Update app.py

app.py

@@ -1,37 +1,39 @@
+__import__('pysqlite3')
+import sys
+
+sys.modules['sqlite3'] = sys.modules.pop('pysqlite3')
+
 from langchain.embeddings.openai import OpenAIEmbeddings
 from langchain.vectorstores import Chroma
-from langchain.text_splitter import CharacterTextSplitter, RecursiveCharacterTextSplitter
-from langchain.chains.question_answering import load_qa_chain
+from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain.chat_models import ChatOpenAI
 from langchain.chains import RetrievalQA
 from langchain.document_loaders import BSHTMLLoader, DirectoryLoader
-from langchain.agents import initialize_agent, Tool, AgentType
-from langchain.agents import AgentType
-from langchain.tools import BaseTool
-from langchain import LLMMathChain, SerpAPIWrapper
+from langchain import SerpAPIWrapper
 from langchain.memory import ConversationBufferMemory, ReadOnlySharedMemory
 from langchain.agents import ZeroShotAgent, Tool, AgentExecutor
-from langchain import OpenAI, LLMChain, PromptTemplate
+from langchain import LLMChain
 
 import os
 from glob import glob
 import shutil
 
-files = glob("./shakespeare/**/*.html")
+files = glob("shakespeare/**/*.html")
 
-os.mkdir('./data')
 destination_folder = './data/'
+if not os.path.exists(destination_folder):
+    os.mkdir('./data')
 
-for html_file in files:
-  shutil.move(html_file, destination_folder + html_file.split("/")[-1])
+    for html_file in files:
+        shutil.copy(html_file, destination_folder + html_file.split("/")[-1])
 
 bshtml_dir_loader = DirectoryLoader('./data/', loader_cls=BSHTMLLoader)
 data = bshtml_dir_loader.load()
 
 text_splitter = RecursiveCharacterTextSplitter(
-    chunk_size = 1000,
-    chunk_overlap  = 20,
-    length_function = len,
+    chunk_size=1000,
+    chunk_overlap=20,
+    length_function=len,
 )
 
 documents = text_splitter.split_documents(data)
@@ -53,22 +55,22 @@ search = SerpAPIWrapper()
 memory = ConversationBufferMemory(memory_key="chat_history")
 readonlymemory = ReadOnlySharedMemory(memory=memory)
 
-shakespeare_qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=doc_retriever, memory=readonlymemory)
+shakespeare_qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=doc_retriever,
+                                             memory=readonlymemory)
 
 tools = [
     Tool(
-        name = "Shakespeare QA System",
+        name="Shakespeare QA System",
         func=shakespeare_qa.run,
         description="useful for when you need to answer questions about Shakespeare's works. Input should be a fully formed question."
     ),
     Tool(
-        name = "SERP API Search",
+        name="SERP API Search",
         func=search.run,
         description="useful for when you need to answer questions about ruff (a python linter). Input should be a fully formed question."
     ),
 ]
 
-
 prefix = """Have a conversation with a human, answering the following questions as best you can. You have access to the following tools:"""
 suffix = """Begin!"
 
@@ -77,9 +79,9 @@ Question: {input}
 {agent_scratchpad}"""
 
 prompt = ZeroShotAgent.create_prompt(
-    tools, 
-    prefix=prefix, 
-    suffix=suffix, 
+    tools,
+    prefix=prefix,
+    suffix=suffix,
     input_variables=["input", "chat_history", "agent_scratchpad"]
 )
 
@@ -90,9 +92,10 @@ agent_chain = AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbo
 
 
 def make_inference(query):
-    response = agent_chain.run(input="What age was she in the play?")
+    response = agent_chain.run(input=query)
     return (response)
 
+
 if __name__ == "__main__":
     # make a gradio interface
     import gradio as gr