kg

audit_page/knowledge_graph.py

@@ -4,7 +4,8 @@ from utils.audit.rag import get_text_from_content_for_doc,get_text_from_content_
 from streamlit_agraph import agraph, Node, Edge, Config
 import random
 import math
-from utils.audit.response_llm import generate_response_openai
+from utils.audit.response_llm import generate_response_via_langchain
+from langchain_core.messages import AIMessage, HumanMessage
 
 def if_node_exists(nodes, node_id):
     """
@@ -121,7 +122,7 @@ def convert_neo4j_to_agraph(neo4j_graph, node_colors):
         edges.append(Edge(source=source_id, label=label, target=target_id))
 
     # Define the configuration for Agraph
-    config = Config(width=1200, height=950, directed=True, physics=False, hierarchical=False, nodeSpacing=500)
+    config = Config(width=1200, height=800, directed=True, physics=False, hierarchical=False, nodeSpacing=500)
 
     # Create the Agraph visualization
 
@@ -129,7 +130,8 @@ def convert_neo4j_to_agraph(neo4j_graph, node_colors):
 
 def display_graph(edges, nodes, config):
     # Display the Agraph visualization
-    agraph(edges=edges, nodes=nodes, config=config)
+    return agraph(edges=edges, nodes=nodes, config=config)
+    
 
 def filter_nodes_by_types(nodes:list[Node], node_types_filter:list) -> list[Node]:
     filtered_nodes = []
@@ -141,6 +143,13 @@ def filter_nodes_by_types(nodes:list[Node], node_types_filter:list) -> list[Node
 
 def kg_main():
     #st.set_page_config(page_title="Graphe de connaissance", page_icon="", layout="wide")
+    
+
+    
+    if "audit" not in st.session_state or st.session_state.audit == {}:
+        st.error("Veuillez d'abord effectuer un audit pour visualiser le graphe de connaissance.")
+        return
+    
     if "graph" not in st.session_state:
         st.session_state.graph = None
     st.title("Graphe de connaissance")
@@ -151,10 +160,8 @@ def kg_main():
     if "summary" not in st.session_state:
         st.session_state.summary = None
 
-    
-    if "audit" not in st.session_state or st.session_state.audit == {}:
-        st.error("Veuillez d'abord effectuer un audit pour obtenir des recommandations d'agents.")
-        return
+    if "chat_graph_history" not in st.session_state:
+        st.session_state.chat_graph_history = []
     
     audit = st.session_state.audit_simplified
     content = st.session_state.audit["content"]
@@ -186,11 +193,56 @@ def kg_main():
         #st.write(graph)
         
         edges,nodes,config = convert_neo4j_to_agraph(graph[0],st.session_state.node_types)
-        filter = st.multiselect("Filtrer selon l'étiquette",st.session_state.node_types.keys(),placeholder="Sélectionner une ou plusieurs étiquettes")
         
-        if filter:
-            nodes = filter_nodes_by_types(nodes,filter)
-        display_graph(edges,nodes,config)
+        col1, col2 = st.columns([2.5, 1.5])
+
+        with col1.container(border=True,height=800):
+            filter_col,param_col = st.columns([4,1])
+            with param_col.popover("⚙️"):
+                for node_type,color in st.session_state.node_types.items():
+                    color = st.color_picker(f"La couleur de l'entité **{node_type}**",color)
+                    st.session_state.node_types[node_type] = color
+                
+            filter = filter_col.multiselect("Filtrer selon l'étiquette",st.session_state.node_types.keys(),placeholder="Sélectionner une ou plusieurs étiquettes")
+            if filter:
+                nodes = filter_nodes_by_types(nodes,filter) 
+
+            selected = display_graph(edges,nodes,config)
+
+        with col2.container(border=True,height=800):
+            st.markdown("##### Dialoguer avec le graphe")
+
+            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("Moi"):
+                        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}, {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])))
+            
+            
+
 
     node_types = st.session_state.node_types
     

requirements.txt

@@ -23,3 +23,4 @@ python-dotenv
 langchain-experimental 
 neo4j
 streamlit-agraph
+