Developer Quickstart

pip install chunkr-ai

from chunkr_ai import Chunkr

# Initialize the Chunkr client with your API key - get this from https://chunkr.ai
chunkr = Chunkr(api_key="your_api_key")

# Upload a document via url or local file path
url = "https://chunkr-web.s3.us-east-1.amazonaws.com/landing_page/input/specs.pdf"
task = chunkr.upload(url) 

# Export HTML of document
html = task.html(output_file="output.html")

# Export markdown of document
markdown = task.markdown(output_file="output.md")

# Export text of document
content = task.content(output_file="output.txt")

# Export result as JSON - TaskResponse is already in memory so no need to load it into a variable
task.json(output_file="output.json")

# The output of the task is a list of chunks
chunks = task.output.chunks

# Each chunk is a list of segments
for chunk in chunks:
    for segment in chunk.segments:
        print(segment.segment_type)

# You can also access the `embed` field in the chunk 
# for content to be used in RAG pipelines
for chunk in chunks:
    print(chunk.embed)

chunkr.close()

from chunkr_ai import Chunkr

# Option 1: Initialize with API key directly
chunkr = Chunkr(api_key="your_api_key")

# Option 2: Initialize without api_key parameter - will use CHUNKR_API_KEY from environment
chunkr = Chunkr()

from chunkr_ai import Chunkr

# Option 1: With direct API key
chunkr = Chunkr(
    api_key="your_api_key",
    url="https://your-self-hosted-chunkr.ai"
)

# Option 2: Using environment variables
# Set CHUNKR_API_KEY and CHUNKR_URL in your .env file
chunkr = Chunkr()