prompts suggestions and pdf fix

.dockerignore

@@ -0,0 +1,11 @@
+__pycache__/
+*.pyc
+*.pyo
+*.pyd
+.Python
+env/
+venv/
+.git
+.dockerignore
+Dockerfile
+*.md

Dockerfile

@@ -0,0 +1,34 @@
+# Use the official lightweight Python image.
+# https://hub.docker.com/_/python
+FROM python:3.9-slim
+
+# Set environment variables
+ENV PYTHONDONTWRITEBYTECODE 1
+ENV PYTHONUNBUFFERED 1
+
+# Create and set working directory
+WORKDIR /app
+
+RUN apt-get update \
+  && apt-get install wkhtmltopdf -y \
+  && mv /usr/bin/wkhtmltopdf /usr/local/bin/.
+
+# Copy system package requirements file
+COPY packages.txt .
+
+RUN apt-get update
+
+# Copy the application requirements file
+COPY requirements.txt .
+
+# Install Python dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy the application code
+COPY . .
+
+# Expose the Streamlit port
+EXPOSE 8501
+
+# Run Streamlit app
+CMD ["streamlit", "run", "app.py"]

chat_with_pps.py

@@ -97,7 +97,7 @@ def format_context(partie_prenante_grouped,marque):
     return context
 
 
-def get_response(user_query, chat_history, context,llm=None):
+def get_response(user_query, chat_history, context,llm=None,history_limit=5,stream=True):
 
     template = """
     Fournir des réponses, en francais, précises et contextuelles en agissant comme un expert en affaires, en utilisant le contexte des parties prenantes et leur pouvoir en pourcentage et leur influence en pourcentage pour expliquer les implications pour la marque. Le modèle doit connecter les informations du contexte et de l'historique de la conversation pour donner une réponse éclairée à la dernière question posée.
@@ -120,6 +120,20 @@ def get_response(user_query, chat_history, context,llm=None):
         llm = ChatMistralAI(model_name="mistral-large-latest")
         
     chain = prompt | llm | StrOutputParser()
+
+    if not stream:
+        return chain.invoke({
+            "context": context,
+            "chat_history": chat_history[-history_limit:],
+            "user_question": user_query,
+        })
+
+    if history_limit:
+        return chain.stream({
+            "context": context,
+            "chat_history": chat_history[-history_limit:],
+            "user_question": user_query,
+        })
     
     return chain.stream({
         "context": context,
@@ -158,14 +172,15 @@ def disp_carto_in_chat():
         st.rerun()
 
 @st.experimental_dialog("Télécharger",width="small")
-def dowmload_history():
+def dowmload_history(used_models=None):
     brand_name = st.session_state['Nom de la marque']
     format = st.radio("Choisissez le document à télécharger",[f"Rapport des parties prenantes (PDF)",f"Tableau des parties prenantes (CSV)",f"Historique de conversation (Fichier Texte)"],index=None)
     if format == f"Rapport des parties prenantes (PDF)":
         with st.spinner("Generation en cours..."):
             summary = get_response("Donne moi un RESUME de la Conversation", st.session_state.chat_history,format_context(st.session_state['pp_grouped'],st.session_state['Nom de la marque']),st.session_state.model)
             summary = ''.join(summary)
-            pdf = export_conversation(AIMessage(content=summary).content)
+            pdf = export_conversation(AIMessage(content=summary).content,used_models=used_models)
+
             if pdf:
                 st.download_button("Télécharger le PDF", data=pdf, file_name=f"Cartographie {brand_name}.pdf", mime="application/pdf")
         
@@ -213,6 +228,17 @@ def import_conversation():
             st.rerun()
         except Exception as e:
             st.error("Erreur lors de la lecture du fichier")
+
+def extract_format_prompts_from_response(response):
+    st.markdown("---\n")
+    prompts = response.split("\n")
+    prompts = [prompt.strip() for prompt in prompts if prompt.strip() != ""]
+    prompts_container = st.container()
+    with prompts_container:
+        for i,prompt in enumerate(prompts):
+            col1,col2 = st.columns([9,1])
+            col1.markdown(f"{prompt}")
+            col2.button("➡️",key=f"exec_{i}",on_click=lambda i=i: st.session_state.chat_history.append(HumanMessage(content=prompts[i])))
     
 
 
@@ -227,6 +253,17 @@ def display_chat():
         "GPT-4o":0
     }
 
+    
+
+    generated_prompt_question = '''En fonction de l'historique, proposez trois prompts pour continuer la conversation. Utilisez les informations fournies et les implications discutées:
+
+                    - Prompt 1 : [Premier prompt suggéré]
+                    - Prompt 2 : [Deuxième prompt suggéré]
+                    - Prompt 3 : [Troisième prompt suggéré]
+
+                    LA LISTE DOIT ETRE EN FRANCAIS CHAQUE LIGNE SANS LE NUMERO DE PROMPT SEULEMENT LE TEXTE DE LA QUESTION
+                    '''
+
     # session state
     if "chat_history" not in st.session_state:
         st.session_state.chat_history = [
@@ -236,6 +273,9 @@ def display_chat():
     if "model" not in st.session_state:
         st.session_state.model = "GPT-4o"
     
+    if "used_models" not in st.session_state:
+        st.session_state.used_models = []
+    
     #sticky bar at the top
     header = st.container()
     col1,col2,col3, col4,col5,col6 = header.columns([2,3,2,3,2,1])
@@ -248,7 +288,7 @@ def display_chat():
     if col3.button("Ma Carto"):
         disp_carto_in_chat()
     if col4.button("Télécharger"):
-        dowmload_history()
+        dowmload_history(st.session_state.used_models)
     header.write("""<div class='fixed-header'/>""", unsafe_allow_html=True)
     if col5.button("Importer"):
         import_conversation()
@@ -293,6 +333,9 @@ def display_chat():
             else:
                 response = st.write_stream(get_response(last_message.content, st.session_state.chat_history,format_context(st.session_state['pp_grouped'],st.session_state['Nom de la marque']),st.session_state.model))
                 st.session_state.chat_history.append(AIMessage(content=response))
+                with st.spinner("Proposition de prompts..."):
+                    propositions_prompts = get_response(generated_prompt_question, st.session_state.chat_history,format_context(st.session_state['pp_grouped'],st.session_state['Nom de la marque']),st.session_state.model,history_limit=1,stream=False)
+                extract_format_prompts_from_response(propositions_prompts)
 
 
 
@@ -310,16 +353,19 @@ def display_chat():
             st.markdown(user_query)
         with st.chat_message("AI"):
             st.markdown(f"**{st.session_state.model}**")
+            if st.session_state.model not in st.session_state.used_models:
+                st.session_state.used_models.append(st.session_state.model)
             if user_query.startswith("/rajoute"):
                 partie_prenante = extract_pp_from_query(user_query)
                 format_pp_add_viz(partie_prenante)
                 disp_carto_in_chat()
             else:
-                st.warning(user_query)
                 response = st.write_stream(get_response(user_query, st.session_state.chat_history,format_context(st.session_state['pp_grouped'],st.session_state['Nom de la marque']),st.session_state.model))
-                if "cartographie" in response:
-                        display_chart()
                 st.session_state.chat_history.append(AIMessage(content=response))
+                with st.spinner("Proposition de prompts..."):
+                    propositions_prompts = get_response(generated_prompt_question, st.session_state.chat_history,format_context(st.session_state['pp_grouped'],st.session_state['Nom de la marque']),st.session_state.model,history_limit=1,stream=False)
+                extract_format_prompts_from_response(propositions_prompts)
+                
             
 
         

export_doc.py

@@ -9,6 +9,7 @@ from datetime import datetime
 from download_chart import construct_plot
 from kaleido.scopes.plotly import PlotlyScope
 import pandas as pd
+import markdown
 
 def colored_circle(color):
     return f'<span style="display: inline-block; width: 15px; height: 15px; border-radius: 50%; background-color: {color};"></span>'
@@ -44,14 +45,18 @@ def convert_pp_to_csv(pp_grouped):
     return pp_df.to_csv(index=True,encoding="utf-8")
 
 @st.cache_data
-def create_pdf_from_markdown(logo_path, conversation,summary,brand_name,graph_html,app_url,list_pps):
+def create_pdf_from_markdown(logo_path, conversation,summary,brand_name,graph_html,app_url,list_pps,used_models=None):
     # Convertir la conversation en markdown
     markdown_text = "\n".join([f"### {entry['speaker']}:\n {entry['text']}\n ---" for entry in conversation])
+
+    if not used_models:
+        used_models = ["Aucun modèle IA n'a été utilisé"]
+    html_used_models = "".join([f"<p>{model}</p>" for model in used_models])
     
     markdown_summary = f"{summary}\n --- \n ---"
     markdown_list_pps = list_to_markdown(list_pps)
     # Convertir le markdown en HTML
-    html_content = markdown2.markdown(markdown_text)
+    html_content = markdown.markdown(markdown_text,extensions=['markdown.extensions.tables'])
     html_summary = markdown2.markdown(markdown_summary)
     html_list_pps = markdown2.markdown(markdown_list_pps)
 
@@ -92,10 +97,7 @@ def create_pdf_from_markdown(logo_path, conversation,summary,brand_name,graph_ht
             <h1>Cartographie des parties prenantes "{brand_name}"</h1>
             <p>Date de l'analyse IA RSE : {analysis_date}</p>
             <p>IA utilisées :</p>
-            <ul>
-                <li>(US) ChatGpt 4.o</li>
-                <li>(FR) Mistral AI - Large (open source)</li>
-            </ul>
+            {html_used_models}
             <img src="{logo_path}" alt="Logo" style="width: 150px;"/>
         </div>
         <div class="page-break"></div>
@@ -204,7 +206,7 @@ def get_conversation():
     return conversation
 
 
-def export_conversation(summary):
+def export_conversation(summary,used_models=None):
     brand_name = st.session_state["Nom de la marque"]
     app_url = "https://huggingface.co/spaces/bziiit/OpenData-Bordeaux-RSE"
     logo_path = "https://static.wixstatic.com/media/d7d3da_b69e03ae99224f7d8b6e358918e60071~mv2.png/v1/crop/x_173,y_0,w_1906,h_938/fill/w_242,h_119,al_c,q_85,usm_0.66_1.00_0.01,enc_auto/BZIIIT_LOGO-HORIZ-COULEUR.png"  # Replace with your image path
@@ -220,9 +222,10 @@ def export_conversation(summary):
             st.error("Erreur lors de la génération de la cartographie")
             graph = ""
         try:
-            pdf = create_pdf_from_markdown(logo_path=logo_path, conversation=conversation,summary=summary,brand_name=brand_name,graph_html=graph,app_url=app_url,list_pps=list_pps)
+            pdf = create_pdf_from_markdown(logo_path=logo_path, conversation=conversation,summary=summary,brand_name=brand_name,graph_html=graph,app_url=app_url,list_pps=list_pps,used_models=used_models)
         except Exception as e:
             pdf = None
+            st.error(f"{e}")
 
     if pdf:
         st.success("PDF généré avec succès!}")

packages.txt

@@ -1,17 +1,2 @@
 wkhtmltopdf
-build-essential 
-libgl1-mesa-dev
-xfonts-75dpi
-xfonts-75dpi 
-xfonts-base 
-gvfs 
-colord 
-glew-utils 
-libvisual-0.4-plugins 
-gstreamer1.0-tools
-opus-tools 
-qt5-image-formats-plugins 
-qtwayland5 
-qt5-qmltooling-plugins 
-librsvg2-bin 
-lm-sensors
+xfonts-75dpi

partie_prenante_carte.py

@@ -6,20 +6,15 @@ import random
 
 import streamlit as st
 from dotenv import load_dotenv
-from langchain.text_splitter import CharacterTextSplitter,RecursiveCharacterTextSplitter
 from langchain_experimental.text_splitter import SemanticChunker
 from langchain_community.embeddings import OpenAIEmbeddings
 from langchain_community.vectorstores import FAISS
 from langchain_community.chat_models import ChatOpenAI
-from langchain.llms import HuggingFaceHub
 from langchain import hub
-from langchain_core.output_parsers import StrOutputParser
 from langchain_core.runnables import RunnablePassthrough
 from langchain_community.document_loaders import WebBaseLoader,FireCrawlLoader,PyPDFLoader
 from langchain_core.prompts.prompt import PromptTemplate
-from session import set_partie_prenante
 import os
-from streamlit_vertical_slider import vertical_slider
 from high_chart import test_chart
 from chat_with_pps import get_response
 

requirements.txt

@@ -38,6 +38,5 @@ langchain-core
 langchain-mistralai
 firecrawl-py
 st_copy_to_clipboard
-pyperclip
 fpdf2
 markdown2

temp.html

@@ -3,7 +3,7 @@
     <html lang="en">
     <head>
         <meta charset="UTF-8">
-        <title>Cartographie des parties prenantes bziiit</title>
+        <title>Cartographie des parties prenantes </title>
         <link href="https://fonts.googleapis.com/css2?family=Roboto:wght@400;700&display=swap" rel="stylesheet">
         <style>
             body {
@@ -22,24 +22,23 @@
     </head>
     <body>
         <div style="text-align: center;">
-            <h1>Cartographie des parties prenantes "bziiit"</h1>
-            <p>Date de l'analyse IA RSE : 2024-06-25</p>
+            <h1>Cartographie des parties prenantes ""</h1>
+            <p>Date de l'analyse IA RSE : 2024-06-27</p>
             <p>IA utilisées :</p>
-            <ul>
-                <li>(US) ChatGpt 4.o</li>
-                <li>(FR) Mistral AI - Large (open source)</li>
-            </ul>
+            <p>Aucun modèle IA n'a été utilisé</p>
             <img src="https://static.wixstatic.com/media/d7d3da_b69e03ae99224f7d8b6e358918e60071~mv2.png/v1/crop/x_173,y_0,w_1906,h_938/fill/w_242,h_119,al_c,q_85,usm_0.66_1.00_0.01,enc_auto/BZIIIT_LOGO-HORIZ-COULEUR.png" alt="Logo" style="width: 150px;"/>
         </div>
         <div class="page-break"></div>
         <div style="text-align: center; margin-top: 20px;">
-            <img src="data:image/png;base64,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">
+            <img src="data:image/png;base64,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">
         </div>
-        <p><span style="display: inline-block; width: 15px; height: 15px; border-radius: 50%; background-color: #46ca57;"></span> test - <b>Pouvoir:</b> 50% <b>Influence:</b> 50%</p>
+        <p><span style="display: inline-block; width: 15px; height: 15px; border-radius: 50%; background-color: #80eabc;"></span> <b>bob</b>: Pouvoir:50% Influence:50%</p>
+
+<p><span style="display: inline-block; width: 15px; height: 15px; border-radius: 50%; background-color: #43e6ed;"></span> <b>tt</b>: Pouvoir:55% Influence:50%</p>
 
         <div class="page-break"></div>
         <h2>RESUME</h2>
-        <p>Dans cette conversation, vous avez demandé une cartographie des parties prenantes pour la marque bziiit. Il a été identifié qu'il y a une seule partie prenante, nommée 0.test, qui possède un pouvoir de 50% et une influence de 50%. En fonction de ces paramètres, il semble que 0.test devrait être géré étroitement car leur pouvoir et leur influence sont tous deux à 50%. Ensuite, vous avez demandé un résumé de cette conversation.</p>
+        <p>Dans cette conversation, nous avons identifié et classé deux parties prenantes de la marque, Bob et TT. Chacun d'eux détient un pouvoir supérieur à 50% et une influence de 50%. En se basant sur ces critères, ils sont tous deux classés dans la catégorie "Gérer étroitement", ce qui signifie que la marque doit accorder une attention particulière à leurs attentes et besoins. Un tableau résumant ces informations a également été généré, montrant les détails de chaque partie prenante, leur pouvoir, leur influence et leur catégorie respective.</p>
 
 <hr />
 
@@ -48,11 +47,61 @@
         <div class="page-break"></div>
         <h2>Historique de la Conversation</h2>
         <h3>AI:</h3>
-
 <p>Salut, voici votre cartographie des parties prenantes. Que puis-je faire pour vous?</p>
-
 <hr />
-
+<h3>Moi:</h3>
+<p>/rajoute bob</p>
+<hr />
+<h3>AI:</h3>
+<p>Partie prenante ajoutée</p>
+<hr />
+<h3>Moi:</h3>
+<p>/rajoute tt</p>
+<hr />
+<h3>AI:</h3>
+<p>Partie prenante ajoutée</p>
+<hr />
+<h3>Moi:</h3>
+<p>repond en une phrase</p>
+<hr />
+<h3>AI:</h3>
+<p>Étant donné que Bob et TT ont tous deux un pouvoir supérieur à 50% et une influence égale à 50%, ils appartiennent à la catégorie "Gérer étroitement", ce qui implique que la marque doit accorder une attention particulière à leurs attentes et besoins pour maintenir une relation positive et productive.</p>
+<hr />
+<h3>Moi:</h3>
+<p>genere moi un tableau avec une seul ligne</p>
+<hr />
+<h3>AI:</h3>
+<p>Voici un tableau qui résume les informations sur les parties prenantes de la marque en une seule ligne :</p>
+<table>
+<thead>
+<tr>
+<th>Partie prenante</th>
+<th>Pouvoir</th>
+<th>Influence</th>
+<th>Catégorie</th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td>Bob</td>
+<td>50%</td>
+<td>50%</td>
+<td>Gérer étroitement</td>
+</tr>
+<tr>
+<td>TT</td>
+<td>55%</td>
+<td>50%</td>
+<td>Gérer étroitement</td>
+</tr>
+<tr>
+<td>---</td>
+<td></td>
+<td></td>
+<td></td>
+</tr>
+</tbody>
+</table>
     </body>
     </html>