vue enhance

app.py

@@ -9,6 +9,7 @@ def main():
     st.set_page_config(page_title="RAG Agent", page_icon="🤖", layout="wide")
 
     audit_page = st.Page("audit_page/audit.py", title="Audit", icon="📋", default=True)
+    dialog_page = st.Page("audit_page/dialogue_doc.py", title="Dialoguer avec le document", icon="💬")
     kg_page = st.Page("audit_page/knowledge_graph.py", title="Graphe de connaissance", icon="🧠")
     agents_page = st.Page("agents_page/catalogue.py", title="Catalogue des agents", icon="📇")
     compte_rendu = st.Page("audit_page/compte_rendu.py", title="Compte rendu", icon="📝")
@@ -18,7 +19,7 @@ def main():
 
     pg = st.navigation(
         {
-            "Audit de contenus": [audit_page, compte_rendu, kg_page],
+            "Audit de contenus": [audit_page,dialog_page, compte_rendu, kg_page],
             "Equipe d'agents IA": [recommended_agents],
             "Chatbot": [chatbot],
             "Documentation": [documentation]

audit_page/audit.py

@@ -111,10 +111,13 @@ def handle_audit(uploaded_file,type:str):
             st.session_state.name_file = uploaded_file.name
             with st.spinner("Analyse du document..."):
                 st.session_state.audit = {}
+                
                 st.session_state.audit = audit_descriptif_pdf(uploaded_file,100)
             with st.spinner("Préparation de la DB..."):
                 vectorstore = setup_rag(type,st.session_state.audit["content"])
                 st.session_state.vectorstore = vectorstore
+                st.session_state.graph = None
+                st.session_state.cr = ""
 
         audit = st.session_state.audit["audit"]
         #global audit
@@ -136,6 +139,12 @@ def handle_audit(uploaded_file,type:str):
             with st.spinner("Analyse de l'audio..."):
                 st.session_state.audit = {}
                 st.session_state.audit = evaluate_audio_quality(uploaded_file)
+            with st.spinner("Préparation de la DB..."):
+                vectorstore = setup_rag(type,st.session_state.audit["content"])
+                st.session_state.vectorstore = vectorstore
+                st.session_state.graph = None
+                st.session_state.cr = ""
+                
         audit = st.session_state.audit["audit"]
         #audit global simplifié
         audit_simplified = {
@@ -218,6 +227,10 @@ def audit_main():
         st.session_state.audit_simplified = {}
     if "vectorstore" not in st.session_state:
         st.session_state.vectorstore = None
+    if "cr" not in st.session_state:
+        st.session_state.cr = ""
+    if "graph" not in st.session_state:
+        st.session_state.graph = None
 
     # File uploader
     uploaded_file = col1.file_uploader("Télécharger un ou plusieurs documents")
@@ -234,4 +247,7 @@ def audit_main():
         display_audit(col1)
         handle_display_content(col2)
         
+        #init graph and cr
+        
+        
 audit_main()

audit_page/dialogue_doc.py

@@ -0,0 +1,287 @@
+import streamlit as st
+from textwrap import dedent
+from utils.audit.rag import get_text_from_content_for_doc,get_text_from_content_for_audio
+from utils.audit.response_llm import generate_response_via_langchain
+from langchain_core.messages import AIMessage, HumanMessage
+import pyperclip
+from utils.kg.construct_kg import get_graph
+from audit_page.knowledge_graph import *
+
+def graph_doc_to_json(graph):
+    nodes = []
+    edges = []
+    for node in graph.nodes:
+        node_id = node.id.replace(" ", "_")
+        label = node.id
+        type = node.type
+        nodes.append({"id": node_id, "label": label, "type": type})
+    for relationship in graph.relationships:
+        source = relationship.source
+        source_id = source.id.replace(" ", "_")
+        target = relationship.target
+        target_id = target.id.replace(" ", "_")
+        label = relationship.type
+        edges.append({"source": source_id, "label": label, "cible": target_id})
+    return {"noeuds": nodes, "relations": edges}
+
+def chat_history_formatter(chat_history):
+    formatted_chat = ""
+    for message in chat_history:
+        if isinstance(message, AIMessage):
+            formatted_chat += f"AI:\n {message.content}\n\n"
+        elif isinstance(message, HumanMessage):
+            formatted_chat += f"Human:\n {message.content}\n\n"
+    return formatted_chat
+
+def doc_dialog_main():
+    st.title("Dialogue avec le document")
+
+    if "audit" not in st.session_state or st.session_state.audit == {}:
+        st.error("Veuillez d'abord effectuer un audit pour générer le compte rendu ou le graphe de connaissance.")
+        return
+    
+    #init cr and chat history cr
+    if "cr" not in st.session_state:
+        st.session_state.cr = ""
+    if "cr_chat_history" not in st.session_state:
+        st.session_state.cr_chat_history = [
+        ]
+
+    #init graph and filter views
+    if "graph" not in st.session_state:
+        st.session_state.graph = None
+    
+    if "filter_views" not in st.session_state:
+        st.session_state.filter_views = {}
+    if "current_view" not in st.session_state:
+        st.session_state.current_view = None
+    if "node_types" not in st.session_state:
+        st.session_state.node_types = None
+    # if "summary" not in st.session_state:
+    #     st.session_state.summary = None
+    if "chat_graph_history" not in st.session_state:
+        st.session_state.chat_graph_history = []
+    
+    if "radio_choice" not in st.session_state:
+        st.session_state.radio_choice = None
+
+    options = ["compte_rendu","graphe de connaissance"]
+    choice = st.radio("Choisissez une option",options,index=st.session_state.radio_choice,horizontal=True,label_visibility="collapsed")
+    if choice:
+        st.session_state.radio_choice = options.index(choice)
+    
+    audit = st.session_state.audit_simplified
+    content = st.session_state.audit["content"]
+
+    if audit["type de fichier"] == "pdf":
+        text = get_text_from_content_for_doc(content)
+    elif audit["type de fichier"] == "audio":
+        text = get_text_from_content_for_audio(content)
+
+    
+
+    if choice == "compte_rendu":
+        if "cr" not in st.session_state or st.session_state.cr == "":
+            with st.spinner("Génération du compte rendu..."):
+                prompt_cr = dedent(f'''
+                    À partir du document ci-dessous, générez un compte rendu détaillé contenant les sections suivantes :
+
+                    2. **Résumé** : Fournissez un résumé concis du document, en mettant en avant les points principaux, les relations essentielles, les concepts , les dates et les lieux, les conclusions et les détails importants.
+
+                    3. **Notes** :
+                    - Présentez les points clés sous forme de liste à puces avec des émojis pertinents pour souligner la nature de chaque point.
+                    - Incluez des sous-points (sans émojis) sous les points principaux pour offrir des détails ou explications supplémentaires.
+
+                    4. **Actions** : Identifiez et listez les actions spécifiques, tâches ou étapes recommandées ou nécessaires selon le contenu du document.
+
+                    **Document :**
+                                    
+                    {text}
+
+                    **Format de sortie :**
+
+
+                    ### Résumé :
+                    [Fournissez un résumé concis du document ici.]
+
+                    ### Notes :
+                    - 📌 **Point Principal 1**
+                    - Sous-point A
+                    - Sous-point B
+                    - 📈 **Point Principal 2**
+                    - Sous-point C
+                    - Sous-point D
+                    - 📝 **Point Principal 3**
+                    - Sous-point E
+                    - Sous-point F
+
+                    ### Actions :
+                    1. [Action 1]
+                    2. [Action 2]
+                    3. [Action 3]
+                    4. ...
+
+                    ---
+                    ''')
+                cr = generate_response_via_langchain(prompt_cr,stream=False,model="gpt-4o")
+                st.session_state.cr =  cr
+                st.session_state.cr_chat_history = []
+        else:
+            cr = st.session_state.cr
+
+        if cr:
+            col1, col2 = st.columns([2.5, 1.5])
+
+            with col1.container(border=True,height=800):
+                st.markdown("##### Compte rendu")
+                with st.container(height=650,border=False):
+                    keywords_paragraph = f"### Mots clés extraits:\n- {audit['Mots clés'].strip()}"
+                    st.markdown(keywords_paragraph)
+                    st.write(cr)
+                col_copy , col_success = st.columns([1,11])
+                if col_copy.button("📋",key="copy_cr"):
+                    pyperclip.copy(keywords_paragraph+"\n\n"+cr)
+                    col_success.success("Compte rendu copié dans le presse-papier")
+                
+            with col2.container(border=True,height=800):
+                st.markdown("##### Dialoguer avec le CR")
+
+                user_query = st.chat_input("Par ici ...")
+                if user_query is not None and user_query != "":
+                    st.session_state.cr_chat_history.append(HumanMessage(content=user_query))
+
+                with st.container(height=600, border=False):
+                    for message in st.session_state.cr_chat_history:
+                        if isinstance(message, AIMessage):
+                            with st.chat_message("AI"):
+                                st.markdown(message.content)
+                        elif isinstance(message, HumanMessage):
+                            with st.chat_message("Human"):
+                                st.write(message.content)
+                
+                    #check if last message is human message
+                    if len(st.session_state.cr_chat_history) > 0:
+                        last_message = st.session_state.cr_chat_history[-1]
+                        if isinstance(last_message, HumanMessage):
+                            with st.chat_message("AI"):
+                                retreive = st.session_state.vectorstore.as_retriever()
+                                context = retreive.invoke(last_message.content)
+                                wrapped_prompt = f'''Étant donné le contexte suivant {context} et le compte rendu du document {cr}, {last_message.content}'''
+                                response = st.write_stream(generate_response_via_langchain(wrapped_prompt,stream=True))
+                                st.session_state.cr_chat_history.append(AIMessage(content=response))
+                col_copy_c , col_success_c = st.columns([1,7])
+                if col_copy_c.button("📋",key="copy_cr_chat"):
+                    chat_formatted = chat_history_formatter(st.session_state.cr_chat_history)
+                    pyperclip.copy(chat_formatted)
+                    col_success_c.success("Historique copié !")
+
+    elif choice == "graphe de connaissance":
+        if "graph" not in st.session_state or st.session_state.graph == None:
+            with st.spinner("Génération du graphe..."):
+                keywords_list = audit["Mots clés"].strip().split(",")
+                allowed_nodes_types =keywords_list+ ["Person","Organization","Location","Event","Date","Time","Ressource","Concept"]
+                graph = get_graph(text,allowed_nodes=allowed_nodes_types)
+                st.session_state.graph = graph
+                st.session_state.filter_views = {}
+                st.session_state.current_view = None
+                st.session_state.node_types = None
+                st.session_state.chat_graph_history = []
+            
+            node_types = get_node_types(graph[0])
+            nodes_type_dict = list_to_dict_colors(node_types)
+            st.session_state.node_types = nodes_type_dict
+            st.session_state.filter_views["Vue par défaut"] = list(node_types)
+            st.session_state.current_view = "Vue par défaut"
+        else:
+            graph = st.session_state.graph
+        
+        if graph is not None:
+            #st.write(graph)
+            
+            edges,nodes,config = convert_neo4j_to_agraph(graph[0],st.session_state.node_types)
+            
+            col1, col2 = st.columns([2.5, 1.5])
+
+            with col1.container(border=True,height=800):
+                st.write("##### Visualisation du graphe (**"+st.session_state.current_view+"**)")
+                filter_col,add_view_col,change_view_col,color_col = st.columns([9,1,1,1])
+                
+                if color_col.button("🎨",help="Changer la couleur"):
+                    change_color_dialog()
+                    
+                if change_view_col.button("🔍",help="Changer de vue"):
+                    change_view_dialog()
+
+                
+                #add mots cles to evry label in audit["Mots clés"]
+                #filter_labels = [ label + " (mot clé)" if label.strip().lower() in audit["Mots clés"].strip().lower().split(",") else label for label in st.session_state.filter_views[st.session_state.current_view] ]
+                filter = filter_col.multiselect("Filtrer selon l'étiquette",st.session_state.node_types.keys(),placeholder="Sélectionner une ou plusieurs étiquettes",default=st.session_state.filter_views[st.session_state.current_view],label_visibility="collapsed")
+                
+                if add_view_col.button("➕",help="Ajouter une vue"):
+                    add_view_dialog(filter)
+                
+                if filter:
+                    nodes = filter_nodes_by_types(nodes,filter) 
+
+                selected = display_graph(edges,nodes,config)
+
+                col_copy , col_success = st.columns([1,11])
+                if col_copy.button("📋",key="copy_graph"):
+                    graph_json = graph_doc_to_json(graph[0])
+                    pyperclip.copy(graph_json)
+                    col_success.success("Graphe copié dans le presse-papier")
+
+            with col2.container(border=True,height=800):
+                st.markdown("##### Dialoguer avec le graphe")
+
+                user_query = st.chat_input("Par ici ...")
+                if user_query is not None and user_query != "":
+                    st.session_state.chat_graph_history.append(HumanMessage(content=user_query))
+
+                with st.container(height=600, border=False):
+                    for message in st.session_state.chat_graph_history:
+                        if isinstance(message, AIMessage):
+                            with st.chat_message("AI"):
+                                st.markdown(message.content)
+                        elif isinstance(message, HumanMessage):
+                            with st.chat_message("Human"):
+                                st.write(message.content)
+                    
+                    #check if last message is human message
+                    if len(st.session_state.chat_graph_history) > 0:
+                        last_message = st.session_state.chat_graph_history[-1]
+                        if isinstance(last_message, HumanMessage):
+                            with st.chat_message("AI"):
+                                retreive = st.session_state.vectorstore.as_retriever()
+                                context = retreive.invoke(last_message.content)
+                                wrapped_prompt = f"Étant donné le contexte suivant {context}, et le graph de connaissance: {graph}, {last_message.content}"
+                                response = st.write_stream(generate_response_via_langchain(wrapped_prompt,stream=True))
+                                st.session_state.chat_graph_history.append(AIMessage(content=response))
+
+                    if selected is not None:
+                            with st.chat_message("AI"):
+                                st.markdown(f" EXPLORER LES DONNEES CONTENUES DANS **{selected}**")
+
+                                prompts = [f"Extrait moi toutes les informations du noeud ''{selected}'' ➡️",
+                                        f"Montre moi les conversations autour du noeud ''{selected}'' ➡️"]
+                                
+                                for i,prompt in enumerate(prompts):
+                                    button = st.button(prompt,key=f"p_{i}",on_click=lambda i=i: st.session_state.chat_graph_history.append(HumanMessage(content=prompts[i])))
+                
+                col_copy_c , col_success_c = st.columns([1,7])
+                if col_copy_c.button("📋",key="copy_graph_chat"):
+                    chat_formatted = chat_history_formatter(st.session_state.chat_graph_history)
+                    pyperclip.copy(chat_formatted)
+                    col_success_c.success("Historique copié !")
+            
+
+
+        
+
+    
+    
+doc_dialog_main()
+
+
+
+    

audit_page/knowledge_graph.py

@@ -131,7 +131,8 @@ def convert_neo4j_to_agraph(neo4j_graph, node_colors):
 def display_graph(edges, nodes, config):
     # Display the Agraph visualization
     return agraph(edges=edges, nodes=nodes, config=config)
-    
+
+
 
 def filter_nodes_by_types(nodes:list[Node], node_types_filter:list) -> list[Node]:
     filtered_nodes = []
@@ -152,7 +153,8 @@ def change_view_dialog():
             del st.session_state.filter_views[item]
             st.session_state.current_view = "Vue par défaut"
             st.rerun()
-        if col3.button("✅", key=f"valid{index}"):
+        but_content = "🔍" if st.session_state.current_view != item else "✅"
+        if col3.button(but_content, key=f"valid{index}"):
             st.session_state.current_view = item
             st.rerun()
         if len(st.session_state.filter_views.keys()) > index:

config.json

@@ -1,5 +1,5 @@
 {
-    "height": "650px",
+    "height": "600px",
     "width": "1200px",
     "autoResize": true,
 

utils/kg/barnes_algo.py

@@ -0,0 +1,211 @@
+from __future__ import division
+import numpy as np
+import math
+import matplotlib.pyplot as plt
+import matplotlib.animation as animation
+import matplotlib.patches as patches
+import random
+
+theta = 0.5
+AU = (149.6e6 * 1000)     # 149.6 million km, in meters.
+G = 6.67408e-11 #m^3 kg^-1 s^-2
+fig1 = plt.figure()
+sim = fig1.add_subplot(111, aspect='equal')
+fig2 = plt.figure()
+quadt = fig2.add_subplot(111, aspect='equal')
+
+class Node:
+    children = None
+    mass = None
+    center_of_mass = None
+    bbox = None
+    vx = vy = None
+
+def quad_insert(root, x, y, m):
+    if root.mass is None:   #when the root is empty, add the first particle
+        root.mass = m
+        root.center_of_mass = [x,y]
+        return
+    elif root.children is None:
+        root.children = [None,None,None,None]
+        old_quadrant = quadrant_of_particle(root.bbox, root.center_of_mass[0], root.center_of_mass[1])
+        if root.children[old_quadrant] is None:
+            root.children[old_quadrant] = Node()
+            root.children[old_quadrant].bbox = quadrant_bbox(root.bbox,old_quadrant)
+        quad_insert(root.children[old_quadrant], root.center_of_mass[0], root.center_of_mass[1], root.mass)
+        new_quadrant = quadrant_of_particle(root.bbox, x, y)
+        if root.children[new_quadrant] is None:
+            root.children[new_quadrant] = Node()
+            root.children[new_quadrant].bbox = quadrant_bbox(root.bbox,new_quadrant)
+        quad_insert(root.children[new_quadrant], x, y, m)
+        root.center_of_mass[0] = (root.center_of_mass[0]*root.mass + x*m) / (root.mass + m)
+        root.center_of_mass[1] = (root.center_of_mass[1]*root.mass + y*m) / (root.mass + m)
+        root.mass = root.mass + m
+    else:
+        new_quadrant = quadrant_of_particle(root.bbox, x, y)
+        if root.children[new_quadrant] is None:
+            root.children[new_quadrant] = Node()
+            root.children[new_quadrant].bbox = quadrant_bbox(root.bbox, new_quadrant)
+        quad_insert(root.children[new_quadrant], x, y, m)
+        root.center_of_mass[0] = (root.center_of_mass[0]*root.mass + x*m) / (root.mass + m)
+        root.center_of_mass[1] = (root.center_of_mass[1]*root.mass + y*m) / (root.mass + m)
+        root.mass = root.mass + m
+
+def display(root):
+    if root.mass is None:
+        return
+    if root.children is not None:
+        x = (root.bbox[0] + root.bbox[1]) / 2
+        y = (root.bbox[2] + root.bbox[3]) / 2
+        width = x-root.bbox[0]
+        plt_node(root.bbox[0], root.bbox[2], width)
+        plt_node(root.bbox[0], y, width)
+        plt_node(x, root.bbox[2], width)
+        plt_node(x, y, width)
+        for i in xrange(4):
+            if root.children[i] is not None:
+                display(root.children[i])
+    else:
+        quadt.scatter(root.center_of_mass[0], root.center_of_mass[1])
+
+def integrate(particles):
+    bodies = particles
+    n = len(bodies)
+    timestep = 24*3600 #one day
+    years = 2 * 365 #how many Earth years that simulate
+    for day in xrange(years):
+        particles_force = {}
+        root = Node()
+        root.center_of_mass = []
+        root.bbox = find_root_bbox(bodies)
+        for i in xrange(n):
+            quad_insert(root, bodies[i][3], bodies[i][4], bodies[i][2])
+        for i in xrange(n):
+            total_fx, total_fy = compute_force(root,bodies[i][3],bodies[i][4],bodies[i][2])
+            particles_force[bodies[i][0]] = (total_fx, total_fy)
+        for i in xrange(n):
+            fx, fy = particles_force[bodies[i][0]]
+            bodies[i][5] += fx / bodies[i][2] * timestep
+            bodies[i][6] += fy / bodies[i][2] * timestep
+
+            bodies[i][3] += bodies[i][5] * timestep
+            bodies[i][4] += bodies[i][6] * timestep
+            sim.scatter(bodies[i][3], bodies[i][4], c=bodies[i][1])
+    display(root)
+    quadt.scatter(root.center_of_mass[0], root.center_of_mass[1], c='red', marker='x')
+
+def compute_force(root,x,y,m):
+    if root.mass is None:
+        return 0, 0
+    if root.center_of_mass[0] == x and root.center_of_mass[1] == y and root.mass == m:
+        return 0, 0
+    d = root.bbox[1]-root.bbox[0]
+    r = distance(x,y, root.center_of_mass[0], root.center_of_mass[1])
+    if d/r < theta or root.children is None:
+        return force(m, x, y, root.mass, root.center_of_mass[0], root.center_of_mass[1])
+    else:
+        fx = 0.0
+        fy = 0.0
+        for i in xrange(4):
+            if root.children[i] is not None:
+                fx += compute_force(root.children[i],x,y,m)[0]
+                fy += compute_force(root.children[i],x,y,m)[1]
+        return fx, fy
+
+################################################# SUPPORTING FUNCTION ##############################################################
+
+def force(m, x, y, mcm, xcm, ycm):
+    d = distance(x, y, xcm, ycm)
+    f = G*m*mcm/(d**2)
+    dx = xcm - x
+    dy = ycm - y
+    angle = math.atan2(dy, dx)
+    fx = math.cos(angle) * f
+    fy = math.sin(angle) * f
+    return fx, fy
+
+def distance(x1, y1, x2, y2):
+    return math.sqrt((x2-x1)**2+(y2-y1)**2)
+
+def plt_node(x, y, width):
+    quadt.add_patch(patches.Rectangle((x, y), width, width, fill = False))
+
+def find_root_bbox(array):
+    """ Create a suitable square boundary box for the input particles
+    """
+    if len(array) == 0 or len(array) == 1:
+        return None
+    xmin, xmax, ymin, ymax = array[0][3], array[0][3], array[0][4], array[0][4]
+    for i in xrange(len(array)):
+        if array[i][3] > xmax:
+            xmax = array[i][3]
+        if array[i][3] < xmin:
+            xmin = array[i][3]
+        if array[i][4] > ymax:
+            ymax = array[i][4]
+        if array[i][4] < ymin:
+            ymin = array[i][4]
+    if xmax - xmin == ymax - ymin:
+        return xmin, xmax, ymin, ymax
+    elif xmax - xmin > ymax - ymin:
+        return xmin, xmax, ymin, ymax+(xmax-xmin-ymax+ymin)
+    else:
+        return xmin, xmax+(ymax-ymin-xmax+xmin), ymin, ymax
+
+def quadrant_of_particle(bbox, x, y):
+    """Return position of quadrant of the particle (x,y)
+    """
+    if y >= (bbox[3] + bbox[2])/2:
+        if x <= (bbox[1] + bbox[0])/2:
+            return 0
+        else:
+            return 1
+    else:
+        if x >= (bbox[1] + bbox[0])/2:
+            return 2
+        else:
+            return 3
+
+def quadrant_bbox(bbox,quadrant):
+    """Return the coordinate of the quadrant
+    """
+    x = (bbox[0] + bbox[1]) / 2
+    y = (bbox[2] + bbox[3]) / 2
+    #Quadrant 0: (xmin, x, y, ymax)
+    if quadrant == 0:
+        return bbox[0], x, y, bbox[3]
+    #Quadrant 1: (x, xmax, y, ymax)
+    elif quadrant == 1:
+        return x, bbox[1], y, bbox[3]
+    #Quadrant 2: (x, xmax, ymin, y)
+    elif quadrant == 2:
+        return x, bbox[1], bbox[2], y
+    #Quadrant 3: (xmin, x, ymin, y)
+    elif quadrant == 3:
+        return bbox[0], x, bbox[2], y
+
+def data_from_file(filename, array):
+    with open(filename) as f:
+        for line in f:
+            if line[0] == '#':
+                continue
+            else:
+                name,color,m,x,y,vx,vy = line.split(',')
+                array.append([name,color,float(m),float(x)*AU,float(y)*AU,float(vx)*1000,float(vy)*1000])
+
+if __name__ == '__main__':
+    filename = ('solar-system.txt')
+    particles = []
+    data_from_file(filename, particles)
+    #root = Node()
+    #root.center_of_mass = []
+    #root.bbox = find_root_bbox(particles)
+    #for i in xrange(len(particles)):
+    #    quad_insert(root, particles[i][3], particles[i][4], particles[i][2])
+    #print 'Boundary box: ',root.bbox
+    #print 'Total mass: ',root.mass
+    #print 'Coordinate of center of mass: ',root.center_of_mass
+    #plt.scatter(root.center_of_mass[0], root.center_of_mass[1], c='r', marker='x', s=50)
+    #print 'Theta: ', theta
+    integrate(particles)
+    plt.show()