Update generate_answer.py

generate_answer.py

@@ -1,8 +1,9 @@
+# generate_answer.py
+
 import os
 from glob import glob
-# import subprocess
-
 import openai
+from openai import OpenAI
 from dotenv import load_dotenv
 
 from langchain.embeddings import OpenAIEmbeddings
@@ -14,34 +15,31 @@ from langchain_community.chat_models import ChatOpenAI
 from langchain.chains import RetrievalQA
 from langchain.memory import ConversationBufferMemory
 
-
 load_dotenv()
 api_key = os.getenv("OPENAI_API_KEY")
 
-client = openai(api_key=api_key)
+# Corrected line: Set the OpenAI API key correctly
 openai.api_key = api_key
 
-
 def base_model_chatbot(messages):
     system_message = [
-        {"role": "system", "content": "You are an helpful AI chatbot, that answers questions asked by User."}]
+        {"role": "system", "content": "You are an helpful AI chatbot, that answers questions asked by User."}
+    ]
     messages = system_message + messages
-    response = client.chat.completions.create(
-        model="gpt-3.5-turbo-1106",
+    response = openai.ChatCompletion.create(
+        model="gpt-3.5-turbo-1106",  # Ensure the model is specified correctly
         messages=messages
     )
-    return response.choices[0].message.content
+    return response.choices[0].message['content']
 
 
 class VectorDB:
     """Class to manage document loading and vector database creation."""
     
-    def __init__(self, docs_directory:str):
-
+    def __init__(self, docs_directory: str):
         self.docs_directory = docs_directory
 
     def create_vector_db(self):
-
         text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
 
         files = glob(os.path.join(self.docs_directory, "*.pdf"))
@@ -61,32 +59,22 @@ class ConversationalRetrievalChain:
     def __init__(self, model_name="gpt-3.5-turbo", temperature=0):
         self.model_name = model_name
         self.temperature = temperature
-      
-    def create_chain(self):
-
-        model = ChatOpenAI(model_name=self.model_name,
-                           temperature=self.temperature,
-                           )
 
-        memory = ConversationBufferMemory(
-            memory_key="chat_history",
-            return_messages=True
-            )
+    def create_chain(self):
+        model = ChatOpenAI(model_name=self.model_name, temperature=self.temperature)
+        memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
         vector_db = VectorDB('docs/')
-        retriever = vector_db.create_vector_db().as_retriever(search_type="similarity",
-                                                              search_kwargs={"k": 2},
-                                                              )
+        retriever = vector_db.create_vector_db().as_retriever(search_type="similarity", search_kwargs={"k": 2})
         return RetrievalQA.from_chain_type(
             llm=model,
             retriever=retriever,
             memory=memory,
-            )
+        )
     
 def with_pdf_chatbot(messages):
     """Main function to execute the QA system."""
     query = messages[-1]['content'].strip()
 
-
     qa_chain = ConversationalRetrievalChain().create_chain()
     result = qa_chain({"query": query})
-    return result['result']
+    return result['result']