documents = SimpleDirectoryReader("data").load_data()

# must have a LLAMA_CLOUD_API_KEY
# bring in deps
from llama_parse import LlamaParse
from llama_index.core import SimpleDirectoryReader

# set up parser
parser = LlamaParse(
    result_type="markdown"  # "text" also available
)

# use SimpleDirectoryReader to parse our file
file_extractor = {".pdf": parser}
documents = SimpleDirectoryReader(
	input_files=['data/canada.pdf'],
    file_extractor=file_extractor
).load_data()
print(documents)

Settings.embed_model = HuggingFaceEmbedding(model_name="BAAI/bge-small-en-v1.5")

index = VectorStoreIndex.from_documents(documents)

retriever = index.as_retriever()
nodes = retriever.retrieve("Who is Paul Graham?")

query_engine = index.as_query_engine()
response = query_engine.query("Who is Paul Graham?")

def multiply(a: float, b: float) -> float:
    """Multiply two numbers and returns the product"""
    return a * b


multiply_tool = FunctionTool.from_defaults(fn=multiply)

llm = OpenAI(model="gpt-4o", temperature=0.4)

agent = ReActAgent.from_tools(
  [multiply_tool], 
  llm=llm, 
  verbose=True
)

budget_tool = QueryEngineTool.from_defaults(
    query_engine,
    name="canadian_budget_2023",
    description="A RAG engine with some basic facts",
)

llm = OpenAI(model="gpt-4o", temperature=0.4)

agent = ReActAgent.from_tools(
  [budget_tool], 
  llm=llm, 
  verbose=True
)