Update app.py

app.py

@@ -3,35 +3,57 @@ import re
 from dotenv import load_dotenv
 load_dotenv()
 
-from langchain.agents.openai_assistant import OpenAIAssistantRunnable
-from langchain.agents import AgentExecutor
+import gradio as gr
 
+from langchain.agents.openai_assistant import OpenAIAssistantRunnable
 from langchain.schema import HumanMessage, AIMessage
 
-import gradio
-
 api_key = os.getenv('OPENAI_API_KEY')
 extractor_agent = os.getenv('ASSISTANT_ID_SOLUTION_SPECIFIER_A')
 
-extractor_llm = OpenAIAssistantRunnable(assistant_id=extractor_agent, api_key=api_key, as_agent=True)
+# Create the assistant. By default, we don't specify a thread_id,
+# so the first call that doesn't pass one will create a new thread.
+extractor_llm = OpenAIAssistantRunnable(
+    assistant_id=extractor_agent,
+    api_key=api_key,
+    as_agent=True
+)
+
+# We will store thread_id globally or in a session variable.
+THREAD_ID = None
 
 def remove_citation(text):
-    # Define the regex pattern to match the citation format 【number†text】
     pattern = r"【\d+†\w+】"
-    # Replace the pattern with an empty string
     return re.sub(pattern, "📚", text)
 
 def predict(message, history):
-    history_langchain_format = []
-    for human, ai in history:
-        history_langchain_format.append(HumanMessage(content=human))
-        history_langchain_format.append(AIMessage(content=ai))
-    history_langchain_format.append(HumanMessage(content=message))
-    gpt_response = extractor_llm.invoke({"content": message})
-    output = gpt_response.return_values["output"]
+    """
+    Receives the new user message plus the entire conversation history 
+    from Gradio. If no thread_id is set, we create a new thread. 
+    Otherwise we pass the existing thread_id.
+    """
+    global THREAD_ID
+    
+    # 1) Decide if we are creating a new thread or continuing the old one
+    if THREAD_ID is None:
+        # No thread_id yet -> this is the first user message
+        response = extractor_llm.invoke({"content": message})
+        THREAD_ID = response.thread_id  # store for subsequent calls
+    else:
+        # We already have a thread_id -> continue that same thread
+        response = extractor_llm.invoke({"content": message, "thread_id": THREAD_ID})
+    
+    # 2) Extract the text output from the response
+    output = response.return_values["output"]
     non_cited_output = remove_citation(output)
+    
+    # 3) Return the model's text to display in Gradio
     return non_cited_output
 
-#gradio.Markdown("Click [here](https://www.google.com) to visit Google.")
-chat = gradio.ChatInterface(predict, title="Solution Specifier A", description="testing for the time being")
+# Create a Gradio ChatInterface using our predict function
+chat = gr.ChatInterface(
+    fn=predict, 
+    title="Solution Specifier A", 
+    description="Testing threaded conversation"
+)
 chat.launch(share=True)