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?")

list_tool = QueryEngineTool.from_defaults(
    query_engine=list_query_engine,
    description=(
        "Useful for summarization questions related to Paul Graham eassy on"
        " What I Worked On."
    ),
)

vector_tool = QueryEngineTool.from_defaults(
    query_engine=vector_query_engine,
    description=(
        "Useful for retrieving specific context from Paul Graham essay on What"
        " I Worked On."
    ),
)

query_engine = RouterQueryEngine(
    selector=LLMSingleSelector.from_defaults(),
    query_engine_tools=[
        list_tool,
        vector_tool,
    ],
)

# load and parse
documents = SimpleDirectoryReader("data").load_data()

# embed and index
index = VectorStoreIndex.from_documents(documents)

# generate chat engine
chat_engine = index.as_chat_engine()

# start chatting
response = query_engine.chat("What did the author do growing up?")
print(response)

# set up list of tools
query_engine_tools = [
    QueryEngineTool(
        query_engine=vector_query_engine,
        metadata=ToolMetadata(
            name="pg_essay",
            description="Paul Graham essay on What I Worked On",
        ),
    ),
    # more query engine tools here
]

# create engine from tools
query_engine = SubQuestionQueryEngine.from_defaults(
    query_engine_tools=query_engine_tools,
    use_async=True,
)

# define sample Tool
def multiply(a: int, b: int) -> int:
    """Multiply two integers and returns the result integer"""
    return a * b

multiply_tool = FunctionTool.from_defaults(fn=multiply)

# initialize ReAct agent
agent = ReActAgent.from_tools(
  [
    multiply_tool
    # other tools here
  ], 
  verbose=True
)

Thought: I need to use a tool to help me answer the question.
Action: multiply
Action Input: {"a": 2, "b": 4}
Observation: 8
Thought: I need to use a tool to help me answer the question.
Action: add
Action Input: {"a": 20, "b": 8}
Observation: 28
Thought: I can answer without using any more tools.
Answer: 28

# create the function calling worker for reasoning
worker = FunctionCallingAgentWorker.from_tools(
    [lyft_tool, uber_tool], verbose=True
)

# wrap the worker in the top-level planner
agent = StructuredPlannerAgent(
    worker, tools=[lyft_tool, uber_tool], verbose=True
)

response = agent.chat(
    "Summarize the key risk factors for Lyft and Uber in their 2021 10-K filings."
)

=== Initial plan ===
Extract Lyft Risk Factors:
Summarize the key risk factors from Lyft's 2021 10-K filing. -> A summary of the key risk factors for Lyft as outlined in their 2021 10-K filing.
deps: []


Extract Uber Risk Factors:
Summarize the key risk factors from Uber's 2021 10-K filing. -> A summary of the key risk factors for Uber as outlined in their 2021 10-K filing.
deps: []


Combine Risk Factors Summaries:
Combine the summaries of key risk factors for Lyft and Uber from their 2021 10-K filings into a comprehensive overview. -> A comprehensive summary of the key risk factors for both Lyft and Uber as outlined in their respective 2021 10-K filings.
deps: ['Extract Lyft Risk Factors', 'Extract Uber Risk Factors']

agent_worker = LATSAgentWorker.from_tools(
    query_engine_tools,
    llm=llm,
    num_expansions=2,
    max_rollouts=3,
    verbose=True,
)
agent = agent.as_worker()

task = agent.create_task(
    "Given the risk factors of Uber and Lyft described in their 10K files, "
    "which company is performing better? Please use concrete numbers to inform your decision."
)

from llama_index.llms.openai import OpenAI

class OpenAIGenerator(Workflow):
    @step
    async def generate(self, ev: StartEvent) -> StopEvent:
        query = ev.get("query")
        llm = OpenAI()
        response = await llm.acomplete(query)
        return StopEvent(result=str(response))

w = OpenAIGenerator(timeout=10, verbose=False)
result = await w.run(query="What's LlamaIndex?")
print(result)

class LoopExampleFlow(Workflow):

    @step
    async def answer_query(self, ev: StartEvent | QueryEvent ) -> FailedEvent | StopEvent:
        query = ev.query
        # try to answer the query
        random_number = random.randint(0, 1)
        if (random_number == 0):
            return FailedEvent(error="Failed to answer the query.")
        else:
            return StopEvent(result="The answer to your query")
        
    @step
    async def improve_query(self, ev: FailedEvent) -> QueryEvent | StopEvent:
        # improve the query or decide it can't be fixed
        random_number = random.randint(0, 1)
        if (random_number == 0):
            return QueryEvent(query="Here's a better query.")
        else:
            return StopEvent(result="Your query can't be fixed.")

l = LoopExampleFlow(timeout=10, verbose=True)
result = await l.run(query="What's LlamaIndex?")
print(result)

draw_all_possible_flows()

class RAGWorkflow(Workflow):
    @step
    async def ingest(self, ctx: Context, ev: StartEvent) -> Optional[StopEvent]:
        dataset_name = ev.dataset
        documents = SimpleDirectoryReader("data").load_data()
        ctx.data["INDEX"] = VectorStoreIndex.from_documents(documents=documents)
        return StopEvent(result=f"Indexed {len(documents)} documents.")
        
    ...

class MyWorkflow(RAGWorkflow):
    @step
    def rerank(
        self, ctx: Context, ev: Union[RetrieverEvent, StartEvent]
    ) -> Optional[QueryResult]:
        # my custom reranking logic here
        
 
w = MyWorkflow(timeout=60, verbose=True)
result = await w.run(query="Who is Paul Graham?")