Dataku

Accepts free-form natural language instructions to extract structured data from unstructured sources (PDFs, web content, plain text) using LLM-based parsing. The system interprets user intent expressed in conversational language and generates extraction logic dynamically, bypassing the need for regex patterns, XPath, or custom parsing code. Internally routes requests to LLM inference endpoints that generate extraction schemas and apply them to input documents in a single pass.

Chains multiple transformation steps using natural language specifications, where each step is interpreted by an LLM to generate and apply transformations (filtering, aggregation, normalization, enrichment). The system maintains state across steps and allows users to compose complex data workflows by describing transformations in plain English rather than writing SQL or Python. Internally, each step generates a transformation function that is applied to the dataset sequentially.

Processes collections of documents (PDFs, text files, web pages) in parallel or sequential batches, applying the same extraction schema across all inputs to produce a unified structured dataset. The system maintains consistency by caching or reusing the extraction schema generated from the first document and applying it to subsequent documents, reducing redundant LLM calls and improving output uniformity. Supports both synchronous and asynchronous batch jobs with progress tracking.

Provides a user-facing interface to review extracted or transformed data, flag inconsistencies or hallucinations, and provide corrections that feed back into the extraction/transformation logic. The system uses human feedback to refine extraction schemas or transformation rules for subsequent runs, creating a feedback loop that improves accuracy over time. Corrections are stored and can be applied retroactively to previously processed documents.

Allows users to provide one or more example documents with manually annotated fields, and the system infers an extraction schema that can be applied to similar documents. The LLM analyzes the examples to understand the structure and field definitions, then generates a reusable schema without requiring explicit schema definition. This schema can be saved, versioned, and applied to new documents or batches.

Provides unrestricted access to core extraction and transformation capabilities without requiring payment, account creation, or API key management. The free tier is designed to lower barriers to entry for researchers and small teams experimenting with LLM-based data processing. No documented rate limits, quotas, or usage tracking are mentioned, suggesting either generous free allowances or a freemium model where advanced features require payment.