快速入门

from llama_cloud_services import LlamaParse

parser = LlamaParse(
    api_key="llx-...",  # can also be set in your env as LLAMA_CLOUD_API_KEY
    num_workers=4,       # if multiple files passed, split in `num_workers` API calls
    verbose=True,
    language="en",       # optionally define a language, default=en
)

# sync
result = parser.parse("./my_file.pdf")

# sync batch
results = parser.parse(["./my_file1.pdf", "./my_file2.pdf"])

# async
result = await parser.aparse("./my_file.pdf")

# async batch
results = await parser.aparse(["./my_file1.pdf", "./my_file2.pdf"])

# get the llama-index markdown documents
markdown_documents = result.get_markdown_documents(split_by_page=True)

# get the llama-index text documents
text_documents = result.get_text_documents(split_by_page=False)

# get the image documents
image_documents = result.get_image_documents(
    include_screenshot_images=True,
    include_object_images=False,
    # Optional: download the images to a directory
    # (default is to return the image bytes in ImageDocument objects)
    image_download_dir="./images",
)

# access the raw job result
# Items will vary based on the parser configuration
for page in result.pages:
    print(page.text)
    print(page.md)
    print(page.images)
    print(page.layout)
    print(page.structuredData)

import {
  LlamaParseReader,
  // we'll add more here later
} from "llama-cloud-services";
import 'dotenv/config'

async function main() {
  // save the file linked above as sf_budget.pdf, or change this to match
  const path = "./canada.pdf";

  // set up the llamaparse reader
  const reader = new LlamaParseReader({ resultType: "markdown" });

  // parse the document
  const documents = await reader.loadData(path);

  // print the parsed document
  console.log(documents)
}

main().catch(console.error);

[
  Document {
    id_: '02f5e252-9dca-47fa-80b2-abdd902b911a',
    embedding: undefined,
    metadata: { file_path: './canada.pdf' },
    excludedEmbedMetadataKeys: [],
    excludedLlmMetadataKeys: [],
    relationships: {},
    text: '# Fun Facts About Canada\n' +
      '\n' +
      'We may be known as the Great White North, but
  ...etc...