Adam

Turn websites & docs into clean Markdown plus token-bounded, embeddings-ready RAG chunks (heading lineage + sha256) ready for Pinecone, Weaviate, Qdrant or pgvector. Optional no-hallucination field extraction and AEO mode (FAQ, answer-first, llms.txt, citations). Robots honored; ownership required.

Convert PDFs into token-bounded Markdown chunks for RAG, embeddings, and vector databases (Pinecone, Chroma, Weaviate, Qdrant). Set maxTokens + overlap; get clean chunks with page number, token count, and SHA-256 content hash for dedup. JSON dataset ready for any LLM pipeline.

Parse SEC EDGAR filings (10-K, 10-Q, 8-K) into section-segmented Markdown. Splits by Item headings (Item 1A Risk Factors, Item 7 MD&A) into per-section records with sha256 content hashes. RAG/LLM-ready sections, dedupe-friendly, keyless official SEC API. Pay-per-filing.

Convert any OpenAPI/Swagger spec into per-endpoint LLM tool definitions (function calling schemas) plus clean Markdown docs. Generates JSON-schema tools ready for OpenAI, Claude/Anthropic, and any agent framework. Paste a spec URL or inline JSON; deterministic, content-hashed output per endpoint.

Extract every HTML table from any URL into clean, deterministic GitHub-Flavored Markdown (GFM). Auto-detects headers (or synthesizes col1..N), escapes pipes, collapses whitespace, and stamps each table with an sha256 hash for dedup & idempotency. RAG / embeddings / LLM ready. Same HTML, same output.