Update DocuChat.py

DocuChat.py

@@ -41,28 +41,16 @@ class LangchainConversation:
         lines = re.split(r'\r\n|\r|\n', text)
         return '\n'.join([line.strip() for line in lines if line.strip()])
 
-
-    def get_chat_history(self, inputs):
-        chat_history_str = ""
-        for human, ai in inputs:
-            chat_history_str += f"User: {human}\nAI: {ai}\n"
-        return chat_history_str
-
     def qa(self, file, query):
         loader = PyPDFLoader(file)
         documents = loader.load()
-        text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0, context_aware=True)
+        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})
-        question_generator = LLMChain(llm=LangchainOpenAI(), prompt="Your Prompt Here")
-        doc_chain = RetrievalQA.from_chain_type(llm=LangchainOpenAI(), chain_type="stuff", retriever=retriever, return_source_documents=True)
-        qa = ConversationalRetrievalChain(retriever=retriever, combine_docs_chain=doc_chain, question_generator=question_generator)
-        chat_history = self.chat_history if hasattr(self, 'chat_history') else []
-        result = qa({"question": query, "chat_history": chat_history})
-        chat_history.append((query, result["result"]))
-        self.chat_history = chat_history
+        qa = RetrievalQA.from_chain_type(llm=LangchainOpenAI(), chain_type="stuff", retriever=retriever, return_source_documents=True)
+        result = qa({"query": query})
         return result['result']
 
     def view(self):