BookWyrm is an API and Python SDK for automating repetitive tasks that hinder productivity. Optimize throughput and deliver ROI.
Recent reports from MIT show that 95% of AI projects fail. The successful minority aren't replacing humans; they are removing the drudgery.
By automating low-complexity admin tasks, you get less overhead and more throughput.
BookWyrm transforms raw documents into AI-ready data, giving you the tools to automate structured extraction and ground your agents with precise citations.
Looking to implement automated workflows? Read our blog outlining a formula to build learning-capable, autonomous workflows.
From raw documents to intelligent action
Standardize your ingestion pipeline. Convert raw documents into structured inputs optimized for RAG and agentic workflows.
Extract clean text from PDFs, Excel, CSVs, and text files. Automatically handle tables and layout noise without maintaining custom parsers.
bookwyrm extract-pdf document.pdf --output extracted.jsonBetter inputs mean better retrieval. Split text into semantic phrases rather than arbitrary character counts to preserve context.
bookwyrm phrasal --file document.txt --format with_offsets --output phrases.jsonlTurn your processed data into active workflows. Replace manual data entry and unverified answers with type-safe extraction and grounded reporting.
Don't parse strings; extract schemas. Pass a Pydantic model to the summarize endpoint to get validated JSON back—perfect for automating invoice processing or product enrichment.
bookwyrm summarize data/washingm-machine-brochure-phrases.jsonl \
--model-class-file data/product-summary.py \
--model-class-name ProductSummary \
--model-strength smart \
--output data/product-structured-summary.json \
--verboseGenerate answers, not just text. The cite endpoint scans your chunks to provide answers backed by explicit source citations, quality scores, and reasoning chains.
bookwyrm cite data/sales-forecast-chunks.jsonl
--question "What are the top three client prospects by sales value from Graham Johnson?" Discover the complete API reference and learn how to integrate BookWyrm into your workflows.
View API Documentation
The easiest way is to join our Discord server and ask for a demo. One of the team can then join you in a voice channel, show you BookWyrm's endpoints in action, and answer any questions you may have.
The BookWyrm API provides plugin endpoints to use across your AI workflows. It handles time consuming text extraction and processing tasks and provides reliable, high-fidelity data for your AI agents.
Enrich product information from marketing collateral to enhance your agentic commerce performance.
Learn how to build reliable back office automation using BookWyrm's data pipeline. Transform unstructured documents into AI-ready data for automated backoffice workflows.
Manually trawling through documents is resource intensive. BookWyrm's cite endpoint answers complex business questions by finding and verifying evidence within your source files.
Libraries and archives spend thousands of hours manually entering metadata. BookWyrm's structured summarization automates this, extracting standardized records from scanned texts, PDFs, and articles in seconds.
Use BookWyrm to automate literature review and citation extraction with verifiable sources. Build research pipelines that reduce hallucinations and ground every AI output in real, citable evidence.
A step-by-step example of how easy it is to use BookWyrm to perform various RAG tasks.
Unstructured Data
PDFs, Docs, APIs, Emails
Classify Endpoint
Route data by type
Extract / Transform
e.g. Phrasal, Extract endpoints
Task / Prompt
"Summarize", "Find", "Update"
Agent / Logic
e.g. Cite, LLM Call, Business Rule
Structured Outcome
JSON, DB Update, Answer
We are looking for startup and small enterprise builders who need an AI strategy. We have deep expertise in building real agentic pipelines. To help you bootstrap, we're offering to build some of the elements you need that we don't currently have, for free.
This isn't a sales pitch. If you're serious about BookWyrm, we want to help you succeed. Typically, we'd start with a hands-on technical workshop where we will:
Your data pipeline is the foundation for your agentic workflows. Build it right. Get started with the API that's fast to set up, easy to extend, and built for developers.
BookWyrm Discord Server