package.extras]
docs = ["Sphinx (>=4.4.0,<5.0.0)", "sphinx-autodoc-typehints[docs] (>=1.16.0,<2.0.0)", "sphinx-rtd-theme (>=1.0.0,<2.0.0)", "sphinx-sitemap (>=2.2.0,<3.0.0)"]
[[package]] [[package]]
name = "requests" name = "requests"
version = "2.31.0" version = "2.31.0"
@@ -962,4 +928,4 @@ testing = ["big-O", "jaraco.functools", "jaraco.itertools", "more-itertools", "p
[metadata] [metadata]
lock-version = "2.0" lock-version = "2.0"
python-versions = "^3.12" python-versions = "^3.12"
content-hash = "e4aacea5a98281d935411e0d96152d1d24680f6c1e5288e9a1be913a0536b78e" content-hash = "9146cd32f0af25ddc99e5950dbf6ebc5a249f16238834b9a5db8d1b45fa9efb9"
-1
View File
@@ -11,7 +11,6 @@ packages = [
[tool.poetry.dependencies] [tool.poetry.dependencies]
python = "^3.12" python = "^3.12"
gunicorn = "^21.2.0" gunicorn = "^21.2.0"
python-logging-discord-handler = "^0.1.4"
python-dotenv = "^1.0.1" python-dotenv = "^1.0.1"
dash = "^2.15.0" dash = "^2.15.0"
dash-bootstrap-components = "^1.5.0" dash-bootstrap-components = "^1.5.0"
+7 -1
View File
@@ -1,5 +1,11 @@
from .classes import ( from .classes import (
ModelOutputs, ModelOutputs,
VisualCommunication VisualCommunication,
NoDocumentFoundException
) )
from .database import connect from .database import connect
from .utils import (
total_documents,
total_annotated,
get_visual_communication
)
+14 -1
View File
@@ -3,6 +3,7 @@ from pydantic import BaseModel, field_validator, field_serializer
from PIL import Image from PIL import Image
from io import BytesIO from io import BytesIO
from pathlib import Path from pathlib import Path
from base64 import b64encode
from src.model_experiential import ExperientialModelOutput from src.model_experiential import ExperientialModelOutput
from src.model_interpersonal import ( from src.model_interpersonal import (
@@ -36,7 +37,7 @@ class ModelOutputs(BaseModel):
class VisualCommunication(BaseModel): class VisualCommunication(BaseModel):
name: str name: str
image: Image.Image | BytesIO | bytes image: Image.Image
annotation: ModelOutputs | None = None annotation: ModelOutputs | None = None
prediction: ModelOutputs | None = None prediction: ModelOutputs | None = None
@@ -73,3 +74,15 @@ class VisualCommunication(BaseModel):
def __repr__(self) -> str: def __repr__(self) -> str:
return f"{self.classname()}(name='{self.name}')" return f"{self.classname()}(name='{self.name}')"
def webencoded_image(self) -> str:
"""Convert image to be displayed on webpage."""
# convert images to bytes string
buffer = BytesIO()
self.image.save(buffer, format="png")
img_enc = b64encode(buffer.getvalue()).decode("utf-8")
return img_enc
class NoDocumentFoundException(Exception):
pass
+3
View File
@@ -1,7 +1,9 @@
from pymongo import MongoClient from pymongo import MongoClient
from dotenv import load_dotenv from dotenv import load_dotenv
import logging
import os import os
def connect(): def connect():
"""Connect to MongoDB.""" """Connect to MongoDB."""
# load env vars # load env vars
@@ -18,4 +20,5 @@ def connect():
db = client[os.getenv("MONGO_DB")] db = client[os.getenv("MONGO_DB")]
collection = db[os.getenv("MONGO_COLLECTION")] collection = db[os.getenv("MONGO_COLLECTION")]
collection.create_index("name", unique=True) collection.create_index("name", unique=True)
logging.info("connected to database")
return collection, db, client return collection, db, client
+48
View File
@@ -0,0 +1,48 @@
from pymongo.collection import Collection
from .classes import (
VisualCommunication,
NoDocumentFoundException
)
def total_documents(
collection: Collection
) -> int:
"""Get total number of documents in database."""
return collection.count_documents(filter={})
def total_annotated(
collection: Collection
) -> int:
"""Get total number of annotated documents in database."""
query = {
"annotation": { "$ne": None }
}
return collection.count_documents(filter=query)
def get_visual_communication(
collection: Collection,
with_annotation: bool = False,
with_prediction: bool = False
) -> VisualCommunication:
"""Get a random visual communication from the database."""
query = {}
if with_annotation:
query["annotation"] = {"$ne": None}
else:
query["annotation"] = None
if with_prediction:
query["prediction"] = {"$ne": None}
else:
query["prediction"] = None
data = collection.aggregate([
{ "$match": query }, # find using filters
{ "$sample": { "size": 1 } } # get one random
])
data = list(data) # read data from cursor object
if len(data) == 0:
raise NoDocumentFoundException
return VisualCommunication.model_validate(data[0])
-6
View File
@@ -1,6 +0,0 @@
[main]
logger_level=debug
[discord]
service_name=visual_critical_discourse_analysis
logger_level=warning
+33 -84
View File
@@ -1,99 +1,48 @@
import logging import logging
from discord_logging.handler import DiscordHandler
from dotenv import load_dotenv from dotenv import load_dotenv
from configparser import ConfigParser
from pathlib import Path from pathlib import Path
import logging import logging
import os import os
from src.web import server # prepare optional local setup
env_path = Path(__file__).parent.parent / "local.env"
load_dotenv(env_path)
# load default values # ensure env vars set
config = ConfigParser() necesasary_var_list = {
config.read(Path(__file__).parent / 'defaults.ini') "MONGO_HOST",
LOGGER_LEVEL = config.get('main', 'logger_level') "MONGO_DB",
DISCORD_SERVICE_NAME = config.get('discord', 'service_name') "MONGO_COLLECTION",
DISCORD_LOGGER_LEVEL = config.get('discord', 'logger_level') "MONGO_USER",
"MONGO_PASSWORD",
}
def setup_logging( for env_var in necesasary_var_list:
discord_webhook_url: str, # ensure env var set
discord_service_name: str = DISCORD_SERVICE_NAME, assert (
discord_logger_level: str = DISCORD_LOGGER_LEVEL, env_var in os.environ
logger_level: str = LOGGER_LEVEL, ), (
) -> None: f"environment variable not set: {env_var}"
# setup stream handler
fmt = (
'%(asctime)s | '
'%(levelname)s | '
'%(filename)s | '
'%(funcName)s | '
'%(message)s'
) )
datefmt = '%Y-%m-%d %H:%M:%S'
level = getattr(logging, logger_level.upper())
logging.basicConfig(format=fmt, datefmt=datefmt, level=level)
logger = logging.getLogger()
# add discord handler
discord_handler = DiscordHandler(
service_name=discord_service_name,
webhook_url=discord_webhook_url,
)
discord_handler.setFormatter(logging.Formatter('%(message)s'))
level = getattr(logging, discord_logger_level.upper())
discord_handler.setLevel(level=level)
logger.addHandler(discord_handler)
logging.debug('finished')
# setup logging stream handler
fmt = (
'%(asctime)s | '
'%(levelname)s | '
'%(filename)s | '
'%(funcName)s | '
'%(message)s'
)
datefmt = '%Y-%m-%d %H:%M:%S'
logging.basicConfig(format=fmt, datefmt=datefmt, level=logging.INFO)
def initialise_app() -> None: logging.info("initialized app")
"""
Ensure all necessary environment variables are provided
"""
# load env vars
load_dotenv()
# ensure env vars set
necesasary_var_map = {
'LOGGER_LEVEL': False,
'DISCORD_SERVICE_NAME': False,
'DISCORD_WEBHOOK_URL': True,
'DISCORD_LOGGER_LEVEL': False,
'DATABASE_HOST': True,
'DATABASE_PORT': True,
'DATABASE_ENGINE': True,
'DATABASE_DATABASE': True,
'DATABASE_USERNAME': True,
'DATABASE_PASSWORD': True,
}
for env_var, must_be_set in necesasary_var_map.items():
if must_be_set:
# ensure env var set
assert (
env_var in os.environ
), (
f"environment variable not set: {env_var}"
)
# set variable from env var
locals()[env_var.lower()] = os.getenv(key=env_var)
else:
# ensure default value set
assert env_var in globals(), f"default variable not set: {env_var}"
# set variable from env var with backup from default value
locals()[env_var.lower()] = os.getenv(
key=env_var,
default=globals()[env_var]
)
setup_logging(
discord_webhook_url=locals()['discord_webhook_url'],
discord_service_name=locals()['discord_service_name'],
discord_logger_level=locals()['discord_logger_level'],
logger_level=locals()['logger_level'],
)
logging.debug('finished')
from src.web import app
server = app.server
if __name__ == "__main__": if __name__ == "__main__":
from src.web import app # prepare local env vars
# initialise_app() os.environ["MONGO_HOST"] = "localhost"
# run app
app.run(debug=True) app.run(debug=True)
logging.info("started app") logging.info("started app")
+61 -24
View File
@@ -1,28 +1,65 @@
from dash import Dash, html, Input, Output, State, page_container, page_registry from dash import Dash, Input, Output
import dash_bootstrap_components as dbc import dash_bootstrap_components as dbc
import dash_mantine_components as dmc import logging
from .header import generate_header from .layout import app_layout
from .body import generate_body from src.database import (
connect,
get_visual_communication,
app = Dash(__name__, external_stylesheets=[dbc.themes.BOOTSTRAP]) NoDocumentFoundException
server = app.server
app.layout = dmc.MantineProvider(
theme={
'fontFamily': '"Inter", sans-serif',
"components": {
"NavLink":{'styles':{'label':{'color':'#c2c7d0'}}}
},
},
children=[
dmc.Container(
[
generate_header(),
generate_body(),
], fluid=True
),
],
) )
# setup app
app = Dash(__name__, external_stylesheets=[dbc.themes.BOOTSTRAP])
app.title = "visual critical discourse analysis".title()
app.layout = app_layout
server = app.server
# connect to database
collection, db, client = connect()
# define callbacks
@app.callback(
Output("alert-element", "is_open"),
Output("alert-element", "children"),
Input("alert-message", "data")
)
def show_alert(
msg: str | None
):
if msg is None:
return False, ""
return True, msg
@app.callback(
Output("alert-message", "data"),
Output("visual-communication-name", "data"),
Output("image-container", "src"),
Input("next-button", "n_clicks"),
prevent_initial_call=True
)
def load_unannotated_visual_communication_data(
n_clicks: int
):
global collection
try:
vis_com = get_visual_communication(
collection=collection,
with_annotation=False
)
except NoDocumentFoundException:
return (
"Did not find any unannotated data in database",
None,
""
)
# prepare return values
alert_message = None
vis_com_name = vis_com.name
img_src = f"data:image/png;base64, {vis_com.webencoded_image()}"
logging.info("updated visual communication")
return (
alert_message,
vis_com_name,
img_src
)
-143
View File
@@ -1,143 +0,0 @@
import dash_mantine_components as dmc
from dash import dcc, html
from typing import List
from src.model_experiential import ExperientialModelOutput
from src.model_interpersonal import (
ContactModelOutput,
AngleModelOutput,
PointOfViewModelOutput,
DistanceModelOutput,
ModalityLightingModelOutput,
ModalityColorModelOutput,
ModalityDepthModelOutput
)
from src.model_textual import (
InformationValueModelOutput,
FramingModelOutput,
SalienceModelOutput
)
def generate_option_labels(model) -> List[str]:
"""Generate presentable list of attributes from an OutputModel."""
labels = [
label.replace('_', ' ').title()
for label in model.list_fields()
]
return labels
def generate_experiential_options_map():
"""Generate map of titles and options for experiential labels."""
options_map = {}
# add experiential labels
options_map["experiential".title()] = generate_option_labels(ExperientialModelOutput)
return options_map
def generate_interpersonal_options_map():
"""Generate map of titles and options for interpersonal labels."""
options_map = {}
# add interpersonal labels
options_map["contact".title()] = generate_option_labels(ContactModelOutput)
options_map["angle".title()] = generate_option_labels(AngleModelOutput)
options_map["point of view".title()] = generate_option_labels(PointOfViewModelOutput)
options_map["distance".title()] = generate_option_labels(DistanceModelOutput)
options_map["modality lighting".title()] = generate_option_labels(ModalityLightingModelOutput)
options_map["modality color".title()] = generate_option_labels(ModalityColorModelOutput)
options_map["modality depth".title()] = generate_option_labels(ModalityDepthModelOutput)
return options_map
def generate_textual_options_map():
"""Generate map of titles and options for textual labels."""
options_map = {}
# add textual labels
options_map["information value".title()] = generate_option_labels(InformationValueModelOutput)
options_map["framing".title()] = generate_option_labels(FramingModelOutput)
options_map["salience".title()] = generate_option_labels(SalienceModelOutput)
return options_map
def generate_body():
image_container = dmc.Image(
width=600,
height=600,
withPlaceholder=True,
placeholder=[dmc.Loader(color="gray", size="md")],
)
# prepare experiential container
experiential_map = generate_experiential_options_map()
experiential_container = dmc.Col(
children=[
dmc.Container([
html.H4(list(experiential_map.keys())[0]),
html.B("visual syntax".title()),
dcc.RadioItems(options=list(experiential_map.values())[0]),
])
], span=4
)
# prepare interpersonal container
interpersonal_map = generate_interpersonal_options_map()
interpersonal_container = dmc.Col(
children=[
html.H4("interpersonal".title()),
], span=4
)
for title, options in interpersonal_map.items():
interpersonal_container.children.append(
dmc.Container([
html.B(title),
dcc.RadioItems(options)
])
)
# prepare textual container
textual_map = generate_textual_options_map()
textual_container = dmc.Col(
children=[
html.H4("textual".title()),
], span=4
)
for title, options in textual_map.items():
textual_container.children.append(
dmc.Container([
html.B(title),
dcc.RadioItems(options)
])
)
# prepare labels container
label_container = dmc.Grid(
children=[
experiential_container,
interpersonal_container,
textual_container,
],
)
# build the full body container
body_container = dmc.Container(
dmc.Grid(
children=[
dmc.Col(
dmc.Center(
image_container,
),
span=5,
),
dmc.Col(
# radio buttons part
children = [
label_container,
dmc.Button(
"confirm",
id="submit-button",
fullWidth=True,
color="lime",
radius="sm",
size="md",
style={
"height": "50px"
}
),
], span=7,
),
# dmc.Col(span=1),
], grow=True
), fluid=True
)
return body_container
-15
View File
@@ -1,15 +0,0 @@
import dash_mantine_components as dmc
from dash import html
def generate_header():
header = dmc.Header(
height=80,
children=[
dmc.Container(
children=[
html.H2(children="Visual Critical Discourse Analysis Tool", style={"margin-left": "20px", "padding-top": "-5px"}),
], size="xl", px="xl",
),
]
)
return header
+1
View File
@@ -0,0 +1 @@
from .layout import app_layout
+15
View File
@@ -0,0 +1,15 @@
from dash import html, dcc
import dash_bootstrap_components as dbc
alerts_element = html.Div(
children=[
dbc.Alert(
children="",
id="alert-element",
dismissable=True,
fade=False,
is_open=False,
)
]
)
+20
View File
@@ -0,0 +1,20 @@
import dash_mantine_components as dmc
from dash import dcc, html
from typing import List
from .image import image_element
from .inputs import inputs_element
body_element = dmc.Container(
fluid=True,
children=[
dmc.Grid(
grow=True,
children=[
dmc.Col([image_element], span=5),
dmc.Col([inputs_element], span=7)
],
)
],
)
+21
View File
@@ -0,0 +1,21 @@
import dash_mantine_components as dmc
from dash import html
header_element = dmc.Header(
height=80,
children=[
dmc.Container(
children=[
html.H2(
children="Visual Critical Discourse Analysis Tool",
style={
"margin-left": "20px",
"padding-top": "-5px"
},
),
],
size="xl", px="xl",
),
]
)
+19
View File
@@ -0,0 +1,19 @@
import dash_mantine_components as dmc
from dash import html
from pathlib import Path
from base64 import b64encode
# read init img
init_img_path = Path(__file__).parent / "init_img.png"
with open(init_img_path.absolute(), "rb") as fh:
init_img_enc = b64encode(fh.read()).decode("utf-8")
image_element = dmc.Center(
html.Img(
style={
"width": "100%",
},
id="image-container",
src=f"data:image/png;base64, {init_img_enc}"
)
)
Binary file not shown.

After

Width:  |  Height:  |  Size: 9.3 KiB

+22
View File
@@ -0,0 +1,22 @@
import dash_mantine_components as dmc
from .labels import labels_element
next_button = dmc.Button(
"next".title(),
id="next-button",
fullWidth=True,
color="lime",
radius="sm",
size="md",
style={
"height": "50px"
}
)
inputs_element = dmc.SimpleGrid(
children=[
labels_element,
next_button
]
)
+104
View File
@@ -0,0 +1,104 @@
from dash import html, dcc
import dash_mantine_components as dmc
from typing import List
from src.model_experiential import ExperientialModelOutput
from src.model_interpersonal import (
ContactModelOutput,
AngleModelOutput,
PointOfViewModelOutput,
DistanceModelOutput,
ModalityLightingModelOutput,
ModalityColorModelOutput,
ModalityDepthModelOutput
)
from src.model_textual import (
InformationValueModelOutput,
FramingModelOutput,
SalienceModelOutput
)
def generate_option_labels(model) -> List[str]:
"""Generate presentable list of attributes from an OutputModel."""
labels = [
label.replace('_', ' ').title()
for label in model.list_fields()
]
return labels
def generate_experiential_options_map():
"""Generate map of titles and options for experiential labels."""
options_map = {}
# add experiential labels
options_map["experiential".title()] = generate_option_labels(ExperientialModelOutput)
return options_map
def generate_interpersonal_options_map():
"""Generate map of titles and options for interpersonal labels."""
options_map = {}
# add interpersonal labels
options_map["contact".title()] = generate_option_labels(ContactModelOutput)
options_map["angle".title()] = generate_option_labels(AngleModelOutput)
options_map["point of view".title()] = generate_option_labels(PointOfViewModelOutput)
options_map["distance".title()] = generate_option_labels(DistanceModelOutput)
options_map["modality lighting".title()] = generate_option_labels(ModalityLightingModelOutput)
options_map["modality color".title()] = generate_option_labels(ModalityColorModelOutput)
options_map["modality depth".title()] = generate_option_labels(ModalityDepthModelOutput)
return options_map
def generate_textual_options_map():
"""Generate map of titles and options for textual labels."""
options_map = {}
# add textual labels
options_map["information value".title()] = generate_option_labels(InformationValueModelOutput)
options_map["framing".title()] = generate_option_labels(FramingModelOutput)
options_map["salience".title()] = generate_option_labels(SalienceModelOutput)
return options_map
# prepare experiential container
experiential_map = generate_experiential_options_map()
experiential_container = dmc.Col(
children=[
dmc.Container([
html.H4(list(experiential_map.keys())[0]),
html.B("visual syntax".title()),
dcc.RadioItems(options=list(experiential_map.values())[0]),
])
], span=5
)
# prepare interpersonal container
interpersonal_map = generate_interpersonal_options_map()
interpersonal_container = dmc.Col(
children=[
html.H4("interpersonal".title()),
], span=3
)
for title, options in interpersonal_map.items():
interpersonal_container.children.append(
dmc.Container([
html.B(title),
dcc.RadioItems(options)
])
)
# prepare textual container
textual_map = generate_textual_options_map()
textual_container = dmc.Col(
children=[
html.H4("textual".title()),
], span=4
)
for title, options in textual_map.items():
textual_container.children.append(
dmc.Container([
html.B(title),
dcc.RadioItems(options)
])
)
labels_element = dmc.Grid(
children=[
experiential_container,
interpersonal_container,
textual_container,
]
)
+35
View File
@@ -0,0 +1,35 @@
from dash import dcc
import dash_mantine_components as dmc
from .stores import stores_element
from .alerts import alerts_element
from .header import header_element
from .body import body_element
app_layout = dmc.MantineProvider(
theme={
"fontFamily": '"Inter", sans-serif',
"components": {
"NavLink": {
"styles": {
"label": {
"color": "#c2c7d0"
}
}
}
},
},
children=[
stores_element,
alerts_element,
dmc.Container(
children=[
header_element,
body_element,
],
fluid=True
),
]
)
+9
View File
@@ -0,0 +1,9 @@
from dash import html, dcc
stores_element = html.Div(
children=[
dcc.Store(id="alert-message", storage_type="session"),
dcc.Store(id="visual-communication-name", storage_type="session"),
]
)
+21
View File
@@ -0,0 +1,21 @@
from pathlib import Path
from dotenv import load_dotenv
import os
from src.database import (
connect,
get_visual_communication
)
if __name__ == "__main__":
# prepare env vars
env_path = Path(__file__).parent.parent / "local.env"
assert env_path.exists()
load_dotenv(env_path)
os.environ["MONGO_HOST"] = "localhost"
# connect to database
collection, db, client = connect()
print(client.server_info())
# get visual communication
vis_com = get_visual_communication(collection)
print(vis_com.image)
+1 -2
View File
@@ -1,7 +1,5 @@
from pathlib import Path from pathlib import Path
from dotenv import load_dotenv from dotenv import load_dotenv
from pymongo import MongoClient
from typing import List
import os import os
from src.database import VisualCommunication, connect from src.database import VisualCommunication, connect
@@ -25,3 +23,4 @@ if __name__ == "__main__":
print(repr(vis_com)) print(repr(vis_com))
if data is not None: if data is not None:
print(vis_com.image) print(vis_com.image)
print(vis_com.model_dump())
+20
View File
@@ -0,0 +1,20 @@
from pathlib import Path
from dotenv import load_dotenv
import os
from src.database import (
connect,
total_annotated
)
if __name__ == "__main__":
# prepare env vars
env_path = Path(__file__).parent.parent / "local.env"
assert env_path.exists()
load_dotenv(env_path)
os.environ["MONGO_HOST"] = "localhost"
# connect to database
collection, db, client = connect()
# get visual communication
num_docs = total_annotated(collection)
print(f"number of annotated documents in database: {num_docs}")
+20
View File
@@ -0,0 +1,20 @@
from pathlib import Path
from dotenv import load_dotenv
import os
from src.database import (
connect,
total_documents
)
if __name__ == "__main__":
# prepare env vars
env_path = Path(__file__).parent.parent / "local.env"
assert env_path.exists()
load_dotenv(env_path)
os.environ["MONGO_HOST"] = "localhost"
# connect to database
collection, db, client = connect()
# get visual communication
num_docs = total_documents(collection)
print(f"total number of documents in database: {num_docs}")