chore: add prompt viz, add new display for classifier and adjust layo…

…ut for home

app/Home.py

@@ -16,7 +16,7 @@
 # st.image("./data/logo/logo.png", width=300)
 
 DEFAULT_OBJECT = "water_level"
-st.markdown("# Mapa de Alagamentos | Vision AI")
+st.markdown("# Identificações | Vision AI")
 
 # get cameras
 cameras = get_cameras(
@@ -84,7 +84,6 @@
         "timestamp",
         "object",
         "label",
-        "label_explanation",
     ]
     selected_row = get_agrid_table(
         cameras_identifications_merged[selected_cols].reset_index()
@@ -113,6 +112,7 @@
         )
 
 with col1:
+    st.markdown("### 📍 Mapa")
     st_folium(folium_map, key="fig1", height=600, width="100%")
 
     # for camera_id in cameras_identifications_filter.index:

app/pages/Classificador de Labels.py

@@ -34,7 +34,7 @@ def get_translation(label):
         },
         {
             "object": "water_in_road",
-            "title": "Há água na via?",
+            "title": "Há indício de chuva?",
             "condition": "Se a resposta for 'Não', associe o rótulo ‘Baixa ou Indiferente’ à opção 3 e pule para 4.",  # noqa
             "explanation": " Inspeção visual para presença de água na pista, que pode variar desde uma leve umidade até condições de alagamento evidente.",  # noqa
             "labels": {
@@ -104,6 +104,14 @@ def get_translation(label):
     pd.DataFrame(data=snapshots), "snapshot_identification"
 )  # noqa
 
+objects_number = {
+    object_name: i + 1
+    for i, object_name in enumerate(
+        snapshots_objects["object"].unique().tolist()
+    )  # noqa
+}
+snapshots_objects["question_number"] = snapshots_objects["object"].map(objects_number)
+
 
 def put_selected_label(label, snapshots_options):
     snapshots_to_put = snapshots_options.to_dict()
@@ -162,13 +170,11 @@ def buttom(
 else:
     # Get the current image from the DataFrame
     row = snapshots_objects.iloc[st.session_state.row_index]  # noqa
-    st.write(
-        f"INDEX: {st.session_state.row_index +1} / {len(snapshots_objects)}"  # noqa
-    )  # noqa
     # Extract relevant information
     name = row["object"]
     translate_dict = get_translation(name)
     snapshot_url = row["snapshot_url"]
+    question_number = row["question_number"]
 
     labels_options = labels.loc[name]
     choices = labels_options["value"].tolist()
@@ -177,33 +183,31 @@ def buttom(
         choices = ["true", "false"]
 
     # st.write"
-    col1, col2, col3 = st.columns(3)
+    col1, col2 = st.columns(2)
     with col2:
         st.image(snapshot_url)
+    with col1:
         st.markdown(
-            f"### {translate_dict.get('title')}",
+            f"### {question_number}.  {translate_dict.get('title')}",
         )
         st.markdown(
             f"**Explicação:** {translate_dict.get('explanation')}",
         )
     # place labels in a grid of 2 columns
-    col1, col2, col3, col4, col5, col6 = st.columns(6)
     for i, label in enumerate(choices):
         label_translated = translate_dict.get("labels").get(label)
-
-        if i % 2 == 0:
-            with col3:
-                buttom(
-                    label=label,
-                    label_translated=label_translated,
-                    row=row,
-                )
-        else:
-            with col4:
-                buttom(
-                    label=label,
-                    label_translated=label_translated,
-                    row=row,
-                )
+        with col1:
+            buttom(
+                label=label,
+                label_translated=label_translated,
+                row=row,
+            )
+        # else:
+        #     with col4:
+        #         buttom(
+        #             label=label,
+        #             label_translated=label_translated,
+        #             row=row,
+        #         )
 
     st.session_state.row_index += 1  # noqa

app/pages/Visualizar Prompt.py

@@ -0,0 +1,33 @@
+# -*- coding: utf-8 -*-
+import pandas as pd
+import streamlit as st
+from utils.utils import get_objects, get_objetcs_labels_df, get_prompts
+
+st.set_page_config(layout="wide", initial_sidebar_state="collapsed")
+# st.image("./data/logo/logo.png", width=300)
+
+st.markdown("# Visualizar Prompt | Vision AI")
+
+data = get_prompts()
+objects = pd.DataFrame(get_objects())
+labels = get_objetcs_labels_df(objects)
+
+prompt_parameters = data[0]
+prompt_text = prompt_parameters.get("prompt_text")
+prompt_objects = prompt_parameters.get("objects")
+
+selected_labels_cols = ["name", "criteria", "identification_guide", "value"]
+labels = labels[selected_labels_cols]
+labels = labels[labels["name"].isin(prompt_objects)]
+objects_table_md = labels.to_markdown(index=False)
+
+
+output_schema = """{\n    "$defs": {\n        "Object": {\n            "properties": {\n                "object": {\n"description": "The object from the objects table",\n"title": "Object",\n"type": "string"\n                },\n                "label_explanation": {\n"description": "Highly detailed visual description of the image given the object context",\n"title": "Label Explanation",\n"type": "string"\n                },\n                "label": {\n"anyOf": [\n    {\n        "type": "boolean"\n    },\n    {\n        "type": "string"\n    },\n    {\n        "type": "null"\n    }\n],\n"description": "Label indicating the condition or characteristic of the object",\n"title": "Label"\n                }\n            },\n            "required": [\n                "object",\n                "label_explanation",\n                "label"\n            ],\n            "title": "Object",\n            "type": "object"\n        }\n    },\n    "properties": {\n        "objects": {\n            "items": {\n                "$ref": "#/$defs/Object"\n            },\n            "title": "Objects",\n            "type": "array"\n        }\n    },\n    "required": [\n        "objects"\n    ],\n    "title": "Output",\n    "type": "object"\n}\n"""  # noqa
+output_example = """{\n    "objects": [\n        {\n            "object": "<Object from objects table>",\n            "label_explanation": "<Visual description of the image given the object context>",\n            "label": "<Selected label from objects table>"\n        }\n    ]\n}\n"""  # noqa
+
+prompt_text = (
+    prompt_text.replace("{objects_table_md}", objects_table_md)
+    .replace("{output_schema}", output_schema)
+    .replace("{output_example}", output_example)
+)
+st.markdown(prompt_text)

app/utils/utils.py

@@ -54,12 +54,12 @@ def callback_data():
 # )
 
 
-@st.cache_data(ttl=600 * 2, persist=False)
+@st.cache_data(ttl=60 * 5, persist=False)
 def get_cameras(
     only_active=True,
     use_mock_data=False,
     update_mock_data=False,
-    page_size=100,
+    page_size=3000,
     timeout=120,
 ):
     mock_data_path = "./data/temp/mock_api_data.json"
@@ -86,7 +86,7 @@ def get_cameras(
     return data
 
 
-@st.cache_data(ttl=600 * 2, persist=False)
+@st.cache_data(ttl=60 * 2, persist=False)
 def get_objects(
     page_size=100,
     timeout=120,
@@ -97,6 +97,17 @@ def get_objects(
     return data
 
 
+@st.cache_data(ttl=60 * 60, persist=False)
+def get_prompts(
+    page_size=100,
+    timeout=120,
+):
+    data = vision_api._get_all_pages(
+        path="/prompts", page_size=page_size, timeout=timeout
+    )
+    return data
+
+
 def treat_data(response):
     cameras_aux = pd.read_csv("./data/database/cameras_aux.csv", dtype=str)
     cameras_aux = cameras_aux.rename(columns={"id_camera": "id"}).set_index(
@@ -211,19 +222,24 @@ def display_camera_details(row, cameras_identifications):
 
     st.markdown(f"### 📷 Camera snapshot")  # noqa
     st.markdown(f"Endereço: {camera_name}")
-    # st.markdown(f"Data Snapshot: {snapshot_timestamp}")
+    st.markdown(f"Data Snapshot: {snapshot_timestamp}")
 
     # get cameras_attr url from selected row by id
     if image_url is None:
         st.markdown("Falha ao capturar o snapshot da câmera.")
     else:
         st.markdown(
-            f"""<img src='{image_url}' style='max-height: 600px;'> """,
+            f"""<img src='{image_url}' style='max-width: 100%; max-height: 100%;'> """,  # noqa
             unsafe_allow_html=True,
         )
+        st.markdown("<br><br><br><br>", unsafe_allow_html=True)
+
+    st.markdown(f"### 📃 Identificações")
 
     camera_identifications = cameras_identifications.loc[camera_id]  # noqa
-    get_agrid_table(table=camera_identifications.reset_index())
+    selected_cols = ["object", "label", "label_explanation"]
+
+    st.dataframe(camera_identifications[selected_cols].reset_index())
 
 
 def get_icon_color(label: Union[bool, None]):

pyproject.toml

@@ -14,6 +14,7 @@ streamlit-extras = "^0.3.5"
 streamlit-autorefresh = "^1.0.1"
 pillow = "^10.1.0"
 streamlit-aggrid = "0.3.4.post3"
+tabulate = "^0.9.0"
 
 
 [build-system]