fix: linting + text mistakes

app.py

@@ -8,21 +8,17 @@ from src.content import (
     LICENCE_TEXT,
     INTRO_TEXT,
     METHODOLOGY_TEXT,
-    SUPPORT_TEXT
+    SUPPORT_TEXT,
 )
 
 from src.expert import expert_mode
 from src.calculator import calculator_mode
 from src.token_estimator import token_estimator
 
-st.set_page_config(
-    layout="wide",
-    page_title="ECOLOGITS",
-    page_icon='💬'
-)
+st.set_page_config(layout="wide", page_title="ECOLOGITS", page_icon="💬")
 
-with open( "src/style.css" ) as css:
-    st.markdown( f'<style>{css.read()}</style>' , unsafe_allow_html= True)
+with open("src/style.css") as css:
+    st.markdown(f"<style>{css.read()}</style>", unsafe_allow_html=True)
 
 st.html(HERO_TEXT)
 
@@ -30,41 +26,36 @@ st.markdown(INTRO_TEXT, unsafe_allow_html=True)
 
 tab_calculator, tab_expert, tab_token, tab_method, tab_about, tab_support = st.tabs(
     [
-        '🧮 Calculator',
-        '🤓 Expert Mode',
-        '🪙 Tokens estimator',
-        '📖 Methodology',
-        'ℹ️ About',
-        '🩷 Support us'
+        "🧮 Calculator",
+        "🤓 Expert Mode",
+        "🪙 Tokens estimator",
+        "📖 Methodology",
+        "ℹ️ About",
+        "🩷 Support us",
     ]
 )
 
 with tab_calculator:
-
     calculator_mode()
 
 with tab_expert:
-
     expert_mode()
-    
+
 with tab_token:
-    
     token_estimator()
 
 with tab_method:
-
     st.write(METHODOLOGY_TEXT)
 
 with tab_about:
-
     st.markdown(ABOUT_TEXT, unsafe_allow_html=True)
 
 with tab_support:
     st.markdown(SUPPORT_TEXT, unsafe_allow_html=True)
 
 
-with st.expander('📚 Citation'):
+with st.expander("📚 Citation"):
     st.html(CITATION_LABEL)
     st.html(CITATION_TEXT)
 
-st.html(LICENCE_TEXT)
+st.html(LICENCE_TEXT)

src/__init__.py

@@ -6,4 +6,4 @@ from .utils import *
 from .calculator import calculator_mode
 from .impacts import get_impacts, display_impacts
 from .models import load_models
-from .electricity_mix import *
+from .electricity_mix import *

src/calculator.py

@@ -1,72 +1,101 @@
 import streamlit as st
 
 from ecologits.tracers.utils import llm_impacts
-from src.impacts import get_impacts, display_impacts, display_equivalent
+from src.impacts import display_impacts, display_equivalent
 from src.utils import format_impacts
 from src.content import WARNING_CLOSED_SOURCE, WARNING_MULTI_MODAL, WARNING_BOTH
 from src.models import load_models
 
 from src.constants import PROMPTS
 
-def calculator_mode():
 
+def calculator_mode():
     with st.container(border=True):
-        
         df = load_models(filter_main=True)
-        
+
         col1, col2, col3 = st.columns(3)
 
         with col1:
             provider = st.selectbox(
-                label = 'Provider',
-                options = [x for x in df['provider_clean'].unique()],
-                index = 7
+                label="Provider",
+                options=[x for x in df["provider_clean"].unique()],
+                index=7,
             )
 
         with col2:
             model = st.selectbox(
-                label = 'Model',
-                options = [x for x in df['name_clean'].unique() if x in df[df['provider_clean'] == provider]['name_clean'].unique()]
+                label="Model",
+                options=[
+                    x
+                    for x in df["name_clean"].unique()
+                    if x in df[df["provider_clean"] == provider]["name_clean"].unique()
+                ],
             )
 
         with col3:
-            output_tokens = st.selectbox('Example prompt', [x[0] for x in PROMPTS])
-            
+            output_tokens = st.selectbox("Example prompt", [x[0] for x in PROMPTS])
+
         # WARNING DISPLAY
-        provider_raw = df[(df['provider_clean'] == provider) & (df['name_clean'] == model)]['provider'].values[0]
-        model_raw = df[(df['provider_clean'] == provider) & (df['name_clean'] == model)]['name'].values[0]
+        provider_raw = df[
+            (df["provider_clean"] == provider) & (df["name_clean"] == model)
+        ]["provider"].values[0]
+        model_raw = df[
+            (df["provider_clean"] == provider) & (df["name_clean"] == model)
+        ]["name"].values[0]
 
-        df_filtered = df[(df['provider_clean'] == provider) & (df['name_clean'] == model)]
+        df_filtered = df[
+            (df["provider_clean"] == provider) & (df["name_clean"] == model)
+        ]
 
-        if df_filtered['warning_arch'].values[0] and not df_filtered['warning_multi_modal'].values[0]:
+        if (
+            df_filtered["warning_arch"].values[0]
+            and not df_filtered["warning_multi_modal"].values[0]
+        ):
             st.warning(WARNING_CLOSED_SOURCE)
-        if df_filtered['warning_multi_modal'].values[0] and not df_filtered['warning_arch'].values[0]:
+        if (
+            df_filtered["warning_multi_modal"].values[0]
+            and not df_filtered["warning_arch"].values[0]
+        ):
             st.warning(WARNING_MULTI_MODAL)
-        if df_filtered['warning_arch'].values[0] and df_filtered['warning_multi_modal'].values[0]:
+        if (
+            df_filtered["warning_arch"].values[0]
+            and df_filtered["warning_multi_modal"].values[0]
+        ):
             st.warning(WARNING_BOTH)
-            
-    try:
 
+    try:
         impacts = llm_impacts(
-                        provider=provider_raw,
-                        model_name=model_raw,
-                        output_token_count=[x[1] for x in PROMPTS if x[0] == output_tokens][0],
-                        request_latency=100000
-                    )
+            provider=provider_raw,
+            model_name=model_raw,
+            output_token_count=[x[1] for x in PROMPTS if x[0] == output_tokens][0],
+            request_latency=100000,
+        )
 
         impacts, _, _ = format_impacts(impacts)
-        
-        with st.container(border=True):
 
-            st.markdown('<h3 align = "center">Environmental impacts</h3>', unsafe_allow_html=True)
-            st.markdown('<p align = "center">To understand how the environmental impacts are computed go to the 📖 Methodology tab.</p>', unsafe_allow_html=True)
+        with st.container(border=True):
+            st.markdown(
+                '<h3 align = "center">Environmental impacts</h3>',
+                unsafe_allow_html=True,
+            )
+            st.markdown(
+                '<p align = "center">To understand how the environmental impacts are computed go to the 📖 Methodology tab.</p>',
+                unsafe_allow_html=True,
+            )
             display_impacts(impacts)
-        
+
         with st.container(border=True):
-            
-            st.markdown('<h3 align = "center">That\'s equivalent to ...</h3>', unsafe_allow_html=True)
-            st.markdown('<p align = "center">Making this request to the LLM is equivalent to the following actions :</p>', unsafe_allow_html=True)
+            st.markdown(
+                '<h3 align = "center">That\'s equivalent to ...</h3>',
+                unsafe_allow_html=True,
+            )
+            st.markdown(
+                '<p align = "center">Making this request to the LLM is equivalent to the following actions :</p>',
+                unsafe_allow_html=True,
+            )
             display_equivalent(impacts)
-            
-    except Exception as e:
-        st.error('Could not find the model in the repository. Please try another model.')
+
+    except Exception:
+        st.error(
+            "Could not find the model in the repository. Please try another model."
+        )

src/constants.py

@@ -4,99 +4,108 @@ PROMPTS = [
     ("Write an article summary", 250),
     ("Small conversation with a chatbot", 400),
     ("Write a report of 5 pages", 5000),
-    ("Write the code for this app", 15000)
+    ("Write the code for this app", 15000),
 ]
 PROMPTS = [(s + f" ({v} output tokens)", v) for (s, v) in PROMPTS]
 
 MODEL_REPOSITORY_URL = "https://raw.githubusercontent.com/genai-impact/ecologits/refs/heads/main/ecologits/data/models.json"
 
 main_models_openai = [
-    'chatgpt-4o-latest',
-    'gpt-3.5-turbo',
-    'gpt-4',
-    'gpt-4-turbo',
-    'gpt-4o',
-    'gpt-4o-mini',
-    'o1',
-    'o1-mini'
+    "chatgpt-4o-latest",
+    "gpt-3.5-turbo",
+    "gpt-4",
+    "gpt-4-turbo",
+    "gpt-4o",
+    "gpt-4o-mini",
+    "o1",
+    "o1-mini",
 ]
 
 main_models_meta = [
-    'meta-llama/Meta-Llama-3.1-8B',
-    'meta-llama/Meta-Llama-3.1-70B',
-    'meta-llama/Meta-Llama-3.1-405B',
-    'meta-llama/Meta-Llama-3-8B',
-    'meta-llama/Meta-Llama-3-70B',
-    'meta-llama/Meta-Llama-3-70B',
-    'meta-llama/Llama-2-7b',
-    'meta-llama/Llama-2-13b',
-    'meta-llama/Llama-2-70b',
-    'meta-llama/CodeLlama-7b-hf',
-    'meta-llama/CodeLlama-13b-hf',
-    'meta-llama/CodeLlama-34b-hf',
-    'meta-llama/CodeLlama-70b-hf'
+    "meta-llama/Meta-Llama-3.1-8B",
+    "meta-llama/Meta-Llama-3.1-70B",
+    "meta-llama/Meta-Llama-3.1-405B",
+    "meta-llama/Meta-Llama-3-8B",
+    "meta-llama/Meta-Llama-3-70B",
+    "meta-llama/Meta-Llama-3-70B",
+    "meta-llama/Llama-2-7b",
+    "meta-llama/Llama-2-13b",
+    "meta-llama/Llama-2-70b",
+    "meta-llama/CodeLlama-7b-hf",
+    "meta-llama/CodeLlama-13b-hf",
+    "meta-llama/CodeLlama-34b-hf",
+    "meta-llama/CodeLlama-70b-hf",
 ]
 
 main_models_msft = [
-    'microsoft/phi-1',
-    'microsoft/phi-1_5',
-    'microsoft/Phi-3-mini-128k-instruct',
-    'microsoft/Phi-3-small-128k-instruct',
-    'microsoft/Phi-3-medium-128k-instruct',
+    "microsoft/phi-1",
+    "microsoft/phi-1_5",
+    "microsoft/Phi-3-mini-128k-instruct",
+    "microsoft/Phi-3-small-128k-instruct",
+    "microsoft/Phi-3-medium-128k-instruct",
 ]
 
 main_models_anthropic = [
-    'claude-2.0',
-    'claude-2.1',
-    'claude-3-5-haiku-latest',
-    'claude-3-5-sonnet-latest',
-    'claude-3-7-sonnet-latest',
-    'claude-3-haiku-20240307',
-    'claude-3-opus-latest',
-    'claude-3-sonnet-20240229'
+    "claude-2.0",
+    "claude-2.1",
+    "claude-3-5-haiku-latest",
+    "claude-3-5-sonnet-latest",
+    "claude-3-7-sonnet-latest",
+    "claude-3-haiku-20240307",
+    "claude-3-opus-latest",
+    "claude-3-sonnet-20240229",
 ]
 
 main_models_cohere = [
-    'c4ai-aya-expanse-8b',
-    'c4ai-aya-expanse-32b',
-    'command',
-    'command-light',
-    'command-r',
-    'command-r-plus',
+    "c4ai-aya-expanse-8b",
+    "c4ai-aya-expanse-32b",
+    "command",
+    "command-light",
+    "command-r",
+    "command-r-plus",
 ]
 
 main_models_google = [
-    'google/gemma-2-2b',
-    'google/gemma-2-9b',
-    'google/gemma-2-27b',
-    'google/codegemma-2b',
-    'google/codegemma-7b',
-    'gemini-1.0-pro',
-    'gemini-1.5-pro',
-    'gemini-1.5-flash',
-    'gemini-2.0-flash'
+    "google/gemma-2-2b",
+    "google/gemma-2-9b",
+    "google/gemma-2-27b",
+    "google/codegemma-2b",
+    "google/codegemma-7b",
+    "gemini-1.0-pro",
+    "gemini-1.5-pro",
+    "gemini-1.5-flash",
+    "gemini-2.0-flash",
 ]
 
 main_models_databricks = [
-    'databricks/dolly-v1-6b',
-    'databricks/dolly-v2-12b',
-    'databricks/dolly-v2-7b',
-    'databricks/dolly-v2-3b',
-    'databricks/dbrx-base'
+    "databricks/dolly-v1-6b",
+    "databricks/dolly-v2-12b",
+    "databricks/dolly-v2-7b",
+    "databricks/dolly-v2-3b",
+    "databricks/dbrx-base",
 ]
 
 main_models_mistral = [
-    'mistralai/Mistral-7B-v0.3',
-    'mistralai/Mixtral-8x7B-v0.1',
-    'mistralai/Mixtral-8x22B-v0.1',
-    'mistralai/Codestral-22B-v0.1',
-    'mistralai/Mathstral-7B-v0.1',
-    'ministral-3b-latest',
-    'ministral-8b-latest',
-    'mistral-tiny',
-    'mistral-small',
-    'mistral-medium',
-    'mistral-large-latest'
+    "mistralai/Mistral-7B-v0.3",
+    "mistralai/Mixtral-8x7B-v0.1",
+    "mistralai/Mixtral-8x22B-v0.1",
+    "mistralai/Codestral-22B-v0.1",
+    "mistralai/Mathstral-7B-v0.1",
+    "ministral-3b-latest",
+    "ministral-8b-latest",
+    "mistral-tiny",
+    "mistral-small",
+    "mistral-medium",
+    "mistral-large-latest",
 ]
 
-MAIN_MODELS = main_models_meta + main_models_openai + main_models_anthropic + main_models_cohere + main_models_msft + main_models_mistral + main_models_databricks + main_models_google
+MAIN_MODELS = (
+    main_models_meta
+    + main_models_openai
+    + main_models_anthropic
+    + main_models_cohere
+    + main_models_msft
+    + main_models_mistral
+    + main_models_databricks
+    + main_models_google
+)

src/content.py

@@ -18,7 +18,7 @@ HERO_TEXT = """
 """
 
 INTRO_TEXT = """
-<div style="background-color:#d4edda; padding:5px; border-radius:10px; color:#155724;">
+<div align = "center"; style="background-color:#d4edda; padding:10px; border-radius:10px; color:#155724;">
 <p>
   EcoLogits Calculator is developed and maintained by 
   <a href = "https://genai-impact.org/" > GenAI Impact </a> non-profit. 
@@ -76,7 +76,7 @@ ABOUT_TEXT = r"""
 The rapid evolution of generative AI is reshaping numerous industries and aspects of our daily lives. While these 
 advancements offer some benefits, they also **pose substantial environmental challenges that cannot be overlooked**. 
 Plus the issue of AI's environmental footprint has been mainly discussed at training stage but rarely at the inference 
-stage. That is an issue because **inference impacts for LLMs can largely overcome the training impacts when deployed 
+stage. That is an issue because **inference impacts for large langauge models (LLMs) can largely overcome the training impacts when deployed 
 at large scales**.
 At **[GenAI Impact](https://genai-impact.org/) we are dedicated to understanding and mitigating the environmental 
 impacts of generative AI** through rigorous research, innovative tools, and community engagement. Especially, in early 
@@ -134,15 +134,17 @@ We also welcome any open-source contributions on 🌱 **[EcoLogits](https://gith
   <a href="https://creativecommons.org/licenses/by-sa/4.0/?ref=chooser-v1" target="_blank" rel="license noopener noreferrer" style="display:inline-block;">
     CC BY-SA 4.0
   </a>
-  <img style="display:inline-block;height:22px!important;margin-left:3px;vertical-align:text-bottom;" src="https://mirrors.creativecommons.org/presskit/icons/cc.svg?ref=chooser-v1" alt="">
-  <img style="display:inline-block;height:22px!important;margin-left:3px;vertical-align:text-bottom;" src="https://mirrors.creativecommons.org/presskit/icons/by.svg?ref=chooser-v1" alt="">
-  <img style="display:inline-block;height:22px!important;margin-left:3px;vertical-align:text-bottom;" src="https://mirrors.creativecommons.org/presskit/icons/sa.svg?ref=chooser-v1" alt="">
+  <br>
+  <br>
+  <img style="display:inline-block;height:5px!important;margin-left:3px;vertical-align:text-bottom;" src="https://mirrors.creativecommons.org/presskit/icons/cc.svg?ref=chooser-v1" alt="">
+  <img style="display:inline-block;height:5px!important;margin-left:3px;vertical-align:text-bottom;" src="https://mirrors.creativecommons.org/presskit/icons/by.svg?ref=chooser-v1" alt="">
+  <img style="display:inline-block;height:5px!important;margin-left:3px;vertical-align:text-bottom;" src="https://mirrors.creativecommons.org/presskit/icons/sa.svg?ref=chooser-v1" alt="">
 </p>
 
 ## 🙌 Acknowledgement
-We thank [Data For Good](https://dataforgood.fr/) and [Boavizta](https://boavizta.org/en) for supporting this project.
-Their contributions of tools, best practices, and expertise in environmental impact 
-assessment have been extremely valuable.
+We thank [Data For Good](https://dataforgood.fr/) and [Boavizta](https://boavizta.org/en) for supporting the 
+development of this project. Their contributions of tools, best practices, and expertise in environmental impact 
+assessment have been invaluable.
 We also extend our gratitude to the open-source contributions of 🤗 [Hugging Face](huggingface.com) on the LLM-Perf 
 Leaderboard.
 
@@ -150,6 +152,7 @@ Leaderboard.
 For general question on the project, please use the [GitHub thread](https://github.com/genai-impact/ecologits/discussions/45). 
 Otherwise use our contact form on [genai-impact.org/contact](https://genai-impact.org/contact/).
 """
+
 SUPPORT_TEXT = r"""
 ## How to support 
 At GenAI Impact, our projects are powered by the passion and dedication of our team. 
@@ -262,7 +265,7 @@ We multiply that value by the GHG emissions of the request to get an equivalent
 These equivalents are computed based on the request impacts scaled to a worldwide adoption use case. We imply that the
 same request is done 1% of the planet everyday for 1 year, and then compute impact equivalents.
 $$
-I_{scaled} = I_{request} * [1 \\% \ \text{of}\ 8B\ \text{people on earth}] * 365\ \text{days}
+I_{scaled} = I_{request} * [1 \% \ \text{of}\ 8B\ \text{people on earth}] * 365\ \text{days}
 $$
 #### Number of 💨 wind turbines or ☢️ nuclear plants
 We compare the ⚡️ direct energy consumption (scaled) by the energy production of wind turbines and nuclear power 
@@ -307,4 +310,4 @@ LICENCE_TEXT = """<p xmlns:cc="http://creativecommons.org/ns#" >
   <img style="display:inline-block;height:22px!important;margin-left:3px;vertical-align:text-bottom;" src="https://mirrors.creativecommons.org/presskit/icons/cc.svg?ref=chooser-v1" alt="">
   <img style="display:inline-block;height:22px!important;margin-left:3px;vertical-align:text-bottom;" src="https://mirrors.creativecommons.org/presskit/icons/by.svg?ref=chooser-v1" alt="">
   <img style="display:inline-block;height:22px!important;margin-left:3px;vertical-align:text-bottom;" src="https://mirrors.creativecommons.org/presskit/icons/sa.svg?ref=chooser-v1" alt="">
-</p>"""
+</p>"""

src/electricity_mix.py

@@ -142,7 +142,7 @@ COUNTRY_CODES = [
     ("🇦 Netherlands Antilles", "ANT"),
     ("🇦🇲 Armenia", "ARM"),
     ("🇦🇱 Albania", "ALB"),
-    ("🇦🇪 United Arab Emirates", "ARE")
+    ("🇦🇪 United Arab Emirates", "ARE"),
 ]
 
 
@@ -156,20 +156,19 @@ def find_electricity_mix(code: str):
             res += [float(row[code])]
     return res
 
-def dataframe_electricity_mix(countries: list):
 
-    df = pd.read_csv('src/data/electricity_mix.csv')
-    df['name_unit'] = df['name'] + ' (' + df['unit'] + ')'
-    df = df[['name_unit'] + [x[1] for x in COUNTRY_CODES if x[0] in countries]]
+def dataframe_electricity_mix(countries: list):
+    df = pd.read_csv("src/data/electricity_mix.csv")
+    df["name_unit"] = df["name"] + " (" + df["unit"] + ")"
+    df = df[["name_unit"] + [x[1] for x in COUNTRY_CODES if x[0] in countries]]
 
     df_melted = df.melt(
-        id_vars=['name_unit'],
+        id_vars=["name_unit"],
         value_vars=[x[1] for x in COUNTRY_CODES if x[0] in countries],
-        var_name='country',
-        value_name='value')
+        var_name="country",
+        value_name="value",
+    )
 
-    df = df_melted.pivot(columns='name_unit', 
-                        index='country',
-                        values='value')
+    df = df_melted.pivot(columns="name_unit", index="country", values="value")
 
-    return df
+    return df

src/expert.py

@@ -3,125 +3,176 @@ from ecologits.impacts.llm import compute_llm_impacts
 
 from src.utils import format_impacts, average_range_impacts
 from src.impacts import display_impacts
-from src.electricity_mix import COUNTRY_CODES, find_electricity_mix, dataframe_electricity_mix
+from src.electricity_mix import (
+    COUNTRY_CODES,
+    find_electricity_mix,
+    dataframe_electricity_mix,
+)
 from src.models import load_models
 from src.constants import PROMPTS
 
 import plotly.express as px
 
+
 def reset_model():
-    model = 'CUSTOM'
+    model = "CUSTOM"
 
-def expert_mode():
 
+def expert_mode():
     st.markdown("### 🤓 Expert mode")
 
-    with st.container(border = True):
-
+    with st.container(border=True):
         ########## Model info ##########
 
         col1, col2, col3 = st.columns(3)
-        
+
         df = load_models(filter_main=True)
 
         with col1:
             provider_exp = st.selectbox(
-                label = 'Provider',
-                options = [x for x in df['provider_clean'].unique()],
-                index = 7,
-                key = 1
+                label="Provider",
+                options=[x for x in df["provider_clean"].unique()],
+                index=7,
+                key=1,
             )
 
         with col2:
             model_exp = st.selectbox(
-                label = 'Model',
-                options = [x for x in df['name_clean'].unique() if x in df[df['provider_clean'] == provider_exp]['name_clean'].unique()],
-                key = 2
+                label="Model",
+                options=[
+                    x
+                    for x in df["name_clean"].unique()
+                    if x
+                    in df[df["provider_clean"] == provider_exp]["name_clean"].unique()
+                ],
+                key=2,
             )
 
         with col3:
             output_tokens_exp = st.selectbox(
-                label = 'Example prompt',
-                options = [x[0] for x in PROMPTS],
-                key = 3
+                label="Example prompt", options=[x[0] for x in PROMPTS], key=3
             )
-        
-        df_filtered = df[(df['provider_clean'] == provider_exp) & (df['name_clean'] == model_exp)]
+
+        df_filtered = df[
+            (df["provider_clean"] == provider_exp) & (df["name_clean"] == model_exp)
+        ]
 
         try:
-            total_params = int(df_filtered['total_parameters'].iloc[0])
+            total_params = int(df_filtered["total_parameters"].iloc[0])
         except:
-            total_params = int((df_filtered['total_parameters'].values[0]['min'] + df_filtered['total_parameters'].values[0]['max'])/2)
-            
+            total_params = int(
+                (
+                    df_filtered["total_parameters"].values[0]["min"]
+                    + df_filtered["total_parameters"].values[0]["max"]
+                )
+                / 2
+            )
+
         try:
-            active_params = int(df_filtered['active_parameters'].iloc[0])
+            active_params = int(df_filtered["active_parameters"].iloc[0])
         except:
-            active_params = int((df_filtered['active_parameters'].values[0]['min'] + df_filtered['active_parameters'].values[0]['max'])/2)
+            active_params = int(
+                (
+                    df_filtered["active_parameters"].values[0]["min"]
+                    + df_filtered["active_parameters"].values[0]["max"]
+                )
+                / 2
+            )
 
-        ########## Model parameters ##########   
+        ########## Model parameters ##########
 
         col11, col22, col33 = st.columns(3)
 
         with col11:
-            active_params = st.number_input('Active parameters (B)', 0, None, active_params)
+            active_params = st.number_input(
+                "Active parameters (B)", 0, None, active_params
+            )
 
         with col22:
-            total_params = st.number_input('Total parameters (B)', 0, None, total_params)
+            total_params = st.number_input(
+                "Total parameters (B)", 0, None, total_params
+            )
 
         with col33:
             output_tokens = st.number_input(
-                label = 'Output completion tokens',
-                min_value = 0,
-                value = [x[1] for x in PROMPTS if x[0] == output_tokens_exp][0]
+                label="Output completion tokens",
+                min_value=0,
+                value=[x[1] for x in PROMPTS if x[0] == output_tokens_exp][0],
             )
 
         ########## Electricity mix ##########
 
-        location = st.selectbox('Location', [x[0] for x in COUNTRY_CODES])
+        location = st.selectbox("Location", [x[0] for x in COUNTRY_CODES])
 
         col4, col5, col6 = st.columns(3)
 
         with col4:
-            mix_gwp = st.number_input('Electricity mix - GHG emissions [kgCO2eq / kWh]', find_electricity_mix([x[1] for x in COUNTRY_CODES if x[0] ==location][0])[2], format="%0.6f")
-            #disp_ranges = st.toggle('Display impact ranges', False)
+            mix_gwp = st.number_input(
+                "Electricity mix - GHG emissions [kgCO2eq / kWh]",
+                find_electricity_mix(
+                    [x[1] for x in COUNTRY_CODES if x[0] == location][0]
+                )[2],
+                format="%0.6f",
+            )
+            # disp_ranges = st.toggle('Display impact ranges', False)
         with col5:
-            mix_adpe = st.number_input('Electricity mix - Abiotic resources [kgSbeq / kWh]', find_electricity_mix([x[1] for x in COUNTRY_CODES if x[0] ==location][0])[0], format="%0.13f")
+            mix_adpe = st.number_input(
+                "Electricity mix - Abiotic resources [kgSbeq / kWh]",
+                find_electricity_mix(
+                    [x[1] for x in COUNTRY_CODES if x[0] == location][0]
+                )[0],
+                format="%0.13f",
+            )
         with col6:
-            mix_pe = st.number_input('Electricity mix - Primary energy [MJ / kWh]', find_electricity_mix([x[1] for x in COUNTRY_CODES if x[0] ==location][0])[1], format="%0.3f")
-
-    impacts = compute_llm_impacts(model_active_parameter_count=active_params,
-                model_total_parameter_count=total_params,
-                output_token_count=output_tokens,
-                request_latency=100000,
-                if_electricity_mix_gwp=mix_gwp,
-                if_electricity_mix_adpe=mix_adpe,
-                if_electricity_mix_pe=mix_pe
+            mix_pe = st.number_input(
+                "Electricity mix - Primary energy [MJ / kWh]",
+                find_electricity_mix(
+                    [x[1] for x in COUNTRY_CODES if x[0] == location][0]
+                )[1],
+                format="%0.3f",
             )
-    
+
+    impacts = compute_llm_impacts(
+        model_active_parameter_count=active_params,
+        model_total_parameter_count=total_params,
+        output_token_count=output_tokens,
+        request_latency=100000,
+        if_electricity_mix_gwp=mix_gwp,
+        if_electricity_mix_adpe=mix_adpe,
+        if_electricity_mix_pe=mix_pe,
+    )
+
     impacts, usage, embodied = format_impacts(impacts)
-    
-    with st.container(border = True):
 
-        st.markdown('<h3 align="center">Environmental Impacts</h2>', unsafe_allow_html = True)
+    with st.container(border=True):
+        st.markdown(
+            '<h3 align="center">Environmental Impacts</h2>', unsafe_allow_html=True
+        )
 
         display_impacts(impacts)
 
-    with st.expander('⚖️ Usage vs Embodied'):
+    with st.expander("⚖️ Usage vs Embodied"):
+        st.markdown(
+            '<h3 align="center">Embodied vs Usage comparison</h2>',
+            unsafe_allow_html=True,
+        )
 
-        st.markdown('<h3 align="center">Embodied vs Usage comparison</h2>', unsafe_allow_html = True)
+        st.markdown(
+            "The usage impacts account for the electricity consumption of the model while the embodied impacts account for resource extraction (e.g., minerals and metals), manufacturing, and transportation of the hardware."
+        )
 
-        st.markdown('The usage impacts account for the electricity consumption of the model while the embodied impacts account for resource extraction (e.g., minerals and metals), manufacturing, and transportation of the hardware.')
-        
         col_ghg_comparison, col_adpe_comparison, col_pe_comparison = st.columns(3)
-        
-        with col_ghg_comparison:
 
+        with col_ghg_comparison:
             fig_gwp = px.pie(
-            values = [average_range_impacts(usage.gwp.value), average_range_impacts(embodied.gwp.value)],
-            names = ['usage', 'embodied'],
-            title = 'GHG emissions',
-            color_discrete_sequence=["#00BF63", "#0B3B36"],
-            width = 100
+                values=[
+                    average_range_impacts(usage.gwp.value),
+                    average_range_impacts(embodied.gwp.value),
+                ],
+                names=["usage", "embodied"],
+                title="GHG emissions",
+                color_discrete_sequence=["#00BF63", "#0B3B36"],
+                width=100,
             )
             fig_gwp.update_layout(showlegend=False, title_x=0.5)
 
@@ -129,59 +180,66 @@ def expert_mode():
 
         with col_adpe_comparison:
             fig_adpe = px.pie(
-                values = [average_range_impacts(usage.adpe.value), average_range_impacts(embodied.adpe.value)],
-                names = ['usage', 'embodied'],
-                title = 'Abiotic depletion',
-                color_discrete_sequence=["#0B3B36","#00BF63"],
-                width = 100)
-            fig_adpe.update_layout(
-                showlegend=False,
-                title_x=0.5)
-            
+                values=[
+                    average_range_impacts(usage.adpe.value),
+                    average_range_impacts(embodied.adpe.value),
+                ],
+                names=["usage", "embodied"],
+                title="Abiotic depletion",
+                color_discrete_sequence=["#0B3B36", "#00BF63"],
+                width=100,
+            )
+            fig_adpe.update_layout(showlegend=False, title_x=0.5)
+
             st.plotly_chart(fig_adpe)
 
         with col_pe_comparison:
             fig_pe = px.pie(
-                values = [average_range_impacts(usage.pe.value), average_range_impacts(embodied.pe.value)],
-                names = ['usage', 'embodied'],
-                title = 'Primary energy',
+                values=[
+                    average_range_impacts(usage.pe.value),
+                    average_range_impacts(embodied.pe.value),
+                ],
+                names=["usage", "embodied"],
+                title="Primary energy",
                 color_discrete_sequence=["#00BF63", "#0B3B36"],
-                width = 100)
+                width=100,
+            )
             fig_pe.update_layout(showlegend=False, title_x=0.5)
 
             st.plotly_chart(fig_pe)
 
-    with st.expander('🌍️ Location impact'):
-
-        st.markdown('<h4 align="center">How can location impact the footprint ?</h4>', unsafe_allow_html = True)
+    with st.expander("🌍️ Location impact"):
+        st.markdown(
+            '<h4 align="center">How can location impact the footprint ?</h4>',
+            unsafe_allow_html=True,
+        )
 
         countries_to_compare = st.multiselect(
-            label = 'Countries to compare',
-            options = [x[0] for x in COUNTRY_CODES],
-            default = ["🇫🇷 France", "🇺🇸 United States", "🇨🇳 China"]
-            )
+            label="Countries to compare",
+            options=[x[0] for x in COUNTRY_CODES],
+            default=["🇫🇷 France", "🇺🇸 United States", "🇨🇳 China"],
+        )
 
         try:
-
             df_comp = dataframe_electricity_mix(countries_to_compare)
 
             impact_type = st.selectbox(
-                label='Select an impact type to compare',
-                options=[x for x in df_comp.columns if x!='country'],
-                index=1)
+                label="Select an impact type to compare",
+                options=[x for x in df_comp.columns if x != "country"],
+                index=1,
+            )
+
+            df_comp.sort_values(by=impact_type, inplace=True)
 
-            df_comp.sort_values(by = impact_type, inplace = True)
-            
             fig_2 = px.bar(
                 df_comp,
-                x = df_comp.index,
-                y = impact_type,
-                text = impact_type,
-                color = impact_type
+                x=df_comp.index,
+                y=impact_type,
+                text=impact_type,
+                color=impact_type,
             )
-            
+
             st.plotly_chart(fig_2)
 
         except:
-
-            st.warning("Can't display chart with no values.")
+            st.warning("Can't display chart with no values.")

src/impacts.py

@@ -1,5 +1,4 @@
 import streamlit as st
-import ecologits
 from src.utils import (
     format_energy_eq_electric_vehicle,
     format_energy_eq_electricity_consumption_ireland,
@@ -8,57 +7,77 @@ from src.utils import (
     format_gwp_eq_airplane_paris_nyc,
     format_gwp_eq_streaming,
     PhysicalActivity,
-    EnergyProduction
+    EnergyProduction,
 )
 
 ############################################################################################################
 
-def get_impacts(model, active_params, total_params, mix_ghg, mix_adpe, mix_pe):
 
+def get_impacts(model, active_params, total_params, mix_ghg, mix_adpe, mix_pe):
     return 1
 
+
 ############################################################################################################
 
 
 def display_impacts(impacts):
-
     st.divider()
 
     col_energy, col_ghg, col_adpe, col_pe, col_water = st.columns(5)
 
     with col_energy:
-        st.markdown('<h4 align="center">⚡️ Energy</h4>', unsafe_allow_html = True)
-        st.latex(f'\Large {impacts.energy.magnitude:.3g} \ \large {impacts.energy.units}')
-        st.markdown(f'<p align="center"><i>Evaluates the electricity consumption<i></p>', unsafe_allow_html = True)
+        st.markdown('<h4 align="center">⚡️ Energy</h4>', unsafe_allow_html=True)
+        st.latex(
+            f"\Large {impacts.energy.magnitude:.3g} \ \large {impacts.energy.units}"
+        )
+        st.markdown(
+            '<p align="center"><i>Evaluates the electricity consumption<i></p>',
+            unsafe_allow_html=True,
+        )
 
     with col_ghg:
-        st.markdown('<h4 align="center">🌍️ GHG Emissions</h4>', unsafe_allow_html = True)
-        st.latex(f'\Large {impacts.gwp.magnitude:.3g} \ \large {impacts.gwp.units}')
-        st.markdown(f'<p align="center"><i>Evaluates the effect on global warming<i></p>', unsafe_allow_html = True)
+        st.markdown('<h4 align="center">🌍️ GHG Emissions</h4>', unsafe_allow_html=True)
+        st.latex(f"\Large {impacts.gwp.magnitude:.3g} \ \large {impacts.gwp.units}")
+        st.markdown(
+            '<p align="center"><i>Evaluates the effect on global warming<i></p>',
+            unsafe_allow_html=True,
+        )
 
     with col_adpe:
-        st.markdown('<h4 align="center">🪨 Abiotic Resources</h4>', unsafe_allow_html = True)
-        st.latex(f'\Large {impacts.adpe.magnitude:.3g} \ \large {impacts.adpe.units}')
-        st.markdown(f'<p align="center"><i>Evaluates the use of metals and minerals<i></p>', unsafe_allow_html = True)
+        st.markdown(
+            '<h4 align="center">🪨 Abiotic Resources</h4>', unsafe_allow_html=True
+        )
+        st.latex(f"\Large {impacts.adpe.magnitude:.3g} \ \large {impacts.adpe.units}")
+        st.markdown(
+            '<p align="center"><i>Evaluates the use of metals and minerals<i></p>',
+            unsafe_allow_html=True,
+        )
 
     with col_pe:
-        st.markdown('<h4 align="center">⛽️ Primary Energy</h4>', unsafe_allow_html = True)
-        st.latex(f'\Large {impacts.pe.magnitude:.3g} \ \large {impacts.pe.units}')
-        st.markdown(f'<p align="center"><i>Evaluates the use of energy resources<i></p>', unsafe_allow_html = True)
+        st.markdown('<h4 align="center">⛽️ Primary Energy</h4>', unsafe_allow_html=True)
+        st.latex(f"\Large {impacts.pe.magnitude:.3g} \ \large {impacts.pe.units}")
+        st.markdown(
+            '<p align="center"><i>Evaluates the use of energy resources<i></p>',
+            unsafe_allow_html=True,
+        )
 
     with col_water:
-        st.markdown('<h4 align="center">🚰 Water</h4>', unsafe_allow_html = True)
-        st.latex('\Large Upcoming...')
-        st.markdown(f'<p align="center"><i>Evaluates the use of water<i></p>', unsafe_allow_html = True)
+        st.markdown('<h4 align="center">🚰 Water</h4>', unsafe_allow_html=True)
+        st.latex("\Large Upcoming...")
+        st.markdown(
+            '<p align="center"><i>Evaluates the use of water<i></p>',
+            unsafe_allow_html=True,
+        )
+
 
 ############################################################################################################
 
-def display_equivalent(impacts):
 
+def display_equivalent(impacts):
     st.divider()
 
     ev_eq = format_energy_eq_electric_vehicle(impacts.energy)
-    
+
     streaming_eq = format_gwp_eq_streaming(impacts.gwp)
 
     col1, col2, col3 = st.columns(3)
@@ -70,47 +89,85 @@ def display_equivalent(impacts):
         if physical_activity == PhysicalActivity.RUNNING:
             physical_activity = "🏃 " + physical_activity.capitalize()
 
-        st.markdown(f'<h4 align="center">{physical_activity}</h4>', unsafe_allow_html = True)
-        st.latex(f'\Large {distance.magnitude:.3g} \ \large {distance.units}')
-        st.markdown(f'<p align="center"><i>Based on energy consumption<i></p>', unsafe_allow_html = True)
+        st.markdown(
+            f'<h4 align="center">{physical_activity}</h4>', unsafe_allow_html=True
+        )
+        st.latex(f"\Large {distance.magnitude:.3g} \ \large {distance.units}")
+        st.markdown(
+            '<p align="center"><i>Based on energy consumption<i></p>',
+            unsafe_allow_html=True,
+        )
 
     with col2:
         ev_eq = format_energy_eq_electric_vehicle(impacts.energy)
-        st.markdown(f'<h4 align="center">🔋 Electric Vehicle</h4>', unsafe_allow_html = True)
-        st.latex(f'\Large {ev_eq.magnitude:.3g} \ \large {ev_eq.units}')
-        st.markdown(f'<p align="center"><i>Based on energy consumption<i></p>', unsafe_allow_html = True)
+        st.markdown(
+            '<h4 align="center">🔋 Electric Vehicle</h4>', unsafe_allow_html=True
+        )
+        st.latex(f"\Large {ev_eq.magnitude:.3g} \ \large {ev_eq.units}")
+        st.markdown(
+            '<p align="center"><i>Based on energy consumption<i></p>',
+            unsafe_allow_html=True,
+        )
 
     with col3:
         streaming_eq = format_gwp_eq_streaming(impacts.gwp)
-        st.markdown(f'<h4 align="center">⏯️ Streaming</h4>', unsafe_allow_html = True)
-        st.latex(f'\Large {streaming_eq.magnitude:.3g} \ \large {streaming_eq.units}')
-        st.markdown(f'<p align="center"><i>Based on GHG emissions<i></p>', unsafe_allow_html = True)
-    
+        st.markdown('<h4 align="center">⏯️ Streaming</h4>', unsafe_allow_html=True)
+        st.latex(f"\Large {streaming_eq.magnitude:.3g} \ \large {streaming_eq.units}")
+        st.markdown(
+            '<p align="center"><i>Based on GHG emissions<i></p>',
+            unsafe_allow_html=True,
+        )
+
     st.divider()
-    
-    st.markdown('<h3 align="center">What if 1% of the planet does this request everyday for 1 year ?</h3>', unsafe_allow_html = True)
-    st.markdown('<p align="center">If this use case is largely deployed around the world, the equivalent impacts would be the impacts of this request x 1% of 8 billion people x 365 days in a year.</p>', unsafe_allow_html = True)
+
+    st.markdown(
+        '<h3 align="center">What if 1% of the planet does this request everyday for 1 year ?</h3>',
+        unsafe_allow_html=True,
+    )
+    st.markdown(
+        '<p align="center">If this use case is largely deployed around the world, the equivalent impacts would be the impacts of this request x 1% of 8 billion people x 365 days in a year.</p>',
+        unsafe_allow_html=True,
+    )
 
     col4, col5, col6 = st.columns(3)
 
     with col4:
-
-        electricity_production, count = format_energy_eq_electricity_production(impacts.energy)
+        electricity_production, count = format_energy_eq_electricity_production(
+            impacts.energy
+        )
         if electricity_production == EnergyProduction.NUCLEAR:
             emoji = "☢️"
             name = "Nuclear power plants"
         if electricity_production == EnergyProduction.WIND:
             emoji = "💨️ "
             name = "Wind turbines"
-        st.markdown(f'<h4 align="center">{emoji} {count.magnitude:.0f} {name} (yearly)</h4>', unsafe_allow_html = True)
-        st.markdown(f'<p align="center"><i>Based on energy consumption<i></p>', unsafe_allow_html = True)
-        
+        st.markdown(
+            f'<h4 align="center">{emoji} {count.magnitude:.0f} {name} (yearly)</h4>',
+            unsafe_allow_html=True,
+        )
+        st.markdown(
+            '<p align="center"><i>Based on energy consumption<i></p>',
+            unsafe_allow_html=True,
+        )
+
     with col5:
         ireland_count = format_energy_eq_electricity_consumption_ireland(impacts.energy)
-        st.markdown(f'<h4 align="center">🇮🇪 {ireland_count.magnitude:.3f} x Ireland <span style="font-size: 12px">(yearly ⚡️ cons.)</span></h2></h4>', unsafe_allow_html = True)
-        st.markdown(f'<p align="center"><i>Based on energy consumption<i></p>', unsafe_allow_html = True)
+        st.markdown(
+            f'<h4 align="center">🇮🇪 {ireland_count.magnitude:.3f} x Ireland <span style="font-size: 12px">(yearly ⚡️ cons.)</span></h2></h4>',
+            unsafe_allow_html=True,
+        )
+        st.markdown(
+            '<p align="center"><i>Based on energy consumption<i></p>',
+            unsafe_allow_html=True,
+        )
 
     with col6:
         paris_nyc_airplane = format_gwp_eq_airplane_paris_nyc(impacts.gwp)
-        st.markdown(f'<h4 align="center">✈️ {round(paris_nyc_airplane.magnitude):,} Paris ↔ NYC</h4>', unsafe_allow_html = True)
-        st.markdown(f'<p align="center"><i>Based on GHG emissions<i></p>', unsafe_allow_html = True)
+        st.markdown(
+            f'<h4 align="center">✈️ {round(paris_nyc_airplane.magnitude):,} Paris ↔ NYC</h4>',
+            unsafe_allow_html=True,
+        )
+        st.markdown(
+            '<p align="center"><i>Based on GHG emissions<i></p>',
+            unsafe_allow_html=True,
+        )

src/models.py

@@ -4,52 +4,76 @@ import pandas as pd
 from src.constants import MODEL_REPOSITORY_URL, MAIN_MODELS
 import streamlit as st
 
-def clean_models_data(df, with_filter = True):
-    
+
+def clean_models_data(df, with_filter=True):
     dict_providers = {
-        'google': 'Google',
-        'mistralai': 'MistralAI',
-        'meta-llama': 'Meta',
-        'openai': 'OpenAI',
-        'anthropic': 'Anthropic',
-        'cohere': 'Cohere',
-        'microsoft': 'Microsoft',
-        'mistral-community': 'Mistral Community',
-        'databricks': 'Databricks'
+        "google": "Google",
+        "mistralai": "MistralAI",
+        "meta-llama": "Meta",
+        "openai": "OpenAI",
+        "anthropic": "Anthropic",
+        "cohere": "Cohere",
+        "microsoft": "Microsoft",
+        "mistral-community": "Mistral Community",
+        "databricks": "Databricks",
     }
 
     models_to_keep = MAIN_MODELS
-    
-    df.drop('type', axis=1, inplace=True)
-
-    df.loc[df['name'].str.contains('/'), 'name_clean'] = df.loc[df['name'].str.contains('/'), 'name'].str.split('/').str[1]
-    df['name_clean'] = df['name_clean'].fillna(df['name'])
-    df['name_clean'] = df['name_clean'].replace({'-': ' ', 'latest': ''}, regex = True)
-    
-    df.loc[df['provider'] == 'huggingface_hub', 'provider_clean'] = df.loc[df['provider'] == 'huggingface_hub', 'name'].str.split('/').str[0]
-    df['provider_clean'] = df['provider_clean'].fillna(df['provider'])
-    df['provider_clean'] = df['provider_clean'].replace(dict_providers, regex = True)
-    
-    df['architecture_type'] = df['architecture'].apply(lambda x: x['type'])
-    df['architecture_parameters'] = df['architecture'].apply(lambda x: x['parameters'])
-    df['total_parameters'] = df['architecture_parameters'].apply(lambda x: x['total'] if isinstance(x, dict) and 'total' in x.keys() else x)
-    df['active_parameters'] = df['architecture_parameters'].apply(lambda x: x['active'] if isinstance(x, dict) and 'active' in x.keys() else x)
-    
-    df['warnings'] = df['warnings'].apply(lambda x: ', '.join(x) if x else None).fillna('none')
-    df['warning_arch'] = df['warnings'].apply(lambda x: 'model-arch-not-released' in x)
-    df['warning_multi_modal'] = df['warnings'].apply(lambda x: 'model-arch-multimodal' in x)
+
+    df.drop("type", axis=1, inplace=True)
+
+    df.loc[df["name"].str.contains("/"), "name_clean"] = (
+        df.loc[df["name"].str.contains("/"), "name"].str.split("/").str[1]
+    )
+    df["name_clean"] = df["name_clean"].fillna(df["name"])
+    df["name_clean"] = df["name_clean"].replace({"-": " ", "latest": ""}, regex=True)
+
+    df.loc[df["provider"] == "huggingface_hub", "provider_clean"] = (
+        df.loc[df["provider"] == "huggingface_hub", "name"].str.split("/").str[0]
+    )
+    df["provider_clean"] = df["provider_clean"].fillna(df["provider"])
+    df["provider_clean"] = df["provider_clean"].replace(dict_providers, regex=True)
+
+    df["architecture_type"] = df["architecture"].apply(lambda x: x["type"])
+    df["architecture_parameters"] = df["architecture"].apply(lambda x: x["parameters"])
+    df["total_parameters"] = df["architecture_parameters"].apply(
+        lambda x: x["total"] if isinstance(x, dict) and "total" in x.keys() else x
+    )
+    df["active_parameters"] = df["architecture_parameters"].apply(
+        lambda x: x["active"] if isinstance(x, dict) and "active" in x.keys() else x
+    )
+
+    df["warnings"] = (
+        df["warnings"].apply(lambda x: ", ".join(x) if x else None).fillna("none")
+    )
+    df["warning_arch"] = df["warnings"].apply(lambda x: "model-arch-not-released" in x)
+    df["warning_multi_modal"] = df["warnings"].apply(
+        lambda x: "model-arch-multimodal" in x
+    )
 
     if with_filter == True:
-        df = df[df['name'].isin(models_to_keep)]
-        
-    return df[['provider', 'provider_clean', 'name', 'name_clean', 'architecture_type', 'architecture_parameters', 'total_parameters', 'active_parameters', 'warning_arch', 'warning_multi_modal']]
+        df = df[df["name"].isin(models_to_keep)]
+
+    return df[
+        [
+            "provider",
+            "provider_clean",
+            "name",
+            "name_clean",
+            "architecture_type",
+            "architecture_parameters",
+            "total_parameters",
+            "active_parameters",
+            "warning_arch",
+            "warning_multi_modal",
+        ]
+    ]
 
-@st.cache_data
-def load_models(filter_main = True):
 
+@st.cache_data
+def load_models(filter_main=True):
     resp = requests.get(MODEL_REPOSITORY_URL)
     data = json.loads(resp.text)
-    df = pd.DataFrame(data['models'])
+    df = pd.DataFrame(data["models"])
 
     return clean_models_data(df, filter_main)
-

src/token_estimator.py

@@ -2,29 +2,36 @@ import streamlit as st
 import tiktoken
 from .content import TOKEN_ESTIMATOR_TEXT
 
+
 def num_tokens_from_string(string: str, encoding_name: str) -> int:
     """Returns the number of tokens in a text string."""
     encoding = tiktoken.get_encoding(encoding_name)
     num_tokens = len(encoding.encode(string))
     return num_tokens
 
+
 def token_estimator():
-    
     st.markdown("### 🪙 Tokens estimator")
-    
-    st.markdown("As our methodology deeply relies on the number of tokens processed by the model *(and as no-one is token-fluent)*, we provide you with a tool to estimate the number of tokens in a given text.")
-    
-    st.expander("ℹ️ What is a token anyway ?", expanded = False).markdown(TOKEN_ESTIMATOR_TEXT)
-    
-    user_text_input = st.text_area("Type or paste some text to estimate the amount of tokens.", "EcoLogits is a great project!")
-    
+
+    st.markdown(
+        "As our methodology deeply relies on the number of tokens processed by the model *(and as no-one is token-fluent)*, we provide you with a tool to estimate the number of tokens in a given text."
+    )
+
+    st.expander("ℹ️ What is a token anyway ?", expanded=False).markdown(
+        TOKEN_ESTIMATOR_TEXT
+    )
+
+    user_text_input = st.text_area(
+        "Type or paste some text to estimate the amount of tokens.",
+        "EcoLogits is a great project!",
+    )
+
     _, col2, _ = st.columns([2, 1, 2])
-    
+
     with col2:
-    
         st.metric(
-            label = 'tokens estimated amount',
-            #label_visibility = 'hidden',
-            value = num_tokens_from_string(user_text_input, "cl100k_base"),
-            border = True
-        )
+            label="tokens estimated amount",
+            # label_visibility = 'hidden',
+            value=num_tokens_from_string(user_text_input, "cl100k_base"),
+            border=True,
+        )

src/utils.py

@@ -1,9 +1,9 @@
 from dataclasses import dataclass
 from enum import Enum
 
-from ecologits.model_repository import models
 from ecologits.impacts.modeling import Impacts, Energy, GWP, ADPe, PE
-#from ecologits.tracers.utils import llm_impacts
+
+# from ecologits.tracers.utils import llm_impacts
 from pint import UnitRegistry, Quantity
 
 #####################################################################################
@@ -11,24 +11,25 @@ from pint import UnitRegistry, Quantity
 #####################################################################################
 
 u = UnitRegistry()
-u.define('Wh = watt_hour')
-u.define('kWh = kilowatt_hour')
-u.define('MWh = megawatt_hour')
-u.define('GWh = gigawatt_hour')
-u.define('TWh = terawatt_hour')
-u.define('gCO2eq = gram')
-u.define('kgCO2eq = kilogram')
-u.define('tCO2eq = metricton')
-u.define('kgSbeq = kilogram')
-u.define('kJ = kilojoule')
-u.define('MJ = megajoule')
-u.define('m = meter')
-u.define('km = kilometer')
-u.define('s = second')
-u.define('min = minute')
-u.define('h = hour')
+u.define("Wh = watt_hour")
+u.define("kWh = kilowatt_hour")
+u.define("MWh = megawatt_hour")
+u.define("GWh = gigawatt_hour")
+u.define("TWh = terawatt_hour")
+u.define("gCO2eq = gram")
+u.define("kgCO2eq = kilogram")
+u.define("tCO2eq = metricton")
+u.define("kgSbeq = kilogram")
+u.define("kJ = kilojoule")
+u.define("MJ = megajoule")
+u.define("m = meter")
+u.define("km = kilometer")
+u.define("s = second")
+u.define("min = minute")
+u.define("h = hour")
 q = u.Quantity
 
+
 @dataclass
 class QImpacts:
     energy: Quantity
@@ -59,8 +60,8 @@ COUNTRIES = [
 #####################################################################################
 
 # From https://www.runningtools.com/energyusage.htm
-RUNNING_ENERGY_EQ = q("294 kJ / km")     # running 1 km at 10 km/h with a weight of 70 kg
-WALKING_ENERGY_EQ = q("196 kJ / km")     # walking 1 km at 3 km/h with a weight of 70 kg
+RUNNING_ENERGY_EQ = q("294 kJ / km")  # running 1 km at 10 km/h with a weight of 70 kg
+WALKING_ENERGY_EQ = q("196 kJ / km")  # walking 1 km at 3 km/h with a weight of 70 kg
 
 # From https://selectra.info/energie/actualites/insolite/consommation-vehicules-electriques-france-2040
 # and https://www.tesla.com/fr_fr/support/power-consumption
@@ -94,85 +95,113 @@ AIRPLANE_PARIS_NYC_GWP_EQ = q("177000 kgCO2eq")
 ### IMPACTS FORMATING
 #####################################################################################
 
+
 def format_energy(energy: Energy) -> Quantity:
     val = q(energy.value, energy.unit)
     if val < q("1 kWh"):
         val = val.to("Wh")
     return val
 
+
 def format_gwp(gwp: GWP) -> Quantity:
     val = q(gwp.value, gwp.unit)
     if val < q("1 kgCO2eq"):
         val = val.to("gCO2eq")
     return val
 
+
 def format_adpe(adpe: ADPe) -> Quantity:
     return q(adpe.value, adpe.unit)
 
+
 def format_pe(pe: PE) -> Quantity:
     val = q(pe.value, pe.unit)
     if val < q("1 MJ"):
         val = val.to("kJ")
     return val
 
-def format_impacts(impacts: Impacts) -> QImpacts:
 
+def format_impacts(impacts: Impacts) -> QImpacts:
     try:
-        impacts.energy.value = (impacts.energy.value.max + impacts.energy.value.min)/2
-        impacts.gwp.value = (impacts.gwp.value.max + impacts.gwp.value.min)/2
-        impacts.adpe.value = (impacts.adpe.value.max + impacts.adpe.value.min)/2
-        impacts.pe.value = (impacts.pe.value.max + impacts.pe.value.min)/2
-        return QImpacts(
-            energy=format_energy(impacts.energy),
-            gwp=format_gwp(impacts.gwp),
-            adpe=format_adpe(impacts.adpe),
-            pe=format_pe(impacts.pe)
-        ), impacts.usage, impacts.embodied
-    except: #when no range
-        return QImpacts(
-            energy=format_energy(impacts.energy),
-            gwp=format_gwp(impacts.gwp),
-            adpe=format_adpe(impacts.adpe),
-            pe=format_pe(impacts.pe)
-        ), impacts.usage, impacts.embodied
+        impacts.energy.value = (impacts.energy.value.max + impacts.energy.value.min) / 2
+        impacts.gwp.value = (impacts.gwp.value.max + impacts.gwp.value.min) / 2
+        impacts.adpe.value = (impacts.adpe.value.max + impacts.adpe.value.min) / 2
+        impacts.pe.value = (impacts.pe.value.max + impacts.pe.value.min) / 2
+        return (
+            QImpacts(
+                energy=format_energy(impacts.energy),
+                gwp=format_gwp(impacts.gwp),
+                adpe=format_adpe(impacts.adpe),
+                pe=format_pe(impacts.pe),
+            ),
+            impacts.usage,
+            impacts.embodied,
+        )
+    except:  # when no range
+        return (
+            QImpacts(
+                energy=format_energy(impacts.energy),
+                gwp=format_gwp(impacts.gwp),
+                adpe=format_adpe(impacts.adpe),
+                pe=format_pe(impacts.pe),
+            ),
+            impacts.usage,
+            impacts.embodied,
+        )
+
 
 def split_impacts_u_e(impacts: Impacts) -> QImpacts:
     return impacts.usage, impacts.embodied
 
+
 def average_range_impacts(x):
-    
     if isinstance(x, float):
-        return x 
+        return x
     else:
-        return (x.max + x.min)/2
+        return (x.max + x.min) / 2
+
 
 def format_impacts_expert(impacts: Impacts, display_range: bool) -> QImpacts:
-    
     if display_range:
-        return QImpacts(
-            energy=format_energy(impacts.energy),
-            gwp=format_gwp(impacts.gwp),
-            adpe=format_adpe(impacts.adpe),
-            pe=format_pe(impacts.pe)
-        ), impacts.usage, impacts.embodied
-    
+        return (
+            QImpacts(
+                energy=format_energy(impacts.energy),
+                gwp=format_gwp(impacts.gwp),
+                adpe=format_adpe(impacts.adpe),
+                pe=format_pe(impacts.pe),
+            ),
+            impacts.usage,
+            impacts.embodied,
+        )
+
     else:
-        energy = {"value":(impacts.energy.value.max + impacts.energy.value.min)/2, "unit":impacts.energy.unit}
-        gwp = (impacts.gwp.value.max + impacts.gwp.value.min)/2
-        adpe = (impacts.adpe.value.max + impacts.adpe.value.min)/2
-        pe = (impacts.pe.value.max + impacts.pe.value.min)/2
-        return QImpacts(
-            energy=format_energy(energy),
-            gwp=format_gwp(gwp),
-            adpe=format_adpe(adpe),
-            pe=format_pe(pe)
-        ), impacts.usage, impacts.embodied
+        energy = {
+            "value": (impacts.energy.value.max + impacts.energy.value.min) / 2,
+            "unit": impacts.energy.unit,
+        }
+        gwp = (impacts.gwp.value.max + impacts.gwp.value.min) / 2
+        adpe = (impacts.adpe.value.max + impacts.adpe.value.min) / 2
+        pe = (impacts.pe.value.max + impacts.pe.value.min) / 2
+        return (
+            QImpacts(
+                energy=format_energy(energy),
+                gwp=format_gwp(gwp),
+                adpe=format_adpe(adpe),
+                pe=format_pe(pe),
+            ),
+            impacts.usage,
+            impacts.embodied,
+        )
+
 
 #####################################################################################
 ### EQUIVALENT FORMATING
 #####################################################################################
 
-def format_energy_eq_physical_activity(energy: Quantity) -> tuple[PhysicalActivity, Quantity]:
+
+def format_energy_eq_physical_activity(
+    energy: Quantity,
+) -> tuple[PhysicalActivity, Quantity]:
     energy = energy.to("kJ")
     running_eq = energy / RUNNING_ENERGY_EQ
     if running_eq > q("1 km"):
@@ -183,6 +212,7 @@ def format_energy_eq_physical_activity(energy: Quantity) -> tuple[PhysicalActivi
         walking_eq = walking_eq.to("meter")
     return PhysicalActivity.WALKING, walking_eq
 
+
 def format_energy_eq_electric_vehicle(energy: Quantity) -> Quantity:
     energy = energy.to("kWh")
     ev_eq = energy / EV_ENERGY_EQ
@@ -190,6 +220,7 @@ def format_energy_eq_electric_vehicle(energy: Quantity) -> Quantity:
         ev_eq = ev_eq.to("meter")
     return ev_eq
 
+
 def format_gwp_eq_streaming(gwp: Quantity) -> Quantity:
     gwp = gwp.to("kgCO2eq")
     streaming_eq = gwp * STREAMING_GWP_EQ
@@ -199,7 +230,10 @@ def format_gwp_eq_streaming(gwp: Quantity) -> Quantity:
         streaming_eq = streaming_eq.to("s")
     return streaming_eq
 
-def format_energy_eq_electricity_production(energy: Quantity) -> tuple[EnergyProduction, Quantity]:
+
+def format_energy_eq_electricity_production(
+    energy: Quantity,
+) -> tuple[EnergyProduction, Quantity]:
     electricity_eq = energy * ONE_PERCENT_WORLD_POPULATION * DAYS_IN_YEAR
     electricity_eq = electricity_eq.to("TWh")
     if electricity_eq > YEARLY_NUCLEAR_ENERGY_EQ:
@@ -213,7 +247,10 @@ def format_energy_eq_electricity_consumption_ireland(energy: Quantity) -> Quanti
     electricity_eq = electricity_eq.to("TWh")
     return electricity_eq / YEARLY_IRELAND_ELECTRICITY_CONSUMPTION
 
+
 def format_gwp_eq_airplane_paris_nyc(gwp: Quantity) -> Quantity:
     gwp_eq = gwp * ONE_PERCENT_WORLD_POPULATION * DAYS_IN_YEAR
     gwp_eq = gwp_eq.to("kgCO2eq")
-    return gwp_eq / AIRPLANE_PARIS_NYC_GWP_EQ####################################################################################### MODELS PARAMETER####################################################################################
+    return (
+        gwp_eq / AIRPLANE_PARIS_NYC_GWP_EQ
+    )  ####################################################################################### MODELS PARAMETER####################################################################################