from langchain_stack_overflow_for_teams import StackOverflowTeamsApiV3Loaderloader = StackOverflowTeamsApiV3Loader(
   access_token=os.environ.get("SO_PAT"),
   team="my team",
   content_type="articles",
)
docs = loader.load()

from langchain_stack_overflow_for_teams import StackOverflowTeamsApiV3Loaderloader = StackOverflowTeamsApiV3Loader(
   access_token=os.environ.get("SO_PAT"),
   team="my team",
   content_type="questions",
   has_accepted_answer="true",
,
)
docs = loader.load()

from langchain_stack_overflow_for_teams import StackOverflowTeamsApiV3Loaderloader = StackOverflowTeamsApiV3Loader(
   endpoint="[your_site].stackenterprise.co/api",
   access_token=os.environ.get("SO_API_TOKEN"),
   content_type="articles",
)
docs = loader.load()

from langchain_stack_overflow_for_teams import StackOverflowTeamsApiV3Loaderloader = StackOverflowTeamsApiV3Loader(
   endpoint="[your_site].stackenterprise.co/api",
   access_token=os.environ.get("SO_API_TOKEN"),
   team="my team",
   content_type="articles",
)
docs = loader.load()

""" This script demonstrates use the Langchain add_documents model to naively load all documents every time (easy, but not efficient) """
import os
from dotenv import load_dotenv
from langchain_openai import AzureChatOpenAI, AzureOpenAIEmbeddings
from langchain_community.vectorstores import LanceDB
from langchain_text_splitters import HTMLSemanticPreservingSplitter
from langchain_stack_overflow_for_teams import StackOverflowTeamsApiV3Loader
from langchain.tools.retriever import create_retriever_tool
from langchain_core.prompts import ChatPromptTemplate
from langchain.agents import AgentExecutor, create_tool_calling_agentdef main():
   load_dotenv()   # initialize the LLM using gpt-4o-mini from Azure OpenAI
   llm = AzureChatOpenAI(
       azure_deployment="gpt-4o-mini",
       api_version="2025-01-01-preview",
   )   # initialize the embeddings using Azure OpenAI
   embeddings = AzureOpenAIEmbeddings()   # initialize the LanceDB vector store
   db = LanceDB(
       table_name="docs",
       uri="./db/lancedb",
       embedding=embeddings,
   )   # load documents using our StackOverflowTeamsApiV3Loader document loader
   loader = StackOverflowTeamsApiV3Loader(
       endpoint="[your_site].stackenterprise.co/api",
       access_token=os.environ.get("SO_API_TOKEN"),
       team="[your_team]",
       date_from="2021-05-01T00:00:00Z",
       sort="activity",
       order="desc",
       content_type="questions",
       is_answered="true",
       has_accepted_answer="true",
   )
   docs = loader.load()
   print(f"Loaded {len(docs)} documents")   # chunk the documents using the HTMLSemanticPreservingSplitter
   print("Chunking documents...")
   documents = HTMLSemanticPreservingSplitter(
       headers_to_split_on=[("h1", "Header 1"), ("h2", "Header 2")],
       max_chunk_size=1000,
       chunk_overlap=200,
       preserve_parent_metadata=True
   ).transform_documents(docs)
   print(f"Chunked {len(documents)} documents.")
   if len(documents) > 0:
       print(documents[0])       # load the embeddings into our LanceDB vector store
       db.add_documents(documents)   # build a retriever tool from the LanceDB vector store for use by the LLM
   retriever = db.as_retriever()
   retriever_tool = create_retriever_tool(
       retriever=retriever,
       name="StackOverflowTeamsRetriever",
       description="Retrieves Stack Overflow for Teams questions and answers",
   )   # set up the prompt template for the agent
   prompt = ChatPromptTemplate.from_messages(
       [
           ("system", "You are a helpful assistant that answers questions based on Stack Overflow for Teams data."),
           ("human", "{input}"),
           ("placeholder", "{agent_scratchpad}"),
       ]
   )   # create the agent with the LLM and the retriever tool
   tools = [retriever_tool]
   agent = create_tool_calling_agent(llm, tools, prompt)
   agent_executor = AgentExecutor(agent=agent, tools=tools)   # run the agent with an example question that could be answered by the Stack Overflow for Teams data
   result = agent_executor.invoke({"input": "what is the SLA for Stack Overflow for Teams Enterprise?"})
   print(result)if __name__ == "__main__":
   main()