24_groq_llama_parser.py

from llama_parse import LlamaParse
from llama_index.llms.groq import Groq
from llama_parse.base import ResultType, Language
from llama_index.core.node_parser import MarkdownElementNodeParser

parser = LlamaParse(
    api_key="xxx",
    result_type=ResultType.MD,
    language=Language.ENGLISH,
    parsing_instructions="""\
        The document is an exam documents. \
        It contains many tables and images. \
        Do not parse neither the definition, nor requirements, nor explanation sections.\
    """,
)

llm = Groq(
    model="llama3-8b-8192",
    api_key="xxx",
)

documents = parser.load_data("path/to/file.pdf")

node_parser = MarkdownElementNodeParser(
    llm=llm,
    summary_query_str="""
     The document is a property valuation documents. \
     It shows the key metrics for a property sale. \
     The paper includes detailed figures like the price, the size of the property, \
     the year of construction, the number of bedrooms and bathrooms. \
     Answer questions using the information in this document and be precise. \
     Skip lines for each bullet point. \
     Answer with only one number if asked for it.""",
)

nodes = node_parser.get_nodes_from_documents(documents)