Using in Python

First, get an api key. We recommend putting your key in a file called .env that looks like this:

LLAMA_CLOUD_API_KEY=llx-xxxxxx

Set up a new python environment using the tool of your choice, we used poetry init. Then install the deps you’ll need:

pip install llama-extract python-dotenv

Now we have our libraries and our API key available, let’s create a extract.py file and extract data from files. In this case, we're using invoice documents from our examples:

# bring in our LLAMA_CLOUD_API_KEY
from dotenv import load_dotenv
load_dotenv()

# bring in deps
from llama_extract import LlamaExtract

# set up extractor
extractor = LlamaExtract()

# infer a schema from the files
extraction_schema = extractor.infer_schema("Our Schema", ["data/file1.pdf", "data/file2.pdf"])

# extract data using the inferred schema
results = extractor.extract(
    extraction_schema.id,
    ["data/file3.pdf", "data/file4.pdf"],
)

print(results)

Now run it like any python file:

python extract.py

This will print the results of the extraction, containg the data extracted and other additional info.