from llama_index.readers.schema.base import Document

from llmsherpa.readers import LayoutPDFReader

llmsherpa_api_url = "https://readers.llmsherpa.com/api/document/developer/parseDocument?renderFormat=all"
pdf_path = "2023190_riteaid_complaint_filed.pdf" # also allowed is a file path e.g. /home/downloads/xyz.pdf
pdf_reader = LayoutPDFReader(llmsherpa_api_url)
doc = pdf_reader.read_pdf(pdf_path)

doc = pdf_reader.read_pdf(pdf_path)
for chunk in doc.chunks():
    # Create a Document object for each chunk.
    document = Document(text=chunk.to_context_text(), extra_info={})

from llama_index.prompts import PromptTemplate

# Define your custom prompt format
template = (
    "<|system|>\n"
    "{System}\n"
    "<|user|>\n"
    "{User}\n"
    "<|assistant|>\n"
    "{Assistant}"
)
# Create a PromptTemplate with your custom format
custom_prompt = PromptTemplate(template)

# Sample prompts.
prompts = [
    "Hello, my name is",
    "The president of the United States is",
    "The capital of France is",
    "The future of AI is",
]
# Create a sampling params object.
sampling_params = SamplingParams(temperature=0.8, top_p=0.95)

# Create an LLM.
llm = LLM(model="TheBloke/Llama-2-7b-Chat-AWQ", quantization="AWQ")
# Generate texts from the prompts. The output is a list of RequestOutput objects
# that contain the prompt, generated text, and other information.
outputs = llm.generate(prompts, sampling_params)
# Print the outputs.
for output in outputs:
    prompt = output.prompt
    generated_text = output.outputs[0].text
    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")