Update DocuChat.py

DocuChat.py

@@ -8,60 +8,59 @@ from langchain.embeddings import OpenAIEmbeddings
 from langchain.vectorstores import Chroma
 import panel as pn
 
-# Set global sizing mode
-pn.config.sizing_mode = 'stretch_width'
-
-# Panel extension
-pn.extension()
-
-file_input = pn.widgets.FileInput(height=45)
-openaikey = pn.widgets.PasswordInput(value="", placeholder="Enter your OpenAI API Key here...", height=45)
-chatbox = pn.widgets.ChatBox(height=300, primary_name="User")
+class LangChainConversation:
+    def __init__(self):
+        self.file_input = pn.widgets.FileInput(height=45)
+        self.openaikey = pn.widgets.PasswordInput(value="", placeholder="Enter your OpenAI API Key here...", height=45)
+        self.chatbox = pn.widgets.ChatBox(height=300, primary_name="User")
+        self.chatbox.param.watch(self.qa_result, 'value')
 
-def remove_empty_lines(text):
-    lines = re.split(r'\r\n|\r|\n', text)
-    return '\n'.join([line.strip() for line in lines if line.strip()])
+    def remove_empty_lines(self, text):
+        lines = re.split(r'\r\n|\r|\n', text)
+        return '\n'.join([line.strip() for line in lines if line.strip()])
 
-def qa(file, query):
-    loader = PyPDFLoader(file)
-    documents = loader.load()
-    text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
-    texts = text_splitter.split_documents(documents)
-    embeddings = OpenAIEmbeddings()
-    db = Chroma.from_documents(texts, embeddings)
-    retriever = db.as_retriever(search_type="similarity", search_kwargs={"k": 3})
-    qa = RetrievalQA.from_chain_type(llm=OpenAI(), chain_type="stuff", retriever=retriever, return_source_documents=True)
-    result = qa({"query": query})
-    return result['result']
+    def qa(self, file, query):
+           loader = PyPDFLoader(file)
+            documents = loader.load()
+            text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
+            texts = text_splitter.split_documents(documents)
+            embeddings = OpenAIEmbeddings()
+            db = Chroma.from_documents(texts, embeddings)
+            retriever = db.as_retriever(search_type="similarity", search_kwargs={"k": 3})
+        qa = RetrievalQA.from_chain_type(llm=OpenAI(), chain_type="stuff", retriever=retriever, return_source_documents=True)
+            result = qa({"query": query})
+            return result['result']
 
-def qa_result(event):
-    print("Debugging: Event triggered")  # Debugging Line 0
-    if len(event.new) > len(event.old):
-        os.environ["OPENAI_API_KEY"] = openaikey.value
-        if file_input.value is not None:
-            file_input.save("/.cache/temp.pdf")
-            prompt_text = remove_empty_lines(event.new[-1][chatbox.primary_name])
-            print("Debugging: Prompt text:", prompt_text)  # Debugging Line 1
-            print("Debugging: Chat input from user:", event.new[-1][chatbox.primary_name])  # Debugging Line 1.1
-            if prompt_text:
-                print("Debugging: Calling Langchain")  # Debugging Line 2
-                result = qa(file="/.cache/temp.pdf", query=prompt_text)
-                print("Debugging: Result from Langchain:", result)  # Debugging Line 3
-                # Append the AI's response to the chatbox
-                new_value = chatbox.value.copy()  # Copy the existing value
-                new_value.append({"AI": result})   # Append the AI's response
-                chatbox.value = new_value          # Assign the new value
-                print("Debugging: Appended result to chatbox")  # Debugging Line 4
+    def qa_result(self, event):
+        print("Debugging: Event triggered")
+        if len(event.new) > len(event.old):
+            os.environ["OPENAI_API_KEY"] = self.openaikey.value
+            if self.file_input.value is not None:
+                self.file_input.save("/.cache/temp.pdf")
+                prompt_text = self.remove_empty_lines(event.new[-1][self.chatbox.primary_name])
+                print("Debugging: Prompt text:", prompt_text)
+                if prompt_text:
+                    print("Debugging: Calling Langchain")
+                    result = self.qa(file="/.cache/temp.pdf", query=prompt_text)
+                    print("Debugging: Result from Langchain:", result)
+                    # Append the AI's response to the chatbox
+                    new_value = self.chatbox.value.copy()
+                    new_value.append({"AI": result})
+                    self.chatbox.value = new_value
+                    print("Debugging: Appended result to chatbox")
 
+    def view(self):
+        layout = pn.Column(
+            pn.pane.Markdown("""
+            # DocuChat
+            AI-Powered Query Engine for Document Insights (powered by LangChain & OpenAI)
+            ...
+            """),
+            pn.Row(self.file_input, self.openaikey), self.chatbox
+        )
+        return layout.servable()
 
-chatbox.param.watch(qa_result, 'value')
-
-layout = pn.Column(
-    pn.pane.Markdown("""
-    # DocuChat
-    AI-Powered Query Engine for Document Insights (powered by LangChain & OpenAI)
-    ...
-    """),
-    pn.Row(file_input, openaikey), chatbox
-).servable()
-print("Debugging: Application is ready")  # Debugging Line 4
+pn.config.sizing_mode = 'stretch_width'
+pn.extension()
+chat = LangChainConversation()
+chat.view()